git-best-practices
Git workflow patterns for commits, branching, PRs, and history management across heterogeneous repositories. Use when creating commits, managing branches, opening pull requests, or rewriting history. Do not use for non-git implementation tasks or repo-specific release policy decisions without repository documentation.
90
88%
Does it follow best practices?
Impact
90%
1.50xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope around git workflow operations, provides explicit 'Use when' and 'Do not use' guidance, and includes natural trigger terms users would employ. The inclusion of boundary conditions (what NOT to use it for) is a notable strength that helps distinguish it from related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: commits, branching, PRs, and history management. Also specifies 'heterogeneous repositories' and mentions creating commits, managing branches, opening pull requests, and rewriting history. | 3 / 3 |
Completeness | Clearly answers both 'what' (git workflow patterns for commits, branching, PRs, history management) and 'when' (explicit 'Use when' clause with specific triggers). Also includes a helpful 'Do not use' boundary clause that further clarifies scope. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'commits', 'branching', 'PRs', 'pull requests', 'history', 'git', 'branches'. These cover common variations of how users discuss git workflows. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to git workflow operations with distinct triggers like commits, branching, PRs, and history rewriting. The 'Do not use' clause explicitly excludes non-git tasks and repo-specific release decisions, reducing conflict risk with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with excellent concrete examples and well-defined workflows including validation checkpoints and safety guardrails (force-push confirmation, sensitive file warnings, backup before rewrite). The main weakness is that it's somewhat long for a single file — some reference material (commit type table, detailed examples, merge strategies) could be split out. Minor verbosity in a few sections, but overall it respects Claude's intelligence well.
Suggestions
Consider splitting the detailed commit examples and merge strategy table into a separate reference file (e.g., COMMIT-REFERENCE.md) to keep SKILL.md as a concise overview with links to details.
Tighten the Branch Flow section — the explanatory bullets after the diagram largely restate what the diagram already shows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and avoids explaining basic git concepts, but some sections are slightly verbose — e.g., the merge strategy table and branch flow diagram include explanations that Claude would already know. The commit type table is borderline but useful as a quick reference. Some phrasing could be tightened. | 2 / 3 |
Actionability | Provides concrete, executable commands throughout (git add, git push --force-with-lease, gh repo view, git symbolic-ref), specific commit message examples with realistic content, and clear branch naming patterns. The examples section is particularly strong with six varied, copy-paste-ready commit message examples. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit validation checkpoints: the agent git workflow has numbered steps with verification (git status checks), branch discovery has fallback chains with error handling, and history rewriting includes a backup-verify-confirm sequence before force pushing. Force push requires user confirmation, and sensitive file staging triggers warnings. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a fairly long monolithic file (~200 lines) with no references to external files. The commit examples, branch flow details, and merge strategy tables could be split into separate reference files. However, the use of collapsible example blocks and tables provides some internal organization. | 2 / 3 |
Total | 10 / 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
- NeverSight/skills_feed
- Commit
e437c3c
- 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.