CtrlK
BlogDocsLog inGet started
Tessl Logo

git-workflow

Git workflow management with atomic commit principles. Capabilities: commit organization, branching strategies, merge/rebase workflows, PR management, history cleanup, staged change analysis, single-responsibility commits. Actions: commit, push, pull, merge, rebase, branch, stage, stash git operations. Keywords: git commit, git push, git pull, git merge, git rebase, git branch, git stash, atomic commit, commit message, conventional commits, branching strategy, GitFlow, trunk-based, PR, pull request, code review, git history, cherry-pick, squash, amend, interactive rebase, staged changes. Use when: organizing commits, creating branches, merging code, rebasing, writing commit messages, managing PRs, cleaning git history, analyzing staged changes.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/git-workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

The body is highly actionable with excellent concrete workflows and examples, but it is heavily padded with a git cheat-sheet of commands Claude already knows, and everything is crammed into one long SKILL.md with no reference files. The trailing self-assessment claiming '~480 lines (under 500-line rule)' is also inaccurate (the file is ~855 lines).

Suggestions

Move boilerplate git command listings (stash, tagging, bisect, reflog, .gitignore patterns, Quick Reference) into a reference file such as references/command-cheatsheet.md, keeping SKILL.md focused on the atomic-commit workflow and philosophy.

Trim sections that restate knowledge Claude already has (Common Ignores, .gitignore Patterns, Viewing History flag lists) to a few non-obvious pointers, cutting the body to well under 500 lines.

Add explicit guardrails around destructive operations (git reset --hard HEAD~1, git push --force-with-lease, rebase -i) such as pre-checks (git status, reflog snapshot) and recovery steps, and remove the inaccurate 'Line Count: ~480' footer.

DimensionReasoningScore

Conciseness

Roughly 400 of the ~855 lines restate standard git knowledge Claude already has (stash/tag/bisect/reflog command listings, .gitignore patterns, Common Ignores, and a 60-line Quick Reference cheat sheet), which is noticeably padded even though the core commit-organization sections earn their place.

2 / 5

Actionability

Commands are copy-paste ready throughout; the Real Scenario gives a complete executable sequence with actual file paths and commit messages, and good/bad commit message examples cover the common cases.

5 / 5

Workflow Clarity

The core division workflow is clearly sequenced with verification checkpoints (git status, git diff --cached --stat between staging and committing) plus checklists and an amend warning, but destructive recovery commands (git reset --hard HEAD~1) lack guardrails and the rebase/conflict flow's validation is thinner, leaving minor validation gaps.

4 / 5

Progressive Disclosure

No bundle files exist and the entire ~855-line body is inlined in SKILL.md, with content that clearly belongs in separate reference files (gitignore patterns, advanced techniques, quick reference) inline; good section headers keep it navigable, placing it above the header-less monolith anchor but short of appropriate file splitting.

3 / 5

Total

14

/

20

Passed

Description

96%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 highly effective description: explicit capabilities, actions, natural trigger keywords with synonyms, and a concrete Use-when clause. The only weakness is breadth within the git domain, which slightly raises overlap risk with specialized git skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities ("commit organization, branching strategies, merge/rebase workflows, PR management, history cleanup, staged change analysis, single-responsibility commits") plus an explicit Actions list, giving comprehensive concrete coverage rather than minor gaps.

5 / 5

Completeness

It explicitly answers what (Capabilities and Actions lists) and when ("Use when: organizing commits, creating branches, merging code, rebasing, writing commit messages, managing PRs, cleaning git history, analyzing staged changes"), matching the anchor that requires both with concrete trigger phrases.

5 / 5

Trigger Term Quality

The Keywords list comprehensively covers natural user phrases with synonyms ("git commit", "git rebase", "PR", "pull request", "atomic commit", "conventional commits", "GitFlow", "trunk-based", "cherry-pick", "squash", "amend", "interactive rebase", "staged changes"), matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

The git-workflow niche is mostly distinct from non-git skills, but its breadth (commit messages, PRs, code review, history cleanup) creates minor overlap risk with closely related specialized git skills such as commit-message generators; it is not the clear minimal-conflict niche of the 5 anchor.

4 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (857 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
samhvw8/dot-claude
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.