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.

72

Quality

88%

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

The canonical home for this skill is agents-md in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A well-structured, actionable instruction skill that provides concrete templates and a clear writing workflow. Its main weakness is redundancy between the 'Required Sections' templates and the 'Example Structure' section, and the absence of an explicit verification step for the stated line-count target.

Suggestions

Consolidate 'Example Structure' so it references or trims the Commit Attribution and File-Scoped Commands templates already shown under 'Required Sections' rather than duplicating them verbatim.

Add an explicit validation checkpoint after writing, e.g. 'Verify the file is under 60 lines and contains no linter/config rules duplicated from .eslintrc/biome.json/ruff.toml'.

Tighten the brief opening paragraph ('AGENTS.md is the canonical agent-facing documentation...') or fold its line-count guidance into the validation step to reduce token overhead.

DimensionReasoningScore

Conciseness

The body is lean (headers + bullets + template code blocks) and avoids explaining concepts Claude already knows, but the 'Example Structure' section duplicates the Commit Attribution block and File-Scoped Commands table already shown in 'Required Sections', so it could be tightened further.

4 / 5

Actionability

Highly actionable for an instruction-only skill: copy-paste-ready markdown templates, concrete symlink command, named lock-file/config detection lists, and command tables cover the common cases.

5 / 5

Workflow Clarity

A clear sequence exists (File Setup → Before Writing analysis → Writing Rules → Required Sections → Anti-Patterns) with the Anti-Patterns list acting as a checklist, but there is no explicit verification step for the stated 'under 60 lines; never exceed 100' target.

4 / 5

Progressive Disclosure

Well-organized into clearly labeled sections with no nested references and a self-contained structure, but at ~113 lines with some template redundancy it sits just below the fully lean, optimally split top anchor.

4 / 5

Total

17

/

20

Passed

Description

95%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 that uses third-person voice, names concrete trigger actions with relevant file names, and explicitly covers both what the skill does and when to invoke it. The only minor weakness is a somewhat generic 'what' clause ('enforces research-backed best practices'), which keeps specificity just below the top anchor.

DimensionReasoningScore

Specificity

Names several concrete actions ('create AGENTS.md', 'update AGENTS.md', 'maintain agent docs', 'set up CLAUDE.md', 'keep agent instructions concise') alongside 'Enforces research-backed best practices', but the 'what' clause is slightly generic, leaving minor gaps versus the comprehensive anchor.

4 / 5

Completeness

Explicitly answers both 'what' (enforces research-backed best practices for minimal, high-signal agent documentation) and 'when' (concrete quoted trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural user phrases, quoting exact things a user would say ('create AGENTS.md', 'set up CLAUDE.md', 'maintain agent docs') plus the relevant file names (AGENTS.md, CLAUDE.md).

5 / 5

Distinctiveness Conflict Risk

Clear niche (AGENTS.md/CLAUDE.md maintenance) with distinct, file-name-specific triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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
administrakt0r/AI-Agents-Safe-Coding-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.