common-skill-creator
Standardizes the creation and evaluation of high-density Agent Skills (Claude, Cursor, Windsurf). Ensures skills achieve high Activation (specificity/completeness) and Implementation (conciseness/actionability) scores. Use when: writing or auditing SKILL.md, improving trigger accuracy, or refactoring skills to reduce redundancy and maximize token ROI. (triggers: SKILL.md, evals/evals.json, create skill, audit skill, trigger rate, optimize description)
88
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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, well-crafted description that clearly defines a meta-skill for creating and auditing agent skills. It excels across all dimensions with specific actions, explicit 'Use when' triggers, natural keywords, and a distinctive niche. The only minor note is the mention of specific scoring concepts (Activation/Implementation) which are domain-specific but contextually appropriate.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creation and evaluation of high-density Agent Skills', 'Ensures skills achieve high Activation and Implementation scores', 'writing or auditing SKILL.md', 'improving trigger accuracy', 'refactoring skills to reduce redundancy and maximize token ROI'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (standardizes creation/evaluation of Agent Skills, ensures high Activation/Implementation scores) and 'when' with an explicit 'Use when:' clause listing specific scenarios: writing/auditing SKILL.md, improving trigger accuracy, refactoring skills. Also includes explicit trigger terms. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms in parentheses: 'SKILL.md', 'evals/evals.json', 'create skill', 'audit skill', 'trigger rate', 'optimize description'. Also uses natural phrases like 'writing or auditing SKILL.md' and 'improving trigger accuracy' that users would naturally say. Good coverage of relevant terms. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a very clear niche — meta-skill about creating and evaluating other skills. The triggers like 'SKILL.md', 'evals/evals.json', 'trigger rate', and 'audit skill' are highly distinctive and unlikely to conflict with any domain-specific skill. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%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 meta-skill that practices what it preaches regarding progressive disclosure and workflow clarity. Its main weakness is moderate actionability — it describes what good skills look like but could benefit from more concrete, executable examples (e.g., a complete minimal SKILL.md example inline). Some content borders on explaining concepts Claude already understands (what actionability means, what progressive disclosure is) rather than purely providing project-specific rules.
Suggestions
Add a brief inline example of a well-written SKILL.md frontmatter + body (5-10 lines) to make the guidance more concrete and copy-paste ready, improving actionability.
Remove or compress explanations of general concepts like 'Actionability: Examples must be copy-paste ready' — Claude knows what actionability means; instead just state the rule (e.g., 'All examples: copy-paste ready, executable').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some meta-explanations that Claude already knows (e.g., explaining what actionability means, what progressive disclosure is). The anti-patterns section partially restates things covered elsewhere. However, most content is procedural and specific. | 2 / 3 |
Actionability | Provides structured workflows with numbered steps and concrete checklist items, but lacks executable code examples or copy-paste ready commands. The guidance is specific in places (e.g., 'cp -r <skill-dir>') but mostly describes processes at a conceptual level rather than providing fully executable artifacts. | 2 / 3 |
Workflow Clarity | Both new and existing skill workflows are clearly sequenced with numbered steps, include validation/testing checkpoints (steps 4-6), and have explicit iteration loops. The workflow distinguishes between new and existing skills with appropriate branching. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear three-level loading system, concise overview in the body, and well-signaled one-level-deep references with contextual hints ('load when...') that tell Claude exactly when to access each reference file. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- HoangNguyen0403/agent-skills-standard
- Commit
19a1140
- 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.