CtrlK
BlogDocsLog inGet started
Tessl Logo

git-advanced-workflows

Master advanced Git techniques to maintain clean history, collaborate effectively, and recover from any situation with confidence.

42

Quality

43%

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 ./plugins/antigravity-bundle-oss-maintainer/skills/git-advanced-workflows/SKILL.md

The canonical home for this skill is git-advanced-workflows in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides comprehensive coverage of advanced Git workflows with concrete, executable commands, which is its primary strength. However, it is overly verbose for Claude—much of the content explains Git concepts Claude already knows rather than focusing on novel workflow patterns and decision-making guidance. The most significant weakness is the lack of validation checkpoints in workflows involving destructive operations like rebasing and force pushing, and the referenced bundle files don't exist.

Suggestions

Add explicit validation steps to destructive workflows (e.g., 'Run `git log --oneline` to verify rebase result before force pushing', 'Run `git diff main..HEAD` to confirm expected changes')

Trim core concepts sections significantly—Claude knows what cherry-pick and bisect do. Focus on decision criteria (when to use each technique) and edge cases rather than basic usage

Create the referenced bundle files (references/git-rebase-guide.md, assets/git-workflow-checklist.md, etc.) and move detailed reference material there, keeping SKILL.md as a concise overview with workflow patterns

Replace the vague Instructions section ('Clarify goals, constraints, and required inputs') with specific guidance on how Claude should assess the user's situation and select the appropriate workflow

DimensionReasoningScore

Conciseness

The skill contains useful content but is notably verbose for Claude. Phrases like 'Interactive rebase is the Swiss Army knife of Git history editing' and 'Future you will thank present you' are unnecessary filler. The 'Do not use this skill when' section adds little value. Many of the core concepts (cherry-pick, bisect, rebase) are things Claude already knows well, and the explanations could be much more condensed to focus on the specific workflow patterns rather than teaching Git basics.

3 / 5

Actionability

The skill provides concrete, executable bash commands throughout with realistic examples covering common scenarios. The practical workflows section gives copy-paste ready command sequences. Minor gaps exist—some workflows lack specific conflict resolution steps, and the 'Instructions' section at the top is vague ('Clarify goals, constraints, and required inputs') rather than actionable.

4 / 5

Workflow Clarity

The practical workflows provide clear sequences of commands, but they lack explicit validation checkpoints. For destructive operations like force pushing, rebasing, and history rewriting, there are no verification steps (e.g., 'verify the rebase result with git log --oneline before force pushing'). The best practices mention testing before force push but don't integrate validation into the workflows themselves. Per rubric rules, missing feedback loops for destructive changes caps this at 3.

3 / 5

Progressive Disclosure

The Resources section references several supporting files (references/git-rebase-guide.md, assets/git-workflow-checklist.md, etc.), but no bundle files are provided, meaning these references are broken. The main file itself is quite long (~300 lines) and could benefit from moving the core concepts reference material into separate files while keeping the SKILL.md as a concise overview with workflow patterns. The internal structure uses headers well but the content is monolithic.

3 / 5

Total

13

/

20

Passed

Description

28%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.

This description reads like a marketing tagline rather than a functional skill description. It lacks concrete actions, natural trigger terms, and any explicit 'when to use' guidance, making it difficult for Claude to reliably select this skill from a pool of alternatives.

Suggestions

Replace vague phrases with specific Git operations (e.g., 'interactive rebase, cherry-pick, bisect, reflog recovery, squash commits, resolve merge conflicts').

Add an explicit 'Use when...' clause with natural trigger terms like 'rebase', 'squash commits', 'git history', 'recover lost commits', 'merge conflict'.

Remove aspirational language ('with confidence', 'effectively') and replace with concrete scenarios that distinguish this from basic Git skills.

DimensionReasoningScore

Specificity

Names the domain (Git) but actions are vague and abstract — 'maintain clean history', 'collaborate effectively', and 'recover from any situation' are aspirational phrases rather than concrete actions like 'interactive rebase', 'cherry-pick commits', or 'resolve merge conflicts'.

2 / 5

Completeness

The 'what' is vague (advanced Git techniques) and there is no explicit 'when' clause or trigger guidance. The description reads more like a course tagline than a skill selection guide.

2 / 5

Trigger Term Quality

Only 'Git' is a natural keyword a user might say. The rest ('clean history', 'collaborate effectively', 'recover from any situation') are not terms users would naturally use when seeking help with specific Git operations like rebase, merge, stash, or bisect.

2 / 5

Distinctiveness Conflict Risk

It specifies 'advanced Git techniques' which narrows it somewhat from general version control, but could still overlap with basic Git skills, commit message skills, or collaboration workflow skills due to the broad language.

3 / 5

Total

9

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.