CtrlK
BlogDocsLog inGet started
Tessl Logo

agents-md

This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.

67

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The content is highly actionable and well-organized with copy-paste templates and a clear process sequence. The main gaps are mild redundancy from the duplicated Example Structure section and the absence of explicit verification checkpoints in the workflow.

Suggestions

Add an explicit validation step at the end of the workflow, e.g. 'Verify the result: count lines (must be < 60, never > 100) and run `readlink CLAUDE.md` to confirm the symlink resolves' — this turns the implicit length/symlink constraints into a checkpoint.

Collapse the 'Example Structure' section into a reference back to the Required Sections templates (or trim it to only the parts not already shown) to remove the duplication and tighten token usage.

Optionally fold the 'Before Writing' analysis checklist into the workflow as numbered step 1 with a checkpoint ('Confirm all five checks completed before drafting'), making the multi-step sequence and its gate explicit.

DimensionReasoningScore

Conciseness

The body is mostly efficient (headers + bullets, no filler prose, no concept explanations Claude already knows), but the 'Example Structure' section largely duplicates the 'Required Sections' templates and the file-length guidance is restated, so it could be tightened to earn a 3.

2 / 3

Actionability

Guidance is concrete and copy-paste ready throughout: an explicit symlink command, a numbered project-analysis checklist with named lock-file/config filenames, and fully worked markdown templates with table formats for each required section.

3 / 3

Workflow Clarity

A clear sequence exists (File Setup → Before Writing → Writing Rules → Required Sections), but there are no explicit validation checkpoints (e.g. 'verify the file is under 60 lines', 'confirm the symlink resolves'), so checkpoints are implicit rather than enforced.

2 / 3

Progressive Disclosure

The skill is a single self-contained file with clear, well-organized sections and no nested references; it appropriately tells the agent to 'reference, don't embed' and points one level deep to existing project docs (CONTRIBUTING.md, src/api/routes/), so the simple-skill exception applies.

3 / 3

Total

10

/

12

Passed

Description

90%

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 has strong, natural trigger coverage, clear when-guidance, and a distinct niche. Its only weakness is the abstract capability statement, which relies on vague phrasing ('research-backed best practices') rather than naming the concrete actions the skill performs.

Suggestions

Replace the abstract capability clause 'Enforces research-backed best practices for minimal, high-signal agent documentation' with concrete actions, e.g. 'Generates a minimal AGENTS.md (symlinked as CLAUDE.md) under 60 lines, derived from the project's actual toolchain and repo layout.'

Keep the quoted trigger phrases — they are the strongest part of the description and should be preserved verbatim.

DimensionReasoningScore

Specificity

Trigger clauses name concrete actions ('create AGENTS.md', 'update AGENTS.md', 'maintain agent docs', 'set up CLAUDE.md'), but the core capability statement — 'Enforces research-backed best practices for minimal, high-signal agent documentation' — is abstract and does not concretely describe what the skill does, so it is not a comprehensive 3.

2 / 3

Completeness

It explicitly answers both what ('Enforces research-backed best practices for minimal, high-signal agent documentation') and when ('should be used when the user asks to ...'), with explicit trigger guidance, satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Multiple natural phrasings a user would actually say appear verbatim ('create AGENTS.md', 'update AGENTS.md', 'maintain agent docs', 'set up CLAUDE.md', 'keep agent instructions concise'), giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The triggers are scoped to a clear niche (AGENTS.md / CLAUDE.md / agent docs) with distinct terms, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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/antigravity-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.