create-skill

Create a new skill in the current repository. Use when the user wants to create/add a new skill, or mentions creating a skill from scratch. This skill follows the workflow defined in .agents/skills/README.md and helps scaffold, validate, and sync new skills.

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

75%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 instruction skill with concrete commands, a usable template, and a validation feedback loop. Most dimensions sit at 4 due to minor redundancy and slightly implicit checkpoint framing rather than serious defects.

Suggestions

Remove the 'Commands Reference' section (or fold it into the relevant steps) since 'pnpm skills:check' and 'pnpm skills:sync' already appear in Steps 4-5, reducing redundancy.

Strengthen the validation feedback loop in Step 5 with an explicit gate, e.g. '**Validate**: run `pnpm skills:check`; only proceed to the Summary when it passes — otherwise fix and re-run'.

Replace the template's '[Instructions for the skill]' stub with a brief worked example so the scaffolded output is fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the 'Commands Reference' section and 'Public vs Private Skills' table restate commands and rules already covered in the workflow steps, leaving minor trimmable redundancy.	4 / 5
Actionability	Concrete commands ('pnpm skills:check', 'pnpm skills:sync'), exact paths, and a copy-paste SKILL.md template give mostly executable guidance; the template's '[Instructions for the skill]' stub and Step 1's question list are minor gaps versus fully copy-paste-ready coverage.	4 / 5
Workflow Clarity	Six numbered steps form a clear sequence with a validate-then-fix-and-re-run loop in Step 5, but the checkpoint framing ('If there are issues, fix them and re-run') is less explicit than the anchor-5 pattern of bold validation gates and 'only when valid' gating.	4 / 5
Progressive Disclosure	Content is well-organized into clear sections with no external references needed, fitting the good-structure anchor; the duplicated Commands Reference section is a minor organization gap preventing a 5.	4 / 5
	Total	16 / 20 Passed

Description

87%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 description that clearly states both capability and explicit trigger conditions with concrete phrasing. It is distinct and specific, with only minor room to broaden trigger-term synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Create a new skill in the current repository') and several concrete actions ('scaffold, validate, and sync new skills'), matching the anchor listing several specific actions with minor gaps rather than the comprehensive coverage of a 5.	4 / 5
Completeness	Explicitly answers what it does ('Create a new skill ... scaffold, validate, and sync') and when to use it ('Use when the user wants to create/add a new skill, or mentions creating a skill from scratch') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'create/add a new skill' and 'creating a skill from scratch' give good keyword coverage, but common synonyms such as 'make a skill' or 'scaffold a skill' are missing, keeping it just below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Skill creation is a clear, narrow niche with distinct triggers and minimal realistic overlap with other skills, fitting the 'clear niche with minimal conflict risk' anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: CherryHQ/cherry-studio
Path: .agents/skills/create-skill/SKILL.md
Commit: c649419

Reviewed: 3 days 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.