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

git-pr-workflows-git-workflow

Orchestrate a comprehensive git workflow from code review through PR creation, leveraging specialized agents for quality assurance, testing, and deployment readiness. This workflow implements modern g

Quality

48%

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-pr-workflows-git-workflow/SKILL.md

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

Quality

Content

38%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 lays out a thorough, well-sequenced multi-phase git workflow but is held back by verbosity, unresolved prompt placeholders, missing validate-and-retry feedback loops for destructive steps, and a broken reference to a nonexistent playbook file.

Suggestions

Replace the verbose inline Task-tool prompt templates with concise directives and move the full prompt text into a real referenced file (create resources/implementation-playbook.md or remove the broken reference).

Resolve or eliminate the "[insert ...]" placeholders — provide concrete guidance for how context is passed between phases instead of leaving fill-in-the-blank prompts.

Add explicit validation checkpoints with feedback loops, e.g. 'If code-review reports critical/high issues, stop and fix before advancing to Phase 2; re-run review until clear' before push/PR steps.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose — full multi-line Task-tool prompt templates with embedded enumeration and JSON output specs, plus a bracketed 'Extended thinking' prose block — padding that Claude could infer, fitting the score-2 anchor rather than 3.	2 / 5
Actionability	It gives concrete Task-tool invocations (subagent_type, flags, branch-naming patterns) but every prompt leaves unfilled placeholders like "[insert issues summary]" and "[insert file list and summary]", making the guidance incomplete rather than copy-paste ready.	3 / 5
Workflow Clarity	Five phases are clearly sequenced with context threading and expected outputs, but for destructive/batch operations (push, PR creation) there are no explicit validate-and-fail feedback loops gating progression; per the rubric cap this holds at 3 rather than 4.	3 / 5
Progressive Disclosure	The only reference — "open resources/implementation-playbook.md" — points to a file that does not exist (no references/ or resources/ directory), and the long inlined prompt templates arguably belong in a separate file, matching the score-2 anchor of minimal/buried structure.	2 / 5
	Total	10 / 20 Passed

Description

58%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 states a clear, multi-stage capability with concrete actions but is truncated mid-sentence ("modern g") and lacks any "Use when..." trigger guidance, capping completeness and trigger-term quality. It is specific and fairly distinct but not exemplary.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when the user wants to run a full review-to-PR git workflow with automated quality, test, and deploy checks').

Fix the truncated text — 'This workflow implements modern g' is cut off and should be completed or removed.

Include synonyms and concrete file/flag terms users would naturally say (e.g., 'pull request', 'commit message', 'Conventional Commits', '--draft-pr') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — "from code review through PR creation, leveraging specialized agents for quality assurance, testing, and deployment readiness" — with only minor coverage gaps, fitting the score-4 anchor rather than 3 (which expects just 1-2 actions).	4 / 5
Completeness	It gives a clear "what" (orchestrate a git workflow through review to PR) but no explicit "when" trigger clause; per the judging guidelines a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant keywords ("git workflow", "code review", "PR creation", "specialized agents") but no natural "Use when..." phrasing or synonyms, matching the score-3 anchor of relevant-but-incomplete keyword coverage rather than 4's near-comprehensive set.	3 / 5
Distinctiveness Conflict Risk	"Comprehensive git workflow from code review through PR creation with multi-agent orchestration" carves a mostly distinct niche with only minor overlap against generic code-review/git skills, fitting the score-4 anchor.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/git-pr-workflows-git-workflow/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.