CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/skill-maintenance/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 a well-structured but extremely thin pointer: progressive disclosure is exemplary (single real, one-level reference, clearly signaled) and it wastes almost no tokens, yet it delegates everything. It provides no inline workflow or executable guidance, so actionability and workflow clarity suffer — a user must open the reference even for the most basic action.

Suggestions

Inline a minimal quick-start with the two validation commands (`bun run validate:agent-skills` and `bun run validate:skill-routing`) so the most common action is executable without opening the reference.

Add a short 3-4 step sequence for typical tasks, e.g. edit/create skill -> update its routing probe in ts/scripts/test-skill-routing.ts -> run both validators -> only then commit, to give the body a real workflow with validation checkpoints.

State the routing-probe requirement (add/update a probe when adding or renaming a skill or rewriting a description) directly in the body, since it is the easiest requirement to miss when editing the skill tree.

DimensionReasoningScore

Conciseness

The body is three lean sentences with no concept explanations and full delegation to the reference — efficient overall. It is a 4 rather than 5 because "Use this skill when editing the repo-local skill tree" restates the description's trigger guidance and could be trimmed without losing anything.

4 / 5

Actionability

"Read `references/skill-format.md` before changing skill folders, validation, or compatibility mirrors" is a concrete, specific directive, but it is the only guidance in the body — no commands, structure rules, or steps are inlined, so key executable details (e.g. the two bun validation commands) require opening the reference. This sits between the minimal-hints anchor (2) and the mostly-executable anchor (4).

3 / 5

Workflow Clarity

The body contains no step sequence for the create/update/validate/reorganize tasks the description promises — only an implicit 'read reference, then act' — and no validation checkpoints appear in the body despite this being a maintenance task with validators and CI. The simple-skill exception does not apply since the skill is multi-task, but the coherent single pointer keeps it above the incoherent/no-sequence anchor (1).

2 / 5

Progressive Disclosure

The body is a clean overview that directly and clearly signals exactly one reference, `references/skill-format.md`, which exists in the bundle and is one level deep (it links no further reference files). Content is appropriately split: all detail lives in the reference, matching the clear-overview anchor.

5 / 5

Total

14

/

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: it names concrete actions and artifacts, answers both what and when with explicit trigger phrases, and bounds its own scope with 'Use only for'. The only weakness is slightly incomplete keyword coverage — a few natural user phrasings and the .claude/skills alias are absent.

DimensionReasoningScore

Specificity

"Create, update, validate, or reorganize repo-local Agent Skills under .agents/skills, including SKILL.md frontmatter, first-level references, compatibility symlinks, and validation scripts" lists four concrete actions and four concrete artifacts, matching the comprehensive-coverage anchor. It is not a 4 because coverage of the skill-maintenance domain is essentially complete with no notable gaps.

5 / 5

Completeness

The 'what' is explicit ("Create, update, validate, or reorganize... including SKILL.md frontmatter, first-level references, compatibility symlinks, and validation scripts") and the 'when' is explicit with concrete trigger phrases ("Use only for skill-tree maintenance, skill taxonomy changes, or agent-guidance validation work"). This matches the 5 anchor's requirement of both what and when with concrete triggers; the 'only' qualifier even adds a boundary, so it is not a 4.

5 / 5

Trigger Term Quality

Natural terms are present ("Agent Skills", "SKILL.md frontmatter", "skill-tree maintenance", ".agents/skills"), covering what a user would say when asking to add or fix a skill. It falls short of the 5 anchor because common variations like "add a new skill", "rename a skill", ".claude/skills", or "skill descriptions" are missing, and "skill taxonomy changes" leans jargon-ward.

4 / 5

Distinctiveness Conflict Risk

"Use only for skill-tree maintenance..." plus distinctive artifacts like ".agents/skills", "compatibility symlinks", and "SKILL.md frontmatter" carve out a clear niche with minimal conflict risk against generic editing or validation skills. It clearly fits the 5 anchor rather than the 4 anchor's 'minor overlap risk'.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.