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 negative boundaries ('Do not use for...') is a notable strength that helps distinguish it from adjacent skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: commits, branching, PRs, and history management. Also specifies 'heterogeneous repositories' and mentions rewriting history, which adds further specificity. | 3 / 3 |
Completeness | Clearly answers both 'what' (git workflow patterns for commits, branching, PRs, history management) and 'when' (explicit 'Use when' clause with triggers, plus a 'Do not use' clause that further clarifies boundaries). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'commits', 'branching', 'pull requests', 'PRs', 'history', 'git'. These cover common variations of how users discuss git workflows. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to git workflow operations with distinct triggers. The 'Do not use' clause explicitly excludes non-git implementation tasks and repo-specific release decisions, reducing conflict risk with coding or release management 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 git workflow skill with clear sequencing, validation checkpoints, and excellent concrete examples. Its main weakness is moderate verbosity — some content (full commit type table, extensive examples) could be trimmed or split into reference files. The workflow clarity is excellent, with explicit safety gates for destructive operations like force pushes and history rewrites.
Suggestions
Move the conventional commit type table and extended commit examples into a separate reference file (e.g., COMMIT_EXAMPLES.md) to reduce the main skill's token footprint.
Trim the commit type table — Claude already knows what 'docs', 'test', 'ci', and 'style' mean; a shorter list of the less obvious types with brief notes would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and avoids explaining basic git concepts, but some sections are slightly verbose — e.g., the merge strategy rationale column, the full conventional commit type table (Claude knows these), and the branch flow ASCII diagram could be tightened. The commit examples are valuable but collectively take significant space. | 2 / 3 |
Actionability | Highly actionable throughout: executable bash commands for branch discovery (with fallbacks), concrete commit message examples covering multiple scenarios, explicit staging commands, force-push syntax, and PR creation guidance. Nearly every instruction is copy-paste ready. | 3 / 3 |
Workflow Clarity | The agent git workflow is clearly sequenced (check state → discover branches → stage → commit → push) with explicit validation checkpoints (verify with git status, confirm with user before force push, verify byte-for-byte match before rewriting history). The history rewriting workflow includes a backup-then-verify feedback loop. Destructive operations (force push, history rewrite) have explicit user confirmation gates. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical sections, but it's a single monolithic file with no references to supporting documents. The commit examples section and branch discovery fallbacks could be split into separate reference files. For a skill of this length (~200 lines), some progressive disclosure into bundle files would improve scannability. | 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
aa009ea
- 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.