CtrlK
BlogDocsLog inGet started
Tessl Logo

agents-md

Create, revise, or audit AGENTS.md files from repository evidence, verified commands, and correctly scoped instructions without overwriting maintainer intent.

60

Quality

70%

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 ./skills/agents-md/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 content is a well-structured, actionable guide with an excellent validation workflow for a state-changing skill. Its main weakness is moderate redundancy across the Best Practices, Pitfalls, and Limitations sections that inflates token cost without adding new guidance.

Suggestions

Consolidate overlapping guidance between 'How It Works', 'Best Practices', and 'Common Pitfalls' to remove repeated rules such as 'do not invent commands' and 'prefer repository-specific decisions'.

Tighten the 'Limitations' section to points not already implied by the workflow steps.

Consider moving the worked 'Examples' markdown block into a reference file if the skill grows, to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient with direct statements and specific commands, but the Best Practices, Common Pitfalls, and Limitations sections repeat guidance already covered in How It Works and could be tightened.

3 / 5

Actionability

Provides concrete, executable guidance such as 'npm ci', 'npm test -- path/to/file.test.ts', and 'rg --files', plus concrete markdown examples, with only minor gaps.

4 / 5

Workflow Clarity

A clear five-step sequence ends with an explicit 'Validate before handoff' checklist (re-read, remove contradictions, confirm files exist, cross-check commands), giving this state-changing skill proper validation checkpoints and a feedback loop.

5 / 5

Progressive Disclosure

The single file is well-organized into clearly signaled sections with no nested references and no separate bundle files needed, though a few sections overlap and could be consolidated.

4 / 5

Total

16

/

20

Passed

Description

66%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.

The description is specific and distinct, naming concrete actions and a clear AGENTS.md niche, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a 'Use when...' clause would lift the strongest remaining weakness.

Suggestions

Append an explicit trigger clause such as 'Use when the user asks to create, update, shorten, or audit an AGENTS.md file' to satisfy the 'when' half of completeness.

Add natural synonyms users might say ('agent instructions', 'agent config file') to broaden trigger-term coverage.

Distinguish from @agents-generator directly in the description (e.g., 'for evidence-first edits rather than packaged generation') to reduce overlap risk.

DimensionReasoningScore

Specificity

Names the domain (AGENTS.md files) and three concrete actions ('Create, revise, or audit') grounded in 'repository evidence, verified commands', with only minor gaps in coverage compared to a fully comprehensive enumeration.

4 / 5

Completeness

Clearly states what the skill does, but lacks an explicit 'Use when...' trigger clause; per the rubric guideline, a missing explicit trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('AGENTS.md', 'create', 'revise', 'audit') with good coverage, but misses common synonyms such as 'agent instructions' or 'agent config'.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (AGENTS.md files) with distinct triggers, though minor overlap risk exists with the closely related @agents-generator skill noted in the body.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/agentic-awesome-skills
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.