skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
68
52%
Does it follow best practices?
Impact
99%
1.17xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/skill-creator/SKILL.mdQuality
Discovery
57%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 has good completeness with an explicit 'when to use' clause covering both creation and updating of skills. However, it lacks specificity about what concrete actions the skill performs (e.g., generating frontmatter, structuring markdown, defining triggers). The trigger terms are adequate but could be expanded with more natural variations users might employ.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Guides creation of SKILL.md files including YAML frontmatter, description fields, and markdown instruction blocks'
Expand trigger terms to include natural variations like 'SKILL.md', 'skill file', 'teach Claude how to', 'custom workflow', or 'skill template'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'creating effective skills' and 'extends Claude's capabilities with specialized knowledge, workflows, or tool integrations' but these are vague and abstract. No concrete actions like 'generates YAML frontmatter', 'writes markdown instructions', or 'validates skill structure' are mentioned. | 1 / 3 |
Completeness | The description answers both 'what' (guide for creating effective skills that extend Claude's capabilities) and 'when' ('should be used when users want to create a new skill or update an existing skill'). The 'Use when' clause is explicit with clear triggers. | 3 / 3 |
Trigger Term Quality | Includes some relevant trigger terms like 'create a new skill', 'update an existing skill', and 'skill' itself. However, it misses natural variations users might say such as 'SKILL.md', 'skill file', 'teach Claude', 'custom instruction', or 'skill template'. | 2 / 3 |
Distinctiveness Conflict Risk | The skill is somewhat distinctive in targeting skill creation specifically, but the vague language about 'specialized knowledge, workflows, or tool integrations' could overlap with general documentation or configuration skills. The term 'skill' as a trigger is fairly specific to this domain though. | 2 / 3 |
Total | 8 / 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.
The skill has a well-structured workflow with clear sequencing and validation, but is significantly undermined by verbosity. Large sections explain concepts Claude already understands (what skills are, what directories do, what progressive disclosure means), violating the principle that skills should add only what Claude doesn't already know. The actionability is moderate—concrete commands exist but the core creative task (writing SKILL.md content) lacks concrete before/after examples.
Suggestions
Cut the 'About Skills' section drastically—remove explanations of what skills are, what scripts/references/assets directories do, and the progressive disclosure concept. Claude knows these. Keep only non-obvious constraints (e.g., description style, size limits, duplication avoidance rules).
Add a concrete, complete example of a finished SKILL.md (frontmatter + body) for a simple skill, showing the expected output quality rather than just describing it abstractly.
Move detailed reference material (anatomy of a skill, bundled resources guidelines) to a references/ file and keep SKILL.md focused on the creation workflow steps.
Add a concrete example of what good vs. bad SKILL.md writing style looks like, since Step 4's guidance ('answer these questions') is abstract compared to showing an actual example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, explaining concepts Claude already knows (what skills are, what scripts/references/assets are, progressive disclosure as a concept). Sections like 'What Skills Provide' and 'About Skills' are largely unnecessary padding. The entire 'Anatomy of a Skill' section explains directory structures and file purposes at length when brief references would suffice. The 'Bundled Resources' subsections repeat similar patterns with excessive bullet points. | 1 / 3 |
Actionability | The skill provides concrete commands for init_skill.py and package_skill.py, and the step-by-step process is reasonably specific. However, it lacks executable examples of actual SKILL.md content (e.g., a complete example frontmatter + body), and the guidance for writing SKILL.md content (Step 4) is relatively abstract—it asks questions rather than showing concrete output examples. | 2 / 3 |
Workflow Clarity | The six-step process is clearly sequenced with explicit conditions for skipping steps, validation is built into the packaging step (Step 5), and there's a clear feedback loop in Step 6 (iterate). The workflow handles the full lifecycle from understanding through packaging and iteration, with validation checkpoints before distribution. | 3 / 3 |
Progressive Disclosure | The skill references scripts (init_skill.py, package_skill.py) but no bundle files were provided to verify. The content is monolithic—all information is inline in SKILL.md with no references to external documentation. The lengthy 'About Skills' and 'Bundled Resources' sections could be moved to a references file, keeping SKILL.md focused on the creation workflow. | 2 / 3 |
Total | 8 / 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
- davepoon/buildwithclaude
- Commit
c911a92
- 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.