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

88%

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

77%

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

The content is highly actionable with a clear, well-validated eval workflow, but it is over the 500-line budget with conversational padding and references several bundle files that are absent from the actual bundle.

Suggestions

Tighten the body to under 500 lines by trimming conversational filler ('Cool? Cool.', the plumbers anecdote, 'billions a year in economic value', 'Good luck!') and de-duplicating the repeated core-loop summaries.

Add the missing bundle files referenced in the body (agents/grader.md, agents/comparator.md, agents/analyzer.md, eval-viewer/generate_review.py), or remove the references and inline the essential guidance.

Move the environment-specific sections (Claude.ai, Cowork, Cherry Studio) and the Description Optimization deep-dive into reference files to reduce SKILL.md length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body runs ~513 lines, over the skill's own 500-line budget, and carries conversational padding ('Cool? Cool.', the plumbers/grandparents anecdote, 'billions a year in economic value') that could be trimmed without losing substance.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands (e.g. 'python -m scripts.aggregate_benchmark <workspace>/iteration-N --skill-name <name>') and full JSON examples for evals, grading, timing, and feedback files.	3 / 3
Workflow Clarity	The eval loop is clearly sequenced as Steps 1–5 with explicit validation via grading, benchmark aggregation, and a feedback loop with concrete stopping criteria.	3 / 3
Progressive Disclosure	References are one-level-deep and signaled, but the body exceeds 500 lines and points to bundle paths that do not exist (agents/grader.md, agents/comparator.md, agents/analyzer.md, eval-viewer/generate_review.py).	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is strong: concrete multi-action capabilities, an explicit 'Use when' trigger clause, and a distinct skill-authoring niche. The only minor weakness is a couple of specialist terms ('variance analysis', 'triggering accuracy') in the trigger list.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new skills, modify and improve existing skills, and measure skill performance' — matching the multi-action anchor rather than vague domain-only language.	3 / 3
Completeness	Explicitly states what it does, then follows with a clear 'Use when users want to create a skill from scratch, edit, or optimize...' clause answering both what and when.	3 / 3
Trigger Term Quality	Covers natural user phrasings like 'create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill,' though 'variance analysis' and 'triggering accuracy' lean specialist.	3 / 3
Distinctiveness Conflict Risk	Occupies a distinct skill-authoring niche (create/edit/optimize/evaluate skills) with triggers unlikely to collide with domain skills like PDF or spreadsheet tools.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (518 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: CherryHQ/cherry-studio
Path: resources/skills/skill-creator/SKILL.md
Commit: 44c88c4

Reviewed: about 13 hours 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.