git-workflows
Always invoke this skill for any git-related request (commit messages, staging review, history, PR descriptions, etc.) so git workflows are handled consistently.
64
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./git-workflows/SKILL.mdQuality
Discovery
64%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 functions more as a routing instruction than a skill description — it tells Claude when to use the skill but barely explains what the skill actually does. The trigger terms are good and cover natural user language, but the lack of concrete capability descriptions (e.g., 'generates commit messages by analyzing diffs', 'summarizes PR changes') weakens its utility for skill selection. The imperative voice ('Always invoke this skill') is unusual and doesn't describe capabilities.
Suggestions
Add concrete capability descriptions: instead of just listing topics in parentheses, describe what the skill does (e.g., 'Generates commit messages from staged diffs, summarizes git history, drafts PR descriptions').
Restructure to separate 'what' from 'when': lead with specific actions the skill performs, then follow with a 'Use when...' clause listing trigger scenarios.
Narrow the scope or clarify boundaries to reduce overlap risk — 'any git-related request' is very broad and could conflict with code review or CI/CD skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (git) and lists some actions in parenthetical form (commit messages, staging review, history, PR descriptions), but these are listed as examples rather than concrete described capabilities. It doesn't describe what the skill actually does with these things. | 2 / 3 |
Completeness | The 'when' is clearly stated ('any git-related request'), but the 'what' is weak — it says git workflows are 'handled consistently' without explaining what the skill actually does. The description focuses on when to invoke rather than what capabilities it provides. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'git', 'commit messages', 'staging review', 'history', 'PR descriptions', plus the catch-all 'git-related request'. These cover common user phrasings well. | 3 / 3 |
Distinctiveness Conflict Risk | The git domain is fairly specific, but the extremely broad scope ('any git-related request') could overlap with other skills that handle specific git subtasks like code review or CI/CD workflows. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides clear workflows for multiple git operations with appropriate validation checkpoints and user approval gates. Its progressive disclosure is excellent, delegating detailed guidelines to reference files while keeping the main skill as an operational overview. The main weakness is some verbosity in the setup/configuration sections that could be tightened without losing clarity.
Suggestions
Trim the repo-root explanation paragraph — the inline code example already demonstrates the pattern clearly; the multi-sentence justification about wrong-cwd bugs and rev-parse validation is unnecessary for Claude.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity, particularly the lengthy explanation about why to pass repo-root explicitly and the detailed description of how common.sh works. The warning about wrong-cwd bugs and the git rev-parse validation details could be trimmed since Claude can infer these patterns. | 2 / 3 |
Actionability | The skill provides concrete, executable script invocations with clear argument patterns, specific conventional commit format templates, and explicit step-by-step workflows for each operation. Commands are copy-paste ready with clear parameter placeholders. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints and user approval gates (e.g., 'Only move on after explicit approval from the user'). The auto-commit workflow includes a precondition check, and the commit message generation has an iterative review-approve-draft-approve cycle with clear feedback loops. | 3 / 3 |
Progressive Disclosure | The skill is well-structured as an overview that delegates detailed content to reference files (general_code_review_guidelines.md, python/rust review guidelines, auto_commit_workflow.md) with clear one-level-deep references. Navigation is well-signaled with explicit 'Read X for Y' directives in the Building Blocks section and within each operation. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ceshine/ceshine-agent-skills
- Commit
fc251b2
- Reviewed
Table of Contents
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.