Skip to main content
Glama

suggest_skills

Detect repeated multi-step workflows and topic clusters across agent sessions, then rank skill ideas to create, update, or skip against your installed skills. Returns steps, triggers, and evidence sessions.

Instructions

Suggest reusable skills from repeated work across all your agents.

Combines repeated multi-step tool workflows (the same commands/edits in the same order across sessions) with recurring topic clusters, then checks each against your installed skills: create, update , or skip. Returns ranked ideas with steps, triggers and evidence sessions. Never writes files or calls a model; use draft_skill next.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "suggest_skills"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectNo
sourcesNoall
days_backNo
min_sessionsNo
max_candidatesNo
include_workflowsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full load and does add valuable disclosure: it never writes files and never calls a model, and it distinguishes create/update/skip outcomes. It still omits what permissions or data scope it reads, whether it is expensive on long histories, and how long a scan takes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then mechanism, then output shape, then the safety caveat and next step. The parenthetical defining 'repeated multi-step tool workflows' earns its space; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be spelled out, and the description still characterizes them (ranked ideas with steps, triggers and evidence sessions). The one real gap is that six tunable parameters, including thresholds that change result volume, are left entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across six parameters, so the description should compensate and mostly does not — project, sources, days_back, min_sessions, max_candidates and include_workflows are never named. Only indirect hints exist ('across all your agents' implying the source scope, 'repeated' implying a session threshold, 'ranked ideas' implying a cap), so an agent must read the schema to tune anything.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Suggest reusable skills from repeated work') and then explains the actual mechanism: combining repeated multi-step tool workflows with recurring topic clusters and checking them against installed skills. An agent can distinguish this from suggest_rules or analyze_sessions without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear follow-on routing instruction ('use draft_skill next'), which is real when-to-use guidance for this pipeline. It does not say when to prefer this over suggest_rules or suggest_instruction_updates, nor when it is pointless to call (e.g. too little history), so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.