Skip to main content
Glama

ck_skill_evolution

Read-onlyIdempotent

Synthesize a deduplicated skill-evolution packet from recent traces and recurring failure clusters, with optional validation and installation of the proposed skill draft.

Instructions

Synthesize a deduplicated skill-evolution packet from recent traces and recurring failure clusters, including anti-patterns, reinforced practices, and a ready-to-merge skill draft. Set validate_only=true to run the Self-Harness validation stage (held-in/held-out + regression) without writing. Set install=true to validate and then materialize the draft into .agents/skills//SKILL.md under project_root, preserving the previous file as .bak.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
installNoWhen true, validate the packet and, only if accepted, write the suggested skill document to .agents/skills/<name>/SKILL.md under project_root. The previous file is preserved as <path>.bak for rollback. Requires project_root.
session_idNoUnique session identifier for correlating findings, proofs, budget, and audit trail.
project_rootNoAbsolute path to the project root directory on the local filesystem. Required for install mode.
session_limitNoMaximum number of sessions to analyze.
validate_onlyNoWhen true, run the Self-Harness validation stage (static, held-in, held-out, regression) and return the verdict without writing any files.
same_domain_onlyNoWhen true, restrict results to sessions in the same domain.
current_skill_nameNoName of the existing skill to compare against for evolution.
current_skill_contentNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
installNo
guidanceNo
validationNo
anti_patternsNo
merge_strategyNo
reinforced_practicesNo
suggested_skill_documentNo
Behavior1/5

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

The description states the tool writes files when install=true, contradicting annotations (readOnlyHint=true). This is a serious inconsistency, so transparency is poor despite description being explicit about writing.

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?

Two efficient sentences: first states purpose, second explains key parameters. No unnecessary words. Front-loaded and to the point.

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?

Given the tool has 8 parameters, an output schema, and annotations, the description covers core behavior and modes. Missing details on parameter interactions (e.g., both flags set) but schema covers individual params.

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 coverage is high (88%), so schema already documents most parameters. The description adds meaning for validate_only and install, but for other parameters it provides no additional semantics beyond schema.

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?

The description clearly states the tool synthesizes a deduplicated skill-evolution packet from traces and failure clusters, including anti-patterns and a draft. This distinguishes it from siblings like ck_skill_list, ck_skill_load, and ck_skill_validate.

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?

The description explains two modes (validate_only and install) and when to set project_root. It provides clear context for using the tool, though it does not explicitly compare to alternatives like ck_skill_validate.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aryaminus/controlkeel'

If you have feedback or need assistance with the MCP directory API, please join our Discord server