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.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with excellent trigger terms and clear 'when to use' guidance. Its main weakness is that the 'what it does' portion is somewhat abstract — 'enforces research-backed best practices' doesn't tell Claude what specific actions or transformations the skill performs. Adding concrete capabilities (e.g., 'generates concise tool descriptions, defines agent boundaries, structures memory sections') would strengthen it.
Suggestions
Add specific concrete actions the skill performs beyond 'enforces best practices', e.g., 'generates concise tool descriptions, structures agent memory sections, defines role boundaries'
Rewrite to use third-person voice consistently, e.g., 'Creates and updates AGENTS.md files following research-backed best practices...'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions some actions like 'create AGENTS.md', 'update AGENTS.md', 'maintain agent docs', and 'keep agent instructions concise', but it doesn't list concrete specific capabilities beyond these. 'Enforces research-backed best practices for minimal, high-signal agent documentation' is somewhat vague about what those best practices entail. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (enforces best practices for minimal, high-signal agent documentation) and 'when' (when the user asks to create/update AGENTS.md, maintain agent docs, set up CLAUDE.md, or keep agent instructions concise). The 'Use when' guidance is clearly stated upfront. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'create AGENTS.md', 'update AGENTS.md', 'maintain agent docs', 'set up CLAUDE.md', and 'agent instructions'. These cover multiple natural variations of how a user might phrase their request. | 3 / 3 |
Distinctiveness Conflict Risk | The skill targets a very specific niche — AGENTS.md and CLAUDE.md file creation/maintenance with best practices for agent documentation. This is unlikely to conflict with other skills due to the highly specific file names and domain. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill that provides clear guidance for creating and maintaining AGENTS.md files. Its main strengths are concrete templates, executable commands, and a well-sequenced workflow. Its weaknesses are moderate verbosity—some content is redundant (example structure repeats required sections, anti-patterns list some obvious items) and the 'When to Use' and 'Limitations' sections add little value beyond what the frontmatter and Claude's judgment already provide.
Suggestions
Remove the 'When to Use' section since it duplicates the skill's trigger description in frontmatter, and remove the generic 'Limitations' boilerplate to save ~10 lines.
Consolidate the Example Structure section with the Required Sections content—either show the example inline as you define each section, or keep only the final example and remove the per-section code blocks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and well-structured with headers and bullets, but includes some unnecessary content like the 'When to Use' section (which duplicates frontmatter intent), the 'Limitations' boilerplate at the end, and some anti-patterns that are somewhat obvious to Claude (e.g., 'No filler', 'Trust capabilities'). The example structure section also partially duplicates the Required Sections content. | 2 / 3 |
Actionability | Provides concrete, executable commands (ln -s, pnpm commands), specific file paths to check, exact markdown templates to produce, and a complete example structure. The guidance is copy-paste ready with clear tables and code blocks showing the expected output format. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: File Setup → Before Writing (research steps 1-5) → Writing Rules → Required Sections → Optional Sections → Anti-Patterns. For a documentation-generation task, this is a well-ordered process with clear checkpoints (analyze first, then write with specific rules). No destructive operations require validation loops. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical sections, but it's a fairly long single file (~100 lines of content) with no references to supporting files. The Required Sections, Optional Sections, Anti-Patterns, and Example Structure sections could potentially be split out, though for a skill of this complexity it's borderline acceptable as a single file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
4cc48db
- 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.