skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
74
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skill-creator/SKILL.mdQuality
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 skill description that clearly defines its scope (AgentSkills authoring and maintenance), provides explicit trigger guidance with natural user phrases, and occupies a distinct niche. It uses proper third-person voice, lists concrete actions, and includes both 'Use when' and 'Triggers on' clauses for comprehensive selection guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create, edit, improve, audit, restructure skill directories, move files to references/scripts/, remove stale content, validate against the AgentSkills spec. | 3 / 3 |
Completeness | Clearly answers both 'what' (create, edit, improve, audit AgentSkills, restructure directories, validate against spec) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios and a 'Triggers on phrases like...' section). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'create a skill', 'author a skill', 'tidy up a skill', 'improve this skill', 'review the skill', 'clean up the skill', 'audit the skill', plus mentions of SKILL.md files and skill directories. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on AgentSkills and SKILL.md files, with domain-specific terms like 'AgentSkills spec', 'references/', 'scripts/' directories that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive but suffers significantly from verbosity—it explains many concepts Claude already understands (what skills are, what directories do, basic software engineering concepts) and includes extensive philosophical guidance that inflates token cost without proportional value. The workflow is reasonably clear with a 6-step process and concrete script commands, but the ratio of conceptual explanation to actionable instruction is too high. The skill would benefit greatly from aggressive trimming and moving detailed explanations into reference files, practicing the progressive disclosure it preaches.
Suggestions
Cut the 'About Skills' and 'What Skills Provide' sections entirely—Claude already knows what skills are. Start directly with the creation process or core principles condensed to a few bullet points.
Move the extensive progressive disclosure patterns, directory structure explanations, and design principle discussions into a references/skill-design-patterns.md file, keeping only a brief summary and link in SKILL.md.
Add a complete, concrete example of a well-written SKILL.md (frontmatter + body) rather than just fragments and conceptual guidance—this would dramatically improve actionability.
Add explicit validation checkpoints between steps (e.g., 'Before proceeding to Step 4, verify: frontmatter has name and description, resource directories match planned contents') to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, explaining many concepts Claude already knows (what skills are, what PDFs are, what scripts/references/assets directories do). It includes extensive explanations of progressive disclosure, degrees of freedom, and other meta-concepts that could be dramatically condensed. The 'About Skills' and 'What Skills Provide' sections are largely unnecessary preamble. | 1 / 3 |
Actionability | The skill provides some concrete guidance like the init_skill.py and package_skill.py commands with usage examples, and the step-by-step creation process. However, much of the content is conceptual rather than executable—the design principles, progressive disclosure patterns, and planning steps are more philosophical than actionable. The actual SKILL.md writing guidance lacks a concrete example of a complete, well-written SKILL.md. | 2 / 3 |
Workflow Clarity | The 6-step creation process is clearly sequenced and each step has a defined purpose with skip conditions. However, there are no explicit validation checkpoints between steps (e.g., no 'verify the frontmatter is correct before proceeding' or feedback loops for common errors). The packaging step includes validation but earlier steps lack verification gates. | 2 / 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 that could benefit from splitting—the extensive 'About Skills' section, design principles, and directory structure explanations could be moved to reference files. The skill teaches progressive disclosure but doesn't practice it well itself. | 2 / 3 |
Total | 7 / 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
- qsimeon/openclaw-engaging
- Commit
4467e04
- 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.