code-mate-claude-code

Runs Claude Code non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Claude Code or compare its result with another coding agent.

Quality

86%

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

86%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 tight, executable skill body that respects token budget and gives concrete commands with clear sequencing and validation checkpoints. The only meaningful gap is the abstract `<prompt>` placeholder and stop-and-ask error handling rather than a recovery loop, which keep actionability and workflow_clarity at 4.

Suggestions

Add a short concrete example prompt (e.g. a one-line review or implementation request) so the command is copy-paste-ready, lifting actionability toward 5.

For failure cases beyond auth/missing-binary, consider a brief retry or fallback step instead of only 'stop and ask the user' to strengthen the workflow's feedback loop.

Optionally surface the parsed-JSON success path (what fields to read and report) so the run-and-report cycle is fully specified.

Dimension	Reasoning	Score
Conciseness	Lean ~25-line body with no padding and no explanation of concepts Claude already knows; every line earns its place ('Set the Bash working directory...', 'Check availability with `command -v claude`'). Assumes Claude's competence throughout.	5 / 5
Actionability	Provides concrete executable commands (`claude -p "<prompt>" --output-format json`, `command -v claude`) with specific handling instructions ('Pass the prompt as one quoted argument', 'report stderr and the exit status on failure'). Not 5 because `<prompt>` is an abstract placeholder rather than copy-paste-ready content; not 3 because the guidance is mostly executable with only minor gaps.	4 / 5
Workflow Clarity	Clear three-step sequence (set working dir/timeout, check availability, run and exit) with explicit checkpoints (missing binary → stop and ask; missing auth → stop and ask; failure → report stderr/exit status). Not 5 because error handling stops at 'ask the user' rather than a full validate-fix-retry loop; not 3 because most checkpoints are present and explicit.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references (no bundle files present), organized into clear 'Run' and 'Authentication And Permissions' sections — meeting the simple-skill exception for a top score on well-organized sections alone.	5 / 5
	Total	18 / 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, third-person description that clearly states what the skill does and when to use it, with natural trigger phrasing and a distinct niche. Minor keyword/synonym coverage gaps keep specificity and trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain (Claude Code) and several concrete actions — 'Runs Claude Code non-interactively', 'code analysis', 'implementation tasks', 'compare its result with another coding agent' — but coverage is high-level rather than comprehensive. Not 5 because it does not enumerate the range of concrete Claude Code tasks; not 3 because it lists more than 1-2 specific actions.	4 / 5
Completeness	Explicitly answers both 'what' ('Runs Claude Code non-interactively for code analysis and implementation tasks') and 'when' ('Use when the user asks to delegate repository work to Claude Code or compare its result with another coding agent') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say — 'delegate repository work to Claude Code' and 'compare its result with another coding agent' — with good keyword coverage (Claude Code, repository work, coding agent). Not 5 because common synonyms/variations are missing; not 3 because the terms present are natural and relevant rather than generic.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — non-interactive delegation to Claude Code and cross-agent comparison — with distinct triggers and minimal overlap risk with other skills.	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: resources/code-cli-skills/code-mate-claude-code/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.