skill-maintenance

Create, update, validate, or reorganize repo-local Agent Skills under .agents/skills, including SKILL.md frontmatter, first-level references, compatibility symlinks, and validation scripts. Use only for skill-tree maintenance, skill taxonomy changes, or agent-guidance validation work.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an extreme router: maximally concise and correctly structured for progressive disclosure, with a real, well-scoped first-level reference. Its weakness is thin actionability and workflow clarity — no inline quick-start command or ordered edit→validate sequence, so the agent must read the reference before it can act on anything.

Suggestions

Add a one-line inline quick start (e.g., the pnpm validate:agent-skills command) so the most common action is executable without opening the reference.

State the core workflow order explicitly in the body — edit skill folder, then run validation, then verify the compatibility symlink — rather than only a 'read the reference first' precondition.

Briefly enumerate what the reference covers as labeled pointers (e.g., '**Format rules**: references/skill-format.md; '**Validation**: references/skill-format.md#validation') so navigation to the right section is self-evident.

Dimension	Reasoning	Score
Conciseness	The body is three lean lines with zero padding — no concept explanations, no restating of known information — so every token earns its place, matching the 5 anchor exactly.	5 / 5
Actionability	The only directive is "Read `references/skill-format.md` before changing skill folders, validation, or compatibility mirrors" — a concrete, real pointer, but all executable detail (commands, format rules) is deferred to the reference, leaving the body itself with incomplete guidance between the 3 and 4 anchors.	3 / 5
Workflow Clarity	A single unambiguous precondition (read the reference first) rather than a sequence; the create/update/validate/reorganize operations named in the description are never ordered in the body and no validation checkpoint is stated there, matching the 3 anchor (steps implicit, checkpoints missing) even though the reference file itself contains a validation section.	3 / 5
Progressive Disclosure	A short overview body with one clearly signaled, one-level-deep reference (references/skill-format.md, 48 lines) that exists and covers exactly what the body promises (folders, validation, compatibility mirrors), matching the 5 anchor.	5 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete verb-driven capability list, named artifacts, and an explicit 'Use only for' trigger clause that sharply bounds routing. The only weakness is occasional jargon in the trigger terms (e.g., 'skill taxonomy changes') that a user would be unlikely to say verbatim.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ("Create, update, validate, or reorganize") and specific artifacts ("SKILL.md frontmatter, first-level references, compatibility symlinks, and validation scripts"), matching the comprehensive-coverage anchor; no coverage gaps place it below the 5 anchor.	5 / 5
Completeness	Explicitly answers what (first sentence enumerating actions and artifacts) and when ("Use only for skill-tree maintenance, skill taxonomy changes, or agent-guidance validation work") with concrete trigger phrases, matching the 5 anchor rather than the 4 anchor whose 'when' could be more explicit.	5 / 5
Trigger Term Quality	Good keyword coverage with natural terms ("Agent Skills", "skill-tree maintenance", "validation") and a concrete path (.agents/skills), but phrases like "skill taxonomy changes" and "agent-guidance validation work" are jargon users would rarely say, so it falls between the good-coverage (4) and some-keywords (3) anchors — closer to 4.	4 / 5
Distinctiveness Conflict Risk	Scoped to repo-local Agent Skill tree maintenance with an explicit "Use only for" boundary clause, giving a clear niche with minimal overlap with other skills — a clean fit for the 5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ComposioHQ/composio
Path: .agents/skills/skill-maintenance/SKILL.md
Commit: 98b10d7

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.