CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-builder

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.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable meta-skill with clear sequenced workflows, explicit validation/checklist feedback loops, and clean one-level-deep progressive disclosure to real reference files. The main weakness is mild redundancy between the Phase 3 generation rules and the later Generation Rules quick-reference section.

Suggestions

Consolidate the trailing "Generation Rules" quick-reference with the Phase 3 generation rules to remove duplication, or reduce it to pure pointers to the reference files.

Inline the key checklist pass/fail criteria (or a condensed version) so validation checkpoints are visible without jumping to references/checklist.md.

Add a concrete template or example for the 3 SHOULD-trigger / 2 should-NOT-trigger test-prompt generation step rather than describing it abstractly.

DimensionReasoningScore

Conciseness

Mostly efficient, imperative, and free of concept explanations Claude already knows, but the "Generation Rules" quick-reference section near the end duplicates material already covered in Phase 3 (Naming, Description Formula, File Rules, Body Rules, Pattern Selection) and could be trimmed.

4 / 5

Actionability

Provides concrete executable commands ("mkdir -p {scope}/{name}/references", "chmod +x"), specific interview questions, and explicit procedural steps, but test-prompt generation and some validation steps are described rather than given as copy-paste templates, leaving minor gaps.

4 / 5

Workflow Clarity

Both modes use clearly numbered phases with explicit gates ("Do not proceed until you have answers") and feedback loops ("Re-run the checklist on changed files", "Run final checklist — all items should pass"), but the actual validation criteria are delegated to references/checklist.md rather than surfaced inline, a minor checkpoint gap.

4 / 5

Progressive Disclosure

SKILL.md is an overview with well-signaled one-level-deep references (frontmatter-spec.md, description-guide.md, checklist.md, patterns.md), all of which exist, plus a closing "Reference Files Index" table; content is appropriately split between overview and reference files.

5 / 5

Total

17

/

20

Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description with explicit "Use when" trigger guidance, comprehensive natural trigger phrases, and a concrete statement of output. Minor gaps in action specificity and slight overlap risk from generic review/improve verbs keep it just below full marks.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Build, audit, and improve Claude Code skills", "guided interview and generation") and a concrete output ("Produces guide-compliant skill directories with SKILL.md, references, and scripts"), but "guided interview and generation" is a somewhat abstract method description rather than a fully enumerated capability set.

4 / 5

Completeness

Explicitly answers both what ("Build, audit, and improve Claude Code skills... Produces guide-compliant skill directories with SKILL.md, references, and scripts") and when ("Use when user says...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural phrases users would actually 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") plus the slash command "/skill-builder", including synonyms.

5 / 5

Distinctiveness Conflict Risk

The "Claude Code skills" niche is clear and the skill-building triggers are distinctive, but generic verbs like "review my skill" and "improve this skill" create minor overlap risk with general code-review or review skills.

4 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MrToxy/claude-skills
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.