skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

70%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 thorough, actionable skill body with a clearly sequenced eval-and-iterate workflow and strong validation checkpoints. Its main weaknesses are length/redundancy over the 500-line budget and broken or duplicated references that hurt progressive disclosure.

Suggestions

Trim the body under 500 lines by removing the inlined JSON schemas (grading.json, benchmark.json, eval_metadata.json) that duplicate references/schemas.md, and consolidate the redundant 'core loop (summary)' with the 'Creating a skill' and 'Running and Evaluating Test Cases' sections.

Fix broken bundle references — agents/grader.md, agents/comparator.md, agents/analyzer.md, assets/eval_review.html, eval-viewer/generate_review.py, and scripts/generate_review.py are cited but absent; either add the files or remove the references.

Move the lengthy Description Optimization manual-steps detail into a references/ file and keep only a concise pointer plus the automated-script commands inline.

Dimension	Reasoning	Score
Conciseness	At ~600 lines the body exceeds its own stated 500-line budget and includes redundancy (the 'core loop (summary)' repeats earlier sections) and a lengthy description-optimization section; content is mostly substantive rather than padded, but it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready JSON schemas (grading.json, benchmark.json, eval_metadata.json), runnable commands, and a Ruby script template, but several referenced executable scripts (generate_review.py, package_skill.py) do not exist in the bundle, leaving minor gaps.	4 / 5
Workflow Clarity	The eval workflow is laid out as explicit Steps 1–7 with validation checkpoints ('ALWAYS DO THIS BEFORE REVISING THE SKILL', the frontmatter validator), feedback loops (read feedback → improve → repeat), and a summary checklist.	5 / 5
Progressive Disclosure	Section structure is reasonable and scripts/ plus references/schemas.md exist and are signaled, but multiple referenced paths are broken (agents/grader.md, agents/comparator.md, agents/analyzer.md, assets/eval_review.html, eval-viewer/generate_review.py) and full JSON schemas are inlined despite schemas.md existing.	3 / 5
	Total	15 / 20 Passed

Description

92%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, well-constructed description that clearly states concrete capabilities and pairs them with an explicit, trigger-rich 'Use when' clause. Minor room to broaden natural phrasings, but it cleanly satisfies what/when and is highly distinct.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Create new skills, modify and improve existing skills, and measure skill performance' plus 'run evals', 'benchmark skill performance with variance analysis', and 'optimize a skill's description' — giving comprehensive coverage of the create/edit/measure lifecycle.	5 / 5
Completeness	Explicitly answers both 'what' (create/modify/improve/measure skills) and 'when' via a concrete 'Use when users want to...' clause listing specific trigger contexts.	5 / 5
Trigger Term Quality	Good coverage of natural terms a user would say ('create a skill', 'edit', 'optimize an existing skill', 'run evals', 'benchmark') with synonyms, but a few natural phrasings like 'build/make a skill' or 'test a skill' are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear meta-skill niche (creating/improving/measuring skills) with distinct triggers and minimal overlap risk against ordinary task skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (605 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: clacky-ai/openclacky
Path: lib/clacky/default_skills/skill-creator/SKILL.md
Commit: 8a66b10

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.