list-skills

List this project's existing, already-usable skills, grouped by connector -- each skill's real _id can be put directly into an agent's skills[] (create-process-flow's manifest mode or update-process-flow). A skill only appears here if its connector is actually connected in this project (connecting a connector auto-creates one skill per real action) -- this is the ONLY way to discover what's attachable. If the skill you need isn't returned (e.g. searching 'linear' finds nothing), that connector isn't connected yet: try provision-connector, which connects credential-free connectors and mints their skills. Connectors needing an API key or OAuth still require a human in the console. Never invent a skill id or attach a placeholder -- an un-backed skill silently does nothing when the flow actually runs.

What it is called on each surface

The wire name is list-skills everywhere: it is what the Wexa MCP server advertises, the REST path is POST /v1/list-skills, and each SDK exposes it under its own language's naming convention.

Arguments

Every argument is optional: list-skills answers a bare call.

project_id, projectID, organization_id and executed_by are not arguments you pass: the platform binds all four from the credential you authenticated with, and both SDKs refuse them before the request leaves your process — see server-bound arguments.

What it returns

The three surfaces wrap this differently, and code written against one will not read another correctly — see return shape.

A real response, captured from a live call to list-skills:

{
  "content": [
    {
      "type": "text",
      "text": "{\"lifecycle_id\":\"qlc_000173\",\"result\":{\"note\":\"no skills in this project yet, which means no connector is connected \\u2014 not that none exist. Connect a credential-free one with provision-connector (it creates one skill per action), or connect a credentialed one from the Fabric console. If you passed a category or search_key, also try again without it.\",\"skills\":[],\"total_count\":0}}"
    }
  ],
  "isError": false
}

{
  "lifecycle_id": "qlc_000173",
  "result": {
    "note": "no skills in this project yet, which means no connector is connected \u2014 not that none exist. Connect a credential-free one with provision-connector (it creates one skill per action), or connect a credentialed one from the Fabric console. If you passed a category or search_key, also try again without it.",
    "skills": [],
    "total_count": 0
  }
}

// the object you get back IS the result — there is no `.result` to read
{
  note: 'no skills in this project yet, which means no connector is connected — not that none exist. Connect a credential-free one with provision-connector (it creates one skill per action), or connect a credentialed one from the Fabric console. If you passed a category or search_key, also try again without it.',
  skills: [],
  total_count: 0
}

// The TS SDK names these camelCase — lifecycleId, traceId — where Python uses
// lifecycle_id and trace_id. Both are non-enumerable: readable, but omitted by
// Object.keys() and JSON.stringify(). `result.lifecycleId` here is undefined.
result.lifecycleId // 'qlc_000173'

# a dict subclass; `result` is already unwrapped
{
 "note": "no skills in this project yet, which means no connector is connected \u2014 not that none exist. Connect a credential-free one with provision-connector (it creates one skill per action), or connect a credentialed one from the Fabric console. If you passed a category or search_key, also try again without it.",
 "skills": [],
 "total_count": 0
}

out.lifecycle_id  # 'qlc_000173' — an attribute, not a key

Keeping the lifecycle_id is what lets you ask later why a call was allowed, refused or held.

Calling it

The same call on all four surfaces. Pick a tab once and every code block in the documentation follows it.

The ids in this example are real, and resolve against the project the documentation is written against. Swap them for your own. A value in angle brackets is one only you can supply, and the platform refuses a literal <...>.

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "list-skills",
    "arguments": {
      "category": "<category>"
    }
  }
}

curl -sS https://fabric.wexa.ai/v1/list-skills \
  -H "authorization: Bearer $FABRIC_API_KEY" \
  -H "content-type: application/json" \
  -d '{"category":"<category>"}'

import { Fabric } from '@wexa-fabric/sdk'

const fabric = new Fabric()
const { result } = await fabric.listSkills({
  category: "<category>"
})

from wexa import Fabric

fabric = Fabric()
out = fabric.list_skills(category="<category>")

Errors

Both SDKs raise the same typed errors, chosen from the gateway's own error string first and its HTTP status second. list-skills checks the fabric:orchestrate.read grant, and reaches the seven classes every tool reaches — listed under the common set. These are the ones specific to it:

Governance

Every call to list-skills runs through the same ten-stage lifecycle as every other Wexa tool: the credential is resolved to a scope, the fabric:orchestrate.read grant is checked, quota is drawn down, the arguments are validated, policy rules are evaluated, the call is executed, the result is shaped and redacted, and an audit record is written. The lifecycle_id in the response is the handle to that record.

list-skills only reads, so it is not marked consequential: it is audited lightly and is never held for approval. It still consumes quota and is still refused by policy like anything else.

See also

The tool index, errors, and which identifier goes where.