Name: git-advanced-workflows
Rating: 46.400000000000006 (1 reviews)
Author: administrakt0r

git-advanced-workflows

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

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/git-advanced-workflows/SKILL.md

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

Quality

Content

53%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 content is rich and largely executable, but it over-explains familiar Git concepts, lacks explicit validation checkpoints for its destructive operations, and critically advertises reference/asset/script files that are not present in the bundle, breaking progressive disclosure.

Suggestions

Trim explanations of concepts Claude already knows (rebase operation meanings, bisect mechanics, 'Swiss Army knife' phrasing) and keep only the command-driven content.

Add explicit validation checkpoints to destructive workflows — e.g., after `git rebase -i main`, insert a 'Validate: run tests / `git log --oneline`' step before `git push --force-with-lease`.

Either create the missing referenced files (references/git-rebase-guide.md, assets/git-workflow-checklist.md, scripts/git-clean-branches.sh, resources/implementation-playbook.md) or remove the broken references and the 'open resources/implementation-playbook.md' instruction.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient command-driven content, but it restates well-known Git behavior (e.g., explaining what each rebase operation does, 'Swiss Army knife of Git history editing', bisect mechanics) that Claude already knows, and repeats commands across 'Core Concepts' and 'Practical Workflows'.	3 / 5
Actionability	It provides numerous concrete, executable git commands for each technique with real flags and example hashes, covering the common cases; minor gaps like placeholder hashes and the 'Continue until bug found' prose keep it from a 5.	4 / 5
Workflow Clarity	Workflows are sequenced, but operations are destructive/batch (force-push, history rewrite, branch deletion) and validation checkpoints are largely absent — 'Test Before Force Push' and recovery steps appear only as prose in Best Practices, not as explicit validate-then-proceed loops, capping clarity at 3 per the rubric's destructive-operation rule.	3 / 5
Progressive Disclosure	The SKILL.md body is a ~400-line monolith that inlines all material rather than splitting it, and it lists a Resources section plus 'open resources/implementation-playbook.md', but none of the referenced bundle files (references/, assets/, scripts/, resources/) actually exist in the bundle, so the cross-file structure is broken.	2 / 5
	Total	12 / 20 Passed

Description

45%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.

The description is grammatically clean and third-person, but it reads as marketing-flavored and over-claims ('recover from any situation with confidence') without naming the concrete operations or explicit trigger phrases. It answers 'what' but not 'when', capping completeness at 3.

Suggestions

Replace the over-claiming summary with concrete actions: e.g., 'Run interactive rebase, cherry-pick commits, bisect bugs, and manage worktrees to maintain clean Git history and recover lost commits.'

Add an explicit trigger clause: 'Use when cleaning up commit history before merging, applying commits across branches, finding bug-introducing commits, or recovering from Git mistakes.'

Drop the buzzword tail 'recover from any situation with confidence' — it adds no trigger value.

Dimension	Reasoning	Score
Specificity	It names the domain ('advanced Git techniques') but the only concrete action framing is generic ('maintain clean history, collaborate effectively, recover from any situation'), with no enumerated specific operations like rebase, cherry-pick, or bisect.	2 / 5
Completeness	There is a clear 'what' (advanced Git techniques for clean history / collaboration / recovery) but no explicit 'Use when...' trigger clause, which the guidelines cap at 3.	3 / 5
Trigger Term Quality	'advanced Git techniques' and 'clean history' are somewhat natural, but the description lacks the common phrasings users actually say ('rebase', 'cherry-pick', 'bisect', 'interactive rebase', 'squash commits') and any synonyms.	3 / 5
Distinctiveness Conflict Risk	'Advanced Git techniques' carves a reasonably distinct niche away from basic git/version-control skills, with only minor overlap risk with general git helpers.	4 / 5
	Total	12 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/git-advanced-workflows/SKILL.md
Commit: 57c135b

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.