git-workflow

Git 版本控制与协作专家，涵盖 GitHub/Gitee 平台操作、Conventional Commits 规范及 PR/MR 最佳实践。

1.12x

Quality

—

Does it follow best practices?

Impact

98%

1.12x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

50%

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 reasonably organized reference for Git workflow conventions but largely restates knowledge Claude already has and lacks executable, sequenced workflows with validation. It also links to a missing AGENTS.md, which undermines progressive disclosure.

Suggestions

Remove or compress explanations of well-known concepts (Conventional Commit type definitions, Git Flow branch taxonomy) and keep only what is non-obvious or project-specific.

Provide executable, copy-paste-ready commands (e.g., actual git/gh CLI sequences for branching, committing, opening PRs) instead of descriptive bullet guidelines.

Create the referenced AGENTS.md or remove the dangling [AGENTS.md](AGENTS.md) link so that progressive-disclosure references resolve to real files.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient bullet lists, but it explains concepts Claude already knows (Conventional Commit types, Git Flow branch names, GitHub Actions/Pages), so it does not earn the score-3 'every token earns its place' bar.	2 / 3
Actionability	It gives some concrete guidance (a commit format example and branch names) but mostly describes guidelines rather than providing executable commands or copy-paste-ready instructions, matching the score-2 'incomplete' anchor.	2 / 3
Workflow Clarity	Content is organized into modules but there is no sequenced multi-step process with validation checkpoints or feedback loops, so it sits at the score-2 'steps listed but validation gaps / no checkpoints' level.	2 / 3
Progressive Disclosure	Sections provide moderate structure and one inline reference to AGENTS.md, but that referenced file does not exist in any bundle directory, so the reference is not clearly signaled/valid and a higher score is not warranted.	2 / 3
	Total	8 / 12 Passed

Description

57%

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 specific to a clear niche and uses appropriate third-person voice, but it omits any explicit 'when to use it' trigger guidance and relies on domain nouns rather than concrete actions. Adding a 'Use when...' clause with natural trigger terms would lift the weakest dimensions.

Suggestions

Add an explicit trigger clause such as 'Use when the user needs to write Conventional Commits messages, manage branches, or handle PRs/MRs on GitHub or Gitee.' to satisfy the completeness 'when' requirement.

Reframe capabilities as concrete actions (e.g., 'Generate commit messages, manage branches, open and review PRs/MRs') instead of listing topic nouns.

Include natural keyword variations users actually say ('commit messages', 'pull requests', 'merge requests', 'code review') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and several specific areas ('GitHub/Gitee 平台操作、Conventional Commits 规范及 PR/MR 最佳实践') but uses declarative nouns rather than listing multiple concrete actions, matching the score-2 anchor.	2 / 3
Completeness	It clearly states what the skill covers but provides no 'Use when...' clause or explicit trigger guidance for when Claude should invoke it, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	It surfaces some natural terms users would say (GitHub, Gitee, Conventional Commits, PR/MR) but lacks common variations and is framed as a third-person summary rather than trigger-oriented phrasing, so it is not a full score-3.	2 / 3
Distinctiveness Conflict Risk	The combination of Git version control plus GitHub/Gitee plus Conventional Commits is a distinct, clearly bounded niche unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: majiayu000/claude-skill-registry
Commit: 8271354

Reviewed: about 17 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.