skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
69
57%
Does it follow best practices?
Impact
85%
1.21xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skill-creator/SKILL.mdQuality
Discovery
67%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 is competently structured with an explicit 'Use when' clause and covers both what and when. However, it lacks specificity in concrete actions and could include more natural trigger terms that users would actually say. The domain is somewhat niche ('AgentSkills') which helps with distinctiveness but the surrounding language is generic enough to risk overlap.
Suggestions
Add more specific concrete actions, e.g., 'Create or update AgentSkills by generating YAML frontmatter, writing execution scripts, organizing reference files, and bundling assets into skill packages.'
Expand trigger terms with natural variations users might say, e.g., 'Use when the user mentions SKILL.md, skill files, skill templates, creating a new skill, or editing skill metadata.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('AgentSkills') and some actions ('create or update', 'designing, structuring, packaging'), but the actions are somewhat generic and don't list concrete specific operations like 'write YAML frontmatter', 'generate script files', or 'validate skill structure'. | 2 / 3 |
Completeness | Clearly answers both 'what' (create or update AgentSkills with scripts, references, and assets) and 'when' (Use when designing, structuring, or packaging skills). The 'Use when...' clause is explicitly present with trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'skills', 'scripts', 'references', 'assets', 'packaging', but misses natural variations users might say such as 'skill file', 'SKILL.md', 'skill template', 'new skill', or 'skill definition'. 'AgentSkills' is a somewhat specialized term that users may or may not use naturally. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'AgentSkills' provides some distinctiveness, but 'designing, structuring, or packaging' could overlap with general project scaffolding or template-creation skills. The description could be more precise about what differentiates this from other file/project creation skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive and well-structured workflow for creating skills, with clear sequencing and good tooling integration (init_skill.py, package_skill.py). However, it severely violates its own core principle of conciseness—it's extremely verbose, explains concepts Claude already understands (what skills are, what PDFs are, what scripts do), and includes extensive philosophical guidance that could be dramatically condensed or moved to reference files. The skill would benefit from practicing what it preaches about token efficiency.
Suggestions
Cut the 'About Skills' and 'What Skills Provide' sections entirely—Claude already knows what skills are. Start directly with the anatomy and creation process.
Move the 'Progressive Disclosure Design Principle' section with its multiple pattern examples into a references/progressive-disclosure.md file, keeping only a brief summary and link in SKILL.md.
Remove the 'Set Appropriate Degrees of Freedom' metaphorical explanation and replace with a concise table mapping task characteristics to freedom levels.
Condense the 'Bundled Resources' section significantly—Claude doesn't need explanations of what scripts, references, and assets are conceptually; just provide the directory structure and when-to-use rules.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, explaining many concepts Claude already knows (what skills are, what PDFs are, what scripts/references/assets mean conceptually). Extensive sections like 'What Skills Provide' and 'About Skills' add little actionable value. The 'Set Appropriate Degrees of Freedom' section uses metaphors (narrow bridge, open field) that waste tokens. | 1 / 3 |
Actionability | The skill provides concrete commands for init_skill.py and package_skill.py with usage examples, which is good. However, the SKILL.md body writing guidance is mostly abstract principles rather than executable templates. The 'Edit the Skill' section delegates to external reference files (references/workflows.md, references/output-patterns.md) without providing inline actionable content. | 2 / 3 |
Workflow Clarity | The 6-step skill creation process is clearly sequenced with explicit steps (Understand → Plan → Initialize → Edit → Package → Iterate). Each step includes when to skip it, what to do, and validation is built into the packaging step. The packaging script automatically validates before creating the package, providing a feedback loop. | 3 / 3 |
Progressive Disclosure | The skill references external files (references/workflows.md, references/output-patterns.md) which is good progressive disclosure. However, the SKILL.md itself is a monolithic wall of text with extensive inline content about progressive disclosure patterns, naming conventions, and design principles that could be split into reference files. The irony is that a skill about creating concise skills violates its own conciseness principles. | 2 / 3 |
Total | 8 / 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
- Hung-Reo/hungreo-openclaw
- Commit
a5bf5e0
- 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.