Build, audit, and improve Claude Code skills through guided interview and generation. Use when user says "create a skill", "build a skill", "make a new skill", "write a skill", "improve this skill", "audit this skill", "review my skill", "skill from scratch", "turn this into a skill", or /skill-builder. Produces guide-compliant skill directories with SKILL.md, references, and scripts.
100
100%
Does it follow best practices?
Impact
Pending
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 an excellent skill description that hits all the marks. It provides specific actions (build, audit, improve), comprehensive trigger terms covering natural user phrases, explicit 'Use when' guidance, and clear outputs. The description is well-scoped to a distinct domain (Claude Code skills) with minimal conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build, audit, and improve Claude Code skills through guided interview and generation' and specifies outputs: 'guide-compliant skill directories with SKILL.md, references, and scripts.' | 3 / 3 |
Completeness | Clearly answers both what (build, audit, improve skills through guided interview; produces skill directories with specific components) AND when (explicit 'Use when' clause with comprehensive trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create a skill', 'build a skill', 'make a new skill', 'write a skill', 'improve this skill', 'audit this skill', 'review my skill', 'skill from scratch', 'turn this into a skill', and the command '/skill-builder'. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on Claude Code skills with distinct triggers like 'skill-builder' and skill-specific terminology; unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill that demonstrates best practices: it's concise yet comprehensive, provides concrete actionable guidance at every step, has clear multi-phase workflows with explicit validation checkpoints, and uses progressive disclosure effectively by referencing external files for detailed specs. The meta-skill nature is well-suited to its thorough structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables, bullet points, and clear section headers. It assumes Claude's competence and avoids explaining basic concepts, with every section serving a clear purpose. | 3 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific questions to ask, exact file paths to create, explicit commands like `mkdir -p` and `chmod +x`, and clear formulas for description generation. The workflow is copy-paste ready. | 3 / 3 |
Workflow Clarity | Both Create and Edit modes have clearly numbered phases with explicit validation checkpoints (Phase 4 runs checklist, Phase 5 re-runs after changes). Includes feedback loops for refinement and clear sequencing throughout. | 3 / 3 |
Progressive Disclosure | Excellent structure with overview workflows first, then Generation Rules as quick reference, and a clear Reference Files Index pointing to one-level-deep external files. The skill appropriately delegates detailed specs to reference files. | 3 / 3 |
Total | 12 / 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.
65673fe
Table of Contents
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.