com.useaiblocks/libraryv3.0.0 Domain verified
Search and load free AI skills, workflows, agents and prompts. Read-only, no sign-in.
Maintain this server? Claim it
Try it
Call this server's tools from your browser. Nothing to install.
https://useaiblocks.com/mcp
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
advance_outcome Read-only
Apply one event to an engagement. Before the run: brief (the pinned-down outcome), plan (research and the composed plan, checked against our rules and the live catalogue), approve_plan (owner only). During the run: data, start, complete (with outputs and checks), approve (owner only), skip, block, reopen, next_round; a plan event during the run is a revision. autonomy (owner only) works any time. Every problem in an event comes back at once, with its field path.
One event. type picks the fields: brief, plan (research + plan), approve_plan, data, start, complete, approve, skip, block, reopen, autonomy, next_round.
The complete engagement.json from the last outcome tool result, unchanged.
engagement_sha256 from the last outcome tool result. A different value means the engagement changed.
Install
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http library https://useaiblocks.com/mcp
Tools (17)
advance_outcomeApply one event to an engagement. Before the run: brief (the pinned-down outcome), plan (research and the composed plan, checked against our rules and the live catalogue), approve_plan (owner only). During the run: data, start, complete (with outputs and checks), approve (owner only), skip, block, reopen, next_round; a plan event during the run is a revision. autonomy (owner only) works any time. Every problem in an event comes back at once, with its field path.
read-only
advance_outcome
Apply one event to an engagement. Before the run: brief (the pinned-down outcome), plan (research and the composed plan, checked against our rules and the live catalogue), approve_plan (owner only). During the run: data, start, complete (with outputs and checks), approve (owner only), skip, block, reopen, next_round; a plan event during the run is a revision. autonomy (owner only) works any time. Every problem in an event comes back at once, with its field path.
| Argument | Type | Description |
|---|---|---|
| event* | any | One event. type picks the fields: brief, plan (research + plan), approve_plan, data, start, complete, approve, skip, block, reopen, autonomy, next_round. |
| engagement* | object | The complete engagement.json from the last outcome tool result, unchanged. |
| engagement_sha256* | string | engagement_sha256 from the last outcome tool result. A different value means the engagement changed. |
Input schema (JSON)
{
"type": "object",
"required": [
"engagement",
"engagement_sha256",
"event"
],
"properties": {
"event": {
"oneOf": [
{
"type": "object",
"required": [
"type",
"brief"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"type": {
"const": "brief"
},
"brief": {
"type": "object",
"required": [
"outcome",
"deliverable",
"done",
"data_home",
"decides"
],
"properties": {
"done": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 20,
"minItems": 1
},
"assets": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 30
},
"limits": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 20
},
"metric": {
"type": [
"object",
"null"
],
"required": [
"name",
"direction",
"unit",
"baseline_source"
],
"properties": {
"name": {
"type": "string",
"maxLength": 200
},
"unit": {
"type": "string",
"maxLength": 60
},
"target": {
"type": [
"number",
"null"
]
},
"baseline": {
"type": [
"number",
"null"
]
},
"direction": {
"enum": [
"decrease",
"increase",
"reach"
],
"type": "string"
},
"baseline_source": {
"enum": [
"reported",
"verified",
"unknown"
],
"type": "string"
}
},
"additionalProperties": false
},
"answers": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"question",
"answer"
],
"properties": {
"answer": {
"type": "string",
"maxLength": 2000
},
"question": {
"type": "string",
"maxLength": 500
}
},
"additionalProperties": false
},
"maxItems": 40
},
"decides": {
"type": "string",
"maxLength": 300
},
"outcome": {
"type": "string",
"maxLength": 1000
},
"ambition": {
"type": [
"object",
"null"
],
"required": [
"goal_beyond",
"rungs",
"chosen",
"judge"
],
"properties": {
"judge": {
"type": "string",
"maxLength": 500
},
"rungs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 3,
"minItems": 3
},
"chosen": {
"type": "integer",
"maximum": 3,
"minimum": 1
},
"goal_beyond": {
"type": "string",
"maxLength": 500
}
},
"additionalProperties": false
},
"deadline": {
"type": [
"string",
"null"
],
"maxLength": 200
},
"unknowns": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 20
},
"data_home": {
"type": "string",
"maxLength": 300
},
"guardrails": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"maxLength": 500
},
"maxItems": 15
},
"connections": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"name",
"access",
"status"
],
"properties": {
"name": {
"type": "string",
"maxLength": 200
},
"access": {
"enum": [
"read",
"draft",
"live"
],
"type": "string"
},
"status": {
"enum": [
"connected",
"available",
"missing"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 30
},
"deliverable": {
"type": "string",
"maxLength": 600
},
"technical_level": {
"type": [
"string",
"null"
],
"maxLength": 300
}
},
"additionalProperties": false
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"research",
"plan"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"plan": {
"type": "object",
"required": [
"name",
"stages"
],
"properties": {
"data": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"id",
"name",
"why",
"routes"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"why": {
"type": "string",
"maxLength": 600
},
"name": {
"type": "string",
"maxLength": 200
},
"fields": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"maxLength": 200
},
"maxItems": 30
},
"routes": {
"type": "array",
"items": {
"type": "object",
"required": [
"kind",
"how"
],
"properties": {
"how": {
"type": "string",
"maxLength": 600
},
"kind": {
"enum": [
"MCP",
"CSV",
"FILE",
"URL",
"ASK"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 6,
"minItems": 1
},
"alternative": {
"type": [
"string",
"null"
],
"maxLength": 600
},
"required_for": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 40
}
},
"additionalProperties": false
},
"maxItems": 20
},
"name": {
"type": "string",
"maxLength": 160
},
"stages": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"kind",
"name",
"goal",
"owner",
"gate"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"data": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 40
},
"gate": {
"enum": [
"none",
"review",
"approve",
"approve_each_action"
],
"type": "string"
},
"goal": {
"type": "string",
"maxLength": 1500
},
"kind": {
"enum": [
"intake",
"context",
"evidence",
"integrity",
"diagnosis",
"options",
"decision",
"production",
"execution",
"measurement",
"learning"
],
"type": "string"
},
"name": {
"type": "string",
"maxLength": 120
},
"uses": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$"
},
"maxItems": 20
},
"needs": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 40
},
"owner": {
"type": "object",
"required": [],
"properties": {
"gap": {
"type": [
"string",
"null"
],
"maxLength": 500
},
"role": {
"type": [
"string",
"null"
],
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"description": "One of: role (a find_specialist id) or gap (the expert you needed when none fits).",
"additionalProperties": false
},
"checks": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"id",
"name"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"name": {
"type": "string",
"maxLength": 500
},
"required": {
"type": [
"boolean",
"null"
]
}
},
"additionalProperties": false
},
"maxItems": 12
},
"outputs": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"id",
"name",
"format",
"path"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"name": {
"type": "string",
"maxLength": 250
},
"path": {
"type": "string",
"maxLength": 200
},
"format": {
"type": "string",
"maxLength": 40
}
},
"additionalProperties": false
},
"maxItems": 12
},
"support": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 8
},
"reviewers": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 6
},
"depends_on": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 40
},
"from_steps": {
"type": [
"array",
"null"
],
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 10
},
"optional_when": {
"type": [
"string",
"null"
],
"maxLength": 500
}
},
"additionalProperties": false
},
"maxItems": 30,
"minItems": 1
},
"dropped": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"step",
"reason"
],
"properties": {
"step": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"reason": {
"type": "string",
"maxLength": 500
}
},
"additionalProperties": false
},
"maxItems": 30
},
"hypotheses": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"id",
"statement",
"test",
"confirm_if",
"refute_if",
"fix_stage"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"test": {
"type": "string",
"maxLength": 800
},
"fix_stage": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"refute_if": {
"type": "string",
"maxLength": 500
},
"statement": {
"type": "string",
"maxLength": 400
},
"confirm_if": {
"type": "string",
"maxLength": 500
}
},
"additionalProperties": false
},
"maxItems": 30
},
"measurement": {
"type": [
"object",
"null"
],
"required": [
"window",
"min_volume",
"stop_rule"
],
"properties": {
"window": {
"type": "string",
"maxLength": 300
},
"stop_rule": {
"type": "string",
"maxLength": 500
},
"min_volume": {
"type": "string",
"maxLength": 300
}
},
"additionalProperties": false
},
"capabilities": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"id",
"access",
"via",
"name",
"why"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"via": {
"enum": [
"mcp",
"api_key",
"file",
"browser",
"owner"
],
"type": "string"
},
"why": {
"type": "string",
"maxLength": 500
},
"name": {
"type": "string",
"maxLength": 200
},
"access": {
"enum": [
"read",
"draft",
"live"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 25
}
},
"additionalProperties": false
},
"type": {
"const": "plan"
},
"research": {
"type": "object",
"required": [
"approach",
"sources",
"steps"
],
"properties": {
"steps": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"name",
"why",
"sources"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"why": {
"type": "string",
"maxLength": 800
},
"name": {
"type": "string",
"maxLength": 200
},
"sources": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 10,
"minItems": 1
}
},
"additionalProperties": false
},
"maxItems": 30,
"minItems": 1
},
"sources": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"kind",
"title",
"ref"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"ref": {
"type": "string",
"maxLength": 600
},
"date": {
"type": [
"string",
"null"
],
"pattern": "^\\d{4}-\\d{2}(-\\d{2})?$"
},
"kind": {
"enum": [
"web",
"catalogue",
"memory",
"owner"
],
"type": "string"
},
"note": {
"type": [
"string",
"null"
],
"maxLength": 500
},
"title": {
"type": "string",
"maxLength": 300
}
},
"description": "web: full https link and date; catalogue: an item id; memory or owner: where it came from.",
"additionalProperties": false
},
"maxItems": 40,
"minItems": 2
},
"approach": {
"type": "string",
"maxLength": 3000
},
"pitfalls": {
"type": [
"array",
"null"
],
"items": {
"type": "object",
"required": [
"text",
"sources"
],
"properties": {
"text": {
"type": "string",
"maxLength": 500
},
"sources": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 10,
"minItems": 1
}
},
"additionalProperties": false
},
"maxItems": 20
}
},
"additionalProperties": false
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"decision",
"by"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"by": {
"type": "string",
"description": "\"owner\", only after the owner actually said so."
},
"note": {
"type": "string",
"maxLength": 2000
},
"type": {
"const": "approve_plan"
},
"decision": {
"enum": [
"APPROVED",
"CHANGES_REQUESTED"
],
"type": "string"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"data_id",
"status"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"note": {
"type": "string",
"maxLength": 1000
},
"type": {
"const": "data"
},
"status": {
"enum": [
"AVAILABLE",
"MISSING"
],
"type": "string"
},
"data_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"stage_id"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"type": {
"const": "start"
},
"stage_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"stage_id",
"outputs",
"checks"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"type": {
"const": "complete"
},
"checks": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"result"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"note": {
"type": "string",
"maxLength": 1000
},
"result": {
"enum": [
"PASS",
"FAIL",
"NOT_RUN"
],
"type": "string"
}
},
"additionalProperties": false
}
},
"outputs": {
"type": "array",
"items": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"path": {
"type": "string",
"maxLength": 240
},
"sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
},
"additionalProperties": false
}
},
"summary": {
"type": "string",
"maxLength": 2000
},
"stage_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"stage_id",
"decision",
"by"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"by": {
"type": "string",
"description": "\"owner\", only after the owner actually said so."
},
"note": {
"type": "string",
"maxLength": 2000
},
"type": {
"const": "approve"
},
"decision": {
"enum": [
"APPROVED",
"CHANGES_REQUESTED"
],
"type": "string"
},
"stage_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"stage_id",
"reason"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"type": {
"const": "skip"
},
"reason": {
"type": "string",
"maxLength": 1000
},
"stage_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"stage_id",
"reason"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"type": {
"const": "block"
},
"reason": {
"type": "string",
"maxLength": 1000
},
"stage_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"stage_id"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"type": {
"const": "reopen"
},
"stage_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"level",
"by"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"by": {
"type": "string",
"description": "\"owner\", only after the owner actually said so."
},
"note": {
"type": "string",
"maxLength": 1000
},
"type": {
"const": "autonomy"
},
"level": {
"type": "integer",
"maximum": 3,
"minimum": 0
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"note": {
"type": "string",
"maxLength": 1000
},
"type": {
"const": "next_round"
}
},
"additionalProperties": false
}
],
"description": "One event. type picks the fields: brief, plan (research + plan), approve_plan, data, start, complete, approve, skip, block, reopen, autonomy, next_round."
},
"engagement": {
"type": "object",
"description": "The complete engagement.json from the last outcome tool result, unchanged."
},
"engagement_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "engagement_sha256 from the last outcome tool result. A different value means the engagement changed."
}
},
"additionalProperties": false
}fetchRead one item by the id from search (such as skill/ad-angle-planner): its full text (the SKILL.md, or the AI tool or mini tool record), url to cite and metadata. Text over 48,000 characters is cut; metadata.rest says how to read the rest.
read-only
fetch
Read one item by the id from search (such as skill/ad-angle-planner): its full text (the SKILL.md, or the AI tool or mini tool record), url to cite and metadata. Text over 48,000 characters is cut; metadata.rest says how to read the rest.
| Argument | Type | Description |
|---|---|---|
| id* | string | An id from search. |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "An id from search."
}
},
"additionalProperties": false
}find_specialistFind worker candidates for a deliverable. Compare their remit and outputs, then use prepare_specialist to onboard the chosen worker. Keep unrelated private context out of discovery.
read-only
find_specialist
Find worker candidates for a deliverable. Compare their remit and outputs, then use prepare_specialist to onboard the chosen worker. Keep unrelated private context out of discovery.
| Argument | Type | Description |
|---|---|---|
| area | string | |
| task* | string | |
| limit | integer |
Input schema (JSON)
{
"type": "object",
"required": [
"task"
],
"properties": {
"area": {
"type": "string",
"maxLength": 80,
"minLength": 1
},
"task": {
"type": "string",
"maxLength": 3000,
"minLength": 1
},
"limit": {
"type": "integer",
"maximum": 10,
"minimum": 1
}
},
"additionalProperties": false
}get_itemGet one item of any kind by the id from search_library: an agent, prompt, mind, AI tool or mini tool (skills and workflows work too). Concise (default): what it does, inputs and outputs, how to use it, files or links, and for AI tools the price, limits and when we last checked. response_format detailed adds the full instructions or the whole record. Cite its url.
read-only
get_item
Get one item of any kind by the id from search_library: an agent, prompt, mind, AI tool or mini tool (skills and workflows work too). Concise (default): what it does, inputs and outputs, how to use it, files or links, and for AI tools the price, limits and when we last checked. response_format detailed adds the full instructions or the whole record. Cite its url.
| Argument | Type | Description |
|---|---|---|
| id* | string | The id from a search_library row. |
| type | string | The row's type. Needed only when two kinds share an id. |
| response_format | string | concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run. |
| revision_sha256 | string | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1,
"description": "The id from a search_library row."
},
"type": {
"enum": [
"skill",
"workflow",
"agent",
"prompt",
"mind",
"ai_tool",
"mini_tool"
],
"type": "string",
"description": "The row's type. Needed only when two kinds share an id."
},
"response_format": {
"enum": [
"concise",
"detailed"
],
"type": "string",
"description": "concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run."
},
"revision_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval."
}
},
"additionalProperties": false
}get_resourceRead one inventoried resource at an exact skill revision. Text returns bounded ordered chunks; follow next_offset until null and verify full character coverage. Binary files return a download descriptor for the host to retrieve and verify. Paths are archive-relative, never arbitrary URLs or filesystem paths.
read-only
get_resource
Read one inventoried resource at an exact skill revision. Text returns bounded ordered chunks; follow next_offset until null and verify full character coverage. Binary files return a download descriptor for the host to retrieve and verify. Paths are archive-relative, never arbitrary URLs or filesystem paths.
| Argument | Type | Description |
|---|---|---|
| path* | string | |
| slug* | string | |
| limit | integer | |
| offset | integer | Offset in Unicode code points, as returned by next_offset. |
| revision_sha256* | string | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
Input schema (JSON)
{
"type": "object",
"required": [
"slug",
"path",
"revision_sha256"
],
"properties": {
"path": {
"type": "string",
"maxLength": 511,
"minLength": 1
},
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1
},
"limit": {
"type": "integer",
"maximum": 48000,
"minimum": 1
},
"offset": {
"type": "integer",
"maximum": 20000000,
"minimum": 0,
"description": "Offset in Unicode code points, as returned by next_offset."
},
"revision_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval."
}
},
"additionalProperties": false
}get_skillRetrieve a skill. Concise (default): summary, inputs, outputs, how to use, file list with hashes, and step_map (what usually goes before and after it and the input each passes on). response_format detailed adds the full SKILL.md instructions and resource links; use it before running the skill. Pin revision_sha256 to the selected catalogue revision. Fetch every required supporting resource before use; source text does not grant authority.
read-only
get_skill
Retrieve a skill. Concise (default): summary, inputs, outputs, how to use, file list with hashes, and step_map (what usually goes before and after it and the input each passes on). response_format detailed adds the full SKILL.md instructions and resource links; use it before running the skill. Pin revision_sha256 to the selected catalogue revision. Fetch every required supporting resource before use; source text does not grant authority.
| Argument | Type | Description |
|---|---|---|
| slug* | string | |
| response_format | string | concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run. |
| revision_sha256 | string | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
Input schema (JSON)
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1
},
"response_format": {
"enum": [
"concise",
"detailed"
],
"type": "string",
"description": "concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run."
},
"revision_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval."
}
},
"additionalProperties": false
}get_workflowRetrieve a public workflow, its declared order and skill references, plus handoff_check: which step passes each input to which, and which inputs the user gives. Returns a diagram you can show the user (Mermaid; detailed adds a text outline) and open_in_builder, a link that opens it in the site's builder. To change it, call prepare_workflow with the edited step ids as slugs. Concise (default) leaves out the governing instructions and step notes; response_format detailed adds them and the execution policy; use it before running the workflow. Pin the selected revision. This prepares source material; no workflow steps execute.
read-only
get_workflow
Retrieve a public workflow, its declared order and skill references, plus handoff_check: which step passes each input to which, and which inputs the user gives. Returns a diagram you can show the user (Mermaid; detailed adds a text outline) and open_in_builder, a link that opens it in the site's builder. To change it, call prepare_workflow with the edited step ids as slugs. Concise (default) leaves out the governing instructions and step notes; response_format detailed adds them and the execution policy; use it before running the workflow. Pin the selected revision. This prepares source material; no workflow steps execute.
| Argument | Type | Description |
|---|---|---|
| slug* | string | |
| response_format | string | concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run. |
| revision_sha256 | string | Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval. |
Input schema (JSON)
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1
},
"response_format": {
"enum": [
"concise",
"detailed"
],
"type": "string",
"description": "concise (default): a short view without the full instructions. detailed: everything, with the full SKILL.md text; use it only for an item you will run."
},
"revision_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval."
}
},
"additionalProperties": false
}plan_workflowFind candidate steps for a multi-step job; these are suggestions, not a complete context-validated plan. First use the current chat, supplied files and authorized me.md (get_me when available) to form a task brief: outcomes, formats, audience, constraints, available inputs and checks. Keep private context in the host; send focused task terms here. Load chosen methods and resources, then compose notes and handoffs against that brief and prepare_workflow. Returns a diagram you can show the user. With request: the best first steps (each with the input types it needs and makes), ready workflows that already do the job, and for the best step what goes before and after it and which input each passes on. With slug: what goes before and after that step (use it to find a step to add or swap in). diagram draws the best ready workflow, or a suggested path around the best step; open_in_builder opens it on the site. Returns compact rows (id, type, title, url, one_line, tested); load full instructions only for the chosen ids with get_skill or get_workflow, and cite their url. Plain code; does not use a server-side model.
read-only
plan_workflow
Find candidate steps for a multi-step job; these are suggestions, not a complete context-validated plan. First use the current chat, supplied files and authorized me.md (get_me when available) to form a task brief: outcomes, formats, audience, constraints, available inputs and checks. Keep private context in the host; send focused task terms here. Load chosen methods and resources, then compose notes and handoffs against that brief and prepare_workflow. Returns a diagram you can show the user. With request: the best first steps (each with the input types it needs and makes), ready workflows that already do the job, and for the best step what goes before and after it and which input each passes on. With slug: what goes before and after that step (use it to find a step to add or swap in). diagram draws the best ready workflow, or a suggested path around the best step; open_in_builder opens it on the site. Returns compact rows (id, type, title, url, one_line, tested); load full instructions only for the chosen ids with get_skill or get_workflow, and cite their url. Plain code; does not use a server-side model.
| Argument | Type | Description |
|---|---|---|
| slug | string | One step to map before and after. |
| limit | integer | First steps for a request (default 5), or before and after steps for a slug (default 3). |
| request | string | What the user wants, in their words. Send request or slug, not both. |
| response_format | string | concise (default): 3 steps before and after the best first step. detailed: 5, plus the optional inputs of each step and why it was picked. |
Input schema (JSON)
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1,
"description": "One step to map before and after."
},
"limit": {
"type": "integer",
"maximum": 8,
"minimum": 1,
"description": "First steps for a request (default 5), or before and after steps for a slug (default 3)."
},
"request": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "What the user wants, in their words. Send request or slug, not both."
},
"response_format": {
"enum": [
"concise",
"detailed"
],
"type": "string",
"description": "concise (default): 3 steps before and after the best first step. detailed: 5, plus the optional inputs of each step and why it was picked."
}
},
"additionalProperties": false
}prepare_outcome_patternAfter a finished round, returns the exact anonymised PATTERN.json the owner would share (names, figures, links and contact details removed) and its sha256. Only if the owner says yes to that file, call again with consent to get PATTERN-SUBMISSION.json for review by a person at AI Blocks. Nothing is sent or published.
read-only
prepare_outcome_pattern
After a finished round, returns the exact anonymised PATTERN.json the owner would share (names, figures, links and contact details removed) and its sha256. Only if the owner says yes to that file, call again with consent to get PATTERN-SUBMISSION.json for review by a person at AI Blocks. Nothing is sent or published.
| Argument | Type | Description |
|---|---|---|
| keep | array | Public words to keep, such as a platform name. |
| remove | array | More words that identify the business. |
| consent | object | |
| engagement* | object | The complete engagement.json from the last outcome tool result, unchanged. |
| experiments | string | Optional text of experiments.jsonl, to include results as relative change. |
| engagement_sha256* | string |
Input schema (JSON)
{
"type": "object",
"required": [
"engagement",
"engagement_sha256"
],
"properties": {
"keep": {
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"minLength": 1
},
"maxItems": 50,
"description": "Public words to keep, such as a platform name."
},
"remove": {
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"minLength": 1
},
"maxItems": 50,
"description": "More words that identify the business."
},
"consent": {
"type": "object",
"required": [
"pattern_sha256",
"by",
"consented",
"at"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"by": {
"enum": [
"owner"
],
"type": "string"
},
"consented": {
"type": "boolean"
},
"pattern_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
},
"additionalProperties": false
},
"engagement": {
"type": "object",
"description": "The complete engagement.json from the last outcome tool result, unchanged."
},
"experiments": {
"type": "string",
"maxLength": 100000,
"description": "Optional text of experiments.jsonl, to include results as relative change."
},
"engagement_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
},
"additionalProperties": false
}prepare_specialistSupply role_id only to load a complete base specialist: README, setup, SOUL, intake, playbook, handoff and best-practice files, pinned methods and a full ZIP download. The host AI asks task and output questions in the conversation; no website context form is required. Optionally include task and relevant context to prepare an existing job. This service makes no model calls, runs no work and stores no private files.
read-only
prepare_specialist
Supply role_id only to load a complete base specialist: README, setup, SOUL, intake, playbook, handoff and best-practice files, pinned methods and a full ZIP download. The host AI asks task and output questions in the conversation; no website context form is required. Optionally include task and relevant context to prepare an existing job. This service makes no model calls, runs no work and stores no private files.
| Argument | Type | Description |
|---|---|---|
| me | string | |
| task | string | |
| tools | string | |
| context | string | |
| role_id | string | |
| training | string | |
| deliverables | array | Actual task-specific files or outcomes. The host checks whether the worker covers them; source-method examples are not mandatory extra work. |
Input schema (JSON)
{
"type": "object",
"anyOf": [
{
"required": [
"role_id"
]
},
{
"required": [
"task"
]
}
],
"required": [],
"properties": {
"me": {
"type": "string",
"maxLength": 8000,
"minLength": 1
},
"task": {
"type": "string",
"maxLength": 3000,
"minLength": 1
},
"tools": {
"type": "string",
"maxLength": 2000,
"minLength": 1
},
"context": {
"type": "string",
"maxLength": 8000,
"minLength": 1
},
"role_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,69}$",
"maxLength": 70,
"minLength": 1
},
"training": {
"type": "string",
"maxLength": 6000,
"minLength": 1
},
"deliverables": {
"type": "array",
"items": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"maxItems": 30,
"minItems": 1,
"description": "Actual task-specific files or outcomes. The host checks whether the worker covers them; source-method examples are not mandatory extra work."
}
},
"additionalProperties": false
}prepare_workflowCheck a workflow, or a change to one. Call it whenever the user wants to see, check or change a workflow (swap, add, remove or reorder steps), and before showing any plan. Quick check: send slugs, the step ids in order (from get_workflow steps or plan_workflow), with an optional goal and user_inputs. Returns a diagram you can show the user, step_checks (is each required input made by an earlier step or given by the user, plus swap_options for each step), suggestions with reasons (insert a step that makes a missing input, reorder by data flow, swap a step, remove a repeat), the proposed steps with all but swaps applied, and open_in_builder, a link that opens the proposal in the site's builder. Also returns an unsaved portable draft, selected skill inventory, review hash and handoff_check. Send full steps with pinned revisions instead of slugs for custom notes and dependencies. Suggestions and warnings never block the draft; show them and apply only what the user approves. Does not compose with our AI, save, execute or certify approval; an approval hash never authorizes external actions.
read-only
prepare_workflow
Check a workflow, or a change to one. Call it whenever the user wants to see, check or change a workflow (swap, add, remove or reorder steps), and before showing any plan. Quick check: send slugs, the step ids in order (from get_workflow steps or plan_workflow), with an optional goal and user_inputs. Returns a diagram you can show the user, step_checks (is each required input made by an earlier step or given by the user, plus swap_options for each step), suggestions with reasons (insert a step that makes a missing input, reorder by data flow, swap a step, remove a repeat), the proposed steps with all but swaps applied, and open_in_builder, a link that opens the proposal in the site's builder. Also returns an unsaved portable draft, selected skill inventory, review hash and handoff_check. Send full steps with pinned revisions instead of slugs for custom notes and dependencies. Suggestions and warnings never block the draft; show them and apply only what the user approves. Does not compose with our AI, save, execute or certify approval; an approval hash never authorizes external actions.
| Argument | Type | Description |
|---|---|---|
| goal | string | Optional. What the workflow is for. |
| name | string | Optional. Defaults to the goal. |
| notes | string | |
| slugs | array | Step ids in order, for a quick check or a change: each pinned to its current revision and run after the one before. Send slugs or steps, not both. |
| steps | array | Full step objects with pinned revisions, notes and dependencies. Send steps or slugs, not both. |
| user_inputs | array | Input types the user will give (such as ad_copy; get_workflow lists a workflow's in handoff_check.user_inputs). The hand-off check treats them as supplied; they are not part of the draft hash. |
| custom_skills | array | |
| response_format | string | concise (default): the Mermaid diagram and 2 swap options per step. detailed: also a text outline, the proposed workflow's diagram and 4 swap options per step. |
| governing_skills | array | |
| approved_draft_hash | string | Optional host-reported hash of the exact previously reviewed draft. This field cannot establish consent or execution authorization. |
Input schema (JSON)
{
"type": "object",
"properties": {
"goal": {
"type": "string",
"maxLength": 4000,
"minLength": 1,
"description": "Optional. What the workflow is for."
},
"name": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "Optional. Defaults to the goal."
},
"notes": {
"type": "string",
"maxLength": 20000,
"minLength": 1
},
"slugs": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1
},
"maxItems": 40,
"minItems": 1,
"description": "Step ids in order, for a quick check or a change: each pinned to its current revision and run after the one before. Send slugs or steps, not both."
},
"steps": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"slug"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9_-]{0,79}$",
"maxLength": 80,
"minLength": 1
},
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1
},
"notes": {
"type": "string",
"maxLength": 4000,
"minLength": 1
},
"depends_on": {
"type": "array",
"items": {
"type": "string",
"maxLength": 80,
"minLength": 1
},
"maxItems": 40
},
"revision_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval."
}
},
"additionalProperties": false
},
"maxItems": 40,
"minItems": 1,
"description": "Full step objects with pinned revisions, notes and dependencies. Send steps or slugs, not both."
},
"user_inputs": {
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"minLength": 1
},
"maxItems": 40,
"description": "Input types the user will give (such as ad_copy; get_workflow lists a workflow's in handoff_check.user_inputs). The hand-off check treats them as supplied; they are not part of the draft hash."
},
"custom_skills": {
"type": "array",
"items": {
"type": "object",
"required": [
"slug",
"name",
"instructions"
],
"properties": {
"name": {
"type": "string",
"maxLength": 120,
"minLength": 1
},
"slug": {
"type": "string",
"pattern": "^custom-[a-z0-9-]+$",
"maxLength": 120,
"minLength": 1
},
"inputs": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"type": "string",
"maxLength": 100,
"minLength": 1
},
"required": {
"type": "boolean"
}
},
"additionalProperties": false
},
"maxItems": 40
},
"outputs": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"type": "string",
"maxLength": 100,
"minLength": 1
},
"required": {
"type": "boolean"
}
},
"additionalProperties": false
},
"maxItems": 40
},
"resources": {
"type": "array",
"items": {
"type": "object",
"required": [
"slug",
"revision_sha256"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1
},
"revision_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval."
}
},
"additionalProperties": false
},
"maxItems": 24
},
"instructions": {
"type": "string",
"maxLength": 30000,
"minLength": 1
}
},
"additionalProperties": false
},
"maxItems": 10
},
"response_format": {
"enum": [
"concise",
"detailed"
],
"type": "string",
"description": "concise (default): the Mermaid diagram and 2 swap options per step. detailed: also a text outline, the proposed workflow's diagram and 4 swap options per step."
},
"governing_skills": {
"type": "array",
"items": {
"type": "object",
"required": [
"slug",
"revision_sha256"
],
"properties": {
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1
},
"revision_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "Exact lowercase catalogue SHA-256 revision returned by discovery or retrieval."
}
},
"additionalProperties": false
},
"maxItems": 20
},
"approved_draft_hash": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "Optional host-reported hash of the exact previously reviewed draft. This field cannot establish consent or execution authorization."
}
},
"additionalProperties": false
}read_back_outcome_experimentWithout a reading: the read-back schedule for every open experiment and a routine prompt for a host scheduler (Claude Code scheduled task or cron), set up only if the owner agrees. With a reading: compares it with the registered baseline, minimum volume and guardrails; flags a guardrail breach at once; after the window, returns an honest verdict and the close payload for record_outcome_experiment. Budget and pause ideas come back as proposals for the owner; nothing is ever changed.
read-only
read_back_outcome_experiment
Without a reading: the read-back schedule for every open experiment and a routine prompt for a host scheduler (Claude Code scheduled task or cron), set up only if the owner agrees. With a reading: compares it with the registered baseline, minimum volume and guardrails; flags a guardrail breach at once; after the window, returns an honest verdict and the close payload for record_outcome_experiment. Budget and pause ideas come back as proposals for the owner; nothing is ever changed.
| Argument | Type | Description |
|---|---|---|
| reading | object | |
| schedule | object | |
| engagement* | object | The complete engagement.json from the last outcome tool result, unchanged. |
| experiments* | string | The text of experiments.jsonl. |
| engagement_sha256* | string |
Input schema (JSON)
{
"type": "object",
"required": [
"engagement",
"engagement_sha256",
"experiments"
],
"properties": {
"reading": {
"type": "object",
"required": [
"experiment_id",
"at",
"observed",
"volume",
"source"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"note": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"spend": {
"type": "object",
"required": [
"to_date",
"cap"
],
"properties": {
"cap": {
"type": "number"
},
"to_date": {
"type": "number"
}
},
"additionalProperties": false
},
"source": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "Where the numbers were read, read-only."
},
"volume": {
"type": "integer",
"minimum": 0
},
"observed": {
"type": "number"
},
"guardrails": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"held": {
"type": "boolean"
},
"name": {
"type": "string",
"maxLength": 300,
"minLength": 1
},
"note": {
"type": "string",
"maxLength": 500,
"minLength": 1
},
"limit": {
"type": "number"
},
"value": {
"type": "number"
},
"worse_if": {
"enum": [
"above",
"below"
],
"type": "string"
}
},
"additionalProperties": false
},
"maxItems": 20
},
"min_effect": {
"type": "number",
"maximum": 0.99,
"minimum": 0
},
"experiment_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
"schedule": {
"type": "object",
"properties": {
"hour": {
"type": "integer",
"maximum": 23,
"minimum": 0
},
"every_days": {
"enum": [
1,
2,
3,
7,
14
],
"type": "integer"
},
"settle_days": {
"type": "integer",
"maximum": 14,
"minimum": 0
}
},
"additionalProperties": false
},
"engagement": {
"type": "object",
"description": "The complete engagement.json from the last outcome tool result, unchanged."
},
"experiments": {
"type": "string",
"maxLength": 100000,
"description": "The text of experiments.jsonl."
},
"engagement_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$"
}
},
"additionalProperties": false
}record_outcome_decisionRecord what the owner chose, the options considered (best-ranked first), what they passed over and why. Passing over the top option needs a reason. Returns a line for decisions.jsonl and, if a durable rule was stated, a learning candidate with where to save it.
read-only
record_outcome_decision
Record what the owner chose, the options considered (best-ranked first), what they passed over and why. Passing over the top option needs a reason. Returns a line for decisions.jsonl and, if a durable rule was stated, a learning candidate with where to save it.
| Argument | Type | Description |
|---|---|---|
| decision* | object | considered is best-ranked first; passing over the top option needs a rationale. |
| engagement* | object | The complete engagement.json from the last outcome tool result, unchanged. |
| engagement_sha256* | string | engagement_sha256 from the last outcome tool result. A different value means the engagement changed. |
Input schema (JSON)
{
"type": "object",
"required": [
"engagement",
"engagement_sha256",
"decision"
],
"properties": {
"decision": {
"type": "object",
"required": [
"id",
"stage_id",
"considered",
"chosen",
"by"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"by": {
"type": "string",
"description": "\"owner\", only after the owner actually said so."
},
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"rule": {
"type": "object",
"required": [
"text",
"scope"
],
"properties": {
"text": {
"type": "string",
"maxLength": 600
},
"scope": {
"enum": [
"engagement",
"business",
"platform"
],
"type": "string"
}
},
"additionalProperties": false
},
"chosen": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"maxItems": 30
},
"given_up": {
"type": "string",
"maxLength": 1000
},
"stage_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"rationale": {
"type": "string",
"maxLength": 2000
},
"considered": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"summary"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"summary": {
"type": "string",
"maxLength": 500
}
},
"additionalProperties": false
},
"maxItems": 30,
"minItems": 1
},
"revisit_when": {
"type": "string",
"maxLength": 500
}
},
"description": "considered is best-ranked first; passing over the top option needs a rationale.",
"additionalProperties": false
},
"engagement": {
"type": "object",
"description": "The complete engagement.json from the last outcome tool result, unchanged."
},
"engagement_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "engagement_sha256 from the last outcome tool result. A different value means the engagement changed."
}
},
"additionalProperties": false
}record_outcome_experimentRegister a test before it goes live (action register: change, metric, baseline, window, minimum volume, guardrails), then close it (action close: observed, volume, guardrail results, verdict). Low volume forces INCONCLUSIVE; a broken guardrail is never a WIN. Returns a line for experiments.jsonl, a learning candidate and an anonymised outcome report the owner may choose to share.
read-only
record_outcome_experiment
Register a test before it goes live (action register: change, metric, baseline, window, minimum volume, guardrails), then close it (action close: observed, volume, guardrail results, verdict). Low volume forces INCONCLUSIVE; a broken guardrail is never a WIN. Returns a line for experiments.jsonl, a learning candidate and an anonymised outcome report the owner may choose to share.
| Argument | Type | Description |
|---|---|---|
| engagement* | object | The complete engagement.json from the last outcome tool result, unchanged. |
| experiment* | any | register before the change goes live; close with what was observed. |
| engagement_sha256* | string | engagement_sha256 from the last outcome tool result. A different value means the engagement changed. |
Input schema (JSON)
{
"type": "object",
"required": [
"engagement",
"engagement_sha256",
"experiment"
],
"properties": {
"engagement": {
"type": "object",
"description": "The complete engagement.json from the last outcome tool result, unchanged."
},
"experiment": {
"oneOf": [
{
"type": "object",
"required": [
"action",
"id",
"change",
"metric",
"baseline",
"window",
"min_volume",
"guardrails"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"action": {
"const": "register"
},
"change": {
"type": "string",
"maxLength": 1000
},
"metric": {
"type": "string",
"maxLength": 200
},
"target": {
"type": "number"
},
"window": {
"type": "object",
"required": [
"start",
"end"
],
"properties": {
"end": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"start": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
}
},
"additionalProperties": false
},
"card_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"baseline": {
"type": "number"
},
"direction": {
"enum": [
"decrease",
"increase"
],
"type": "string"
},
"guardrails": {
"type": "array",
"items": {
"type": "string",
"maxLength": 300
}
},
"min_volume": {
"type": "integer",
"minimum": 0
},
"hypothesis_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"action",
"id",
"observed",
"volume",
"guardrail_results",
"verdict"
],
"properties": {
"at": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"rule": {
"type": "object",
"required": [
"text",
"scope"
],
"properties": {
"text": {
"type": "string",
"maxLength": 600
},
"scope": {
"enum": [
"engagement",
"business",
"platform"
],
"type": "string"
}
},
"additionalProperties": false
},
"action": {
"const": "close"
},
"volume": {
"type": "integer",
"minimum": 0
},
"verdict": {
"enum": [
"WIN",
"LOSS",
"INCONCLUSIVE"
],
"type": "string"
},
"learning": {
"type": "string",
"maxLength": 1000
},
"observed": {
"type": "number"
},
"guardrail_results": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"held"
],
"properties": {
"held": {
"type": "boolean"
},
"name": {
"type": "string",
"maxLength": 300
},
"note": {
"type": "string",
"maxLength": 500
}
},
"additionalProperties": false
}
}
},
"additionalProperties": false
}
],
"description": "register before the change goes live; close with what was observed."
},
"engagement_sha256": {
"type": "string",
"pattern": "^[a-f0-9]{64}$",
"description": "engagement_sha256 from the last outcome tool result. A different value means the engagement changed."
}
},
"additionalProperties": false
}searchSearch AI Blocks in the shape ChatGPT deep research and company knowledge use: results with id, title and url. Read one with fetch. search_library does the same with filters and one-line summaries.
read-only
search
Search AI Blocks in the shape ChatGPT deep research and company knowledge use: results with id, title and url. Read one with fetch. search_library does the same with filters and one-line summaries.
| Argument | Type | Description |
|---|---|---|
| query* | string | What to look for. |
Input schema (JSON)
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "What to look for."
}
},
"additionalProperties": false
}search_libraryFind one item for a task (for a whole business goal, use start_outcome). Find skills, workflows, agents, prompts, minds, AI tools and mini tools by keywords and intent. Filters: type, job, level, tested, since (what's new). With no query, a job or since browses. Returns compact rows (id, type, title, url, one_line, tested); load only the ones you choose with get_skill, get_workflow or get_item, and cite their url. Plain search; does not use a server-side model.
read-only
search_library
Find one item for a task (for a whole business goal, use start_outcome). Find skills, workflows, agents, prompts, minds, AI tools and mini tools by keywords and intent. Filters: type, job, level, tested, since (what's new). With no query, a job or since browses. Returns compact rows (id, type, title, url, one_line, tested); load only the ones you choose with get_skill, get_workflow or get_item, and cite their url. Plain search; does not use a server-side model.
| Argument | Type | Description |
|---|---|---|
| job | string | A job id such as make-image-ads (the resource aiblocks://jobs lists them; get_item shows an item's job). |
| type | string | Only this kind of item. |
| level | string | |
| limit | integer | |
| query | string | Keywords or the user's words. Leave it out to browse with job or since. |
| since | string | ISO date. Only items added or changed on or after it; newest first when there is no query. |
| offset | integer | |
| tested | boolean | true: only items with the Safety checked label (safety scan passed and a clear list of what goes in and comes out). |
| category | string | |
| response_format | string | concise (default): compact rows. detailed: also inputs, outputs, revision, source and dates. |
Input schema (JSON)
{
"type": "object",
"properties": {
"job": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,119}$",
"maxLength": 120,
"minLength": 1,
"description": "A job id such as make-image-ads (the resource aiblocks://jobs lists them; get_item shows an item's job)."
},
"type": {
"enum": [
"skill",
"workflow",
"agent",
"prompt",
"mind",
"ai_tool",
"mini_tool"
],
"type": "string",
"description": "Only this kind of item."
},
"level": {
"enum": [
"beginner",
"advanced",
"expert"
],
"type": "string"
},
"limit": {
"type": "integer",
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "Keywords or the user's words. Leave it out to browse with job or since."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}",
"maxLength": 40,
"description": "ISO date. Only items added or changed on or after it; newest first when there is no query."
},
"offset": {
"type": "integer",
"maximum": 100000,
"minimum": 0
},
"tested": {
"type": "boolean",
"description": "true: only items with the Safety checked label (safety scan passed and a clear list of what goes in and comes out)."
},
"category": {
"type": "string",
"maxLength": 40,
"minLength": 1
},
"response_format": {
"enum": [
"concise",
"detailed"
],
"type": "string",
"description": "concise (default): compact rows. detailed: also inputs, outputs, revision, source and dates."
}
},
"additionalProperties": false
}start_outcomeThe front door for any goal or problem the owner states, in their own words. Returns a new engagement waiting for its brief, the next step and the files for outcomes/<id>/, with METHOD.md (brief frame with examples, research protocol, composition and run rules). include_example adds a worked example of a good brief, research and plan. No work runs here.
read-only
start_outcome
The front door for any goal or problem the owner states, in their own words. Returns a new engagement waiting for its brief, the next step and the files for outcomes/<id>/, with METHOD.md (brief frame with examples, research protocol, composition and run rules). include_example adds a worked example of a good brief, research and plan. No work runs here.
| Argument | Type | Description |
|---|---|---|
| request* | string | |
| started | string | |
| engagement_id | string | |
| include_example | boolean | Add the worked example (rising ad costs) to see the quality bar. Off by default; it is large. |
Input schema (JSON)
{
"type": "object",
"required": [
"request"
],
"properties": {
"request": {
"type": "string",
"maxLength": 4000,
"minLength": 1
},
"started": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"engagement_id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,79}$"
},
"include_example": {
"type": "boolean",
"description": "Add the worked example (rising ad costs) to see the quality bar. Off by default; it is large."
}
},
"additionalProperties": false
}Security checkA100/100
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 5, 2026.
- Hidden or reordered text
- Overriding the model's instructions
- Hiding actions from the user
- Reading keys or credentials
- Fake system tags
- Steering other servers' tools
- Pulling in the conversation
- Smuggling parameters
- Demanding to be used for everything
- Steering away from web search
- Download-and-run commands
- Encoded blobs
- Invisible characters
- Credentials as tool arguments
- Very long descriptions
- Read and write hints