agentskills
Agent Skills Open Standard reference (agentskills.io). Use when creating portable skills for Claude Code, Cursor, Gemini CLI, OpenAI Codex, VS Code, Roo Code, and 20+ compatible agents. Covers frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring. Load before creating cross-agent skills.
70
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 strong description that clearly identifies a specific domain (Agent Skills Open Standard), lists concrete capabilities (schema, naming, directory structure, validation, authoring), and provides explicit trigger guidance with both a 'Use when' clause and a list of compatible agents. The inclusion of the standard's URL and specific agent names makes it highly distinctive and easy to match.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring.' These are concrete, well-defined aspects of the skill standard. | 3 / 3 |
Completeness | Clearly answers both what ('Agent Skills Open Standard reference covering frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring') and when ('Use when creating portable skills for Claude Code, Cursor, Gemini CLI... Load before creating cross-agent skills'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'portable skills', 'Claude Code', 'Cursor', 'Gemini CLI', 'OpenAI Codex', 'VS Code', 'Roo Code', 'cross-agent skills', 'agentskills.io'. Good coverage of agent names and the concept of portable/cross-agent skills. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — specifically about the Agent Skills Open Standard (agentskills.io) for cross-agent portable skill authoring. Very unlikely to conflict with other skills given its specific domain and explicit mention of the standard name and URL. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured reference skill that effectively documents the Agent Skills Open Standard with concrete examples and good progressive disclosure. Its main weakness is the lack of an explicit authoring workflow with validation checkpoints — the validation tools exist but aren't woven into a sequential creation process. Some sections could be tightened by removing rationale explanations and trusting Claude's existing knowledge.
Suggestions
Add an explicit 'Creating a Skill' workflow section with numbered steps that integrate validation: 1. Create directory → 2. Write SKILL.md → 3. Run `skilllint` → 4. Fix issues → 5. Re-validate → 6. Test with target agents.
Remove the '**Reason:**' explanations from the authoring best practices — the principles themselves are sufficient for Claude, and the rationales add ~100 tokens of content Claude can infer.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary content. The portable vs Claude Code comparison table is useful but lengthy, and some sections like 'Description Guidelines' explain things Claude already understands (third person writing, gerund forms). The authoring best practices section includes rationale explanations that add bulk without proportional value. | 2 / 3 |
Actionability | Provides concrete, executable examples throughout: complete frontmatter YAML blocks, directory structures, validation CLI commands, Python API usage with imports, and specific naming rules with valid/invalid examples. The validation section includes both CLI and Python approaches that are copy-paste ready. | 3 / 3 |
Workflow Clarity | The skill describes a reference/specification rather than a multi-step workflow, but the authoring process is implicit rather than explicitly sequenced. There's no clear 'create a skill' workflow with validation checkpoints — the validation tools are mentioned but not integrated into a step-by-step creation flow with feedback loops (e.g., write → validate → fix → re-validate). | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. The SKILL.md provides a comprehensive overview with clear, one-level-deep references to `references/specification.md`, `references/best-practices.md`, and `references/integration.md`. Content is well-organized into logical sections with a clear navigation path. The skill itself teaches progressive disclosure patterns, demonstrating the concept it describes. | 3 / 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
- Jamie-BitFlight/claude_skills
- Commit
4e61312
- 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.