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

84%

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

85%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.

The body is a well-structured, actionable walkthrough with concrete commands, a scaffold template, explicit validation with a fix-and-retry loop, and a clean single-level reference to the repository's skills README. Weaknesses are minor: some repetition of the check/sync requirements and a placeholder-only template with no worked example.

Suggestions

Consolidate the repeated `pnpm skills:check` / sync instructions into the Commands Reference or a single note to tighten the token budget.

Include a filled-in example skill (name + description) in or beside the SKILL.md template so the scaffold is fully copy-paste ready.

Merge the Constraints section with the workflow steps it duplicates (e.g., the sync-before-validate note) to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no basic-concept explanations, and the template/commands are compact. However, `pnpm skills:check` appears four times (Step 4 note, Step 5, Constraints, Commands Reference) and the sync-before-validate requirement is repeated three times, so minor trimming is possible; this fits the 'efficient; minor instances that could be trimmed' anchor rather than the every-token-earns-its-place 5.	4 / 5
Actionability	Concrete, executable guidance throughout: exact commands (`pnpm skills:check`, `pnpm skills:sync`), a SKILL.md frontmatter template, and specific paths (`public-skills.txt`, `.agents/skills/<skill-name>/`). The template is a placeholder skeleton with no filled-in example or description-format guidance, which are minor gaps keeping it below fully copy-paste-ready 5.	4 / 5
Workflow Clarity	Six clearly sequenced steps with an explicit validation step ("Run pnpm skills:check... If there are issues, fix them and re-run") forming a validate-fix-retry feedback loop, plus the sync-before-validate checkpoint in Step 4. Error recovery and ordering caveats are called out explicitly, matching the top anchor.	5 / 5
Progressive Disclosure	The body is a well-organized overview with clear sections that delegates workflow rules to a single one-level-deep, well-signaled reference ("Always read .agents/skills/README.md"), with no bundle files needed. No content that belongs in separate files is inlined beyond what the task requires, matching the clear-overview anchor.	5 / 5
	Total	18 / 20 Passed

Description

83%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 explicitly states what the skill does and when to use it, with an explicit 'Use when...' clause and natural trigger phrases. Minor improvements would come from broadening trigger synonyms and acknowledging the related skill-creator tooling in the trigger boundary.

Suggestions

Add natural trigger variations such as "new skill", "set up a skill", or "bootstrap a skill" to broaden when-matching.

Clarify the boundary with the separate skill-creator skill (e.g., 'For basic scaffolding; for evals and iteration use skill-creator') to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	The description names concrete actions — "Create a new skill in the current repository" and "helps scaffold, validate, and sync new skills" — plus a concrete artifact path (".agents/skills/README.md"). It lists several specific actions with only minor gaps (e.g., it doesn't mention gathering intent or the public/private distinction), which fits the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	It explicitly answers both: what ("Create a new skill... scaffold, validate, and sync new skills") and when ("Use when the user wants to create/add a new skill, or mentions creating a skill from scratch"). Both halves are present with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural phrases like "create/add a new skill" and "creating a skill from scratch" match what a user would actually say. Coverage is good but misses common variations such as "new skill", "skill setup", or "bootstrap a skill", so it sits between the good (4) and comprehensive (5) anchors.	4 / 5
Distinctiveness Conflict Risk	The niche is distinct — repo-scoped skill scaffolding tied to ".agents/skills/README.md" — with clear triggers. There is minor overlap risk with other meta/skill-authoring skills (the body itself references a separate "skill-creator" skill), keeping it below the minimal-conflict 5 anchor.	4 / 5
	Total	17 / 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: 113ef7e

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.