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

55%

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

Quality

Content

52%Weight 40%Scale 1-3

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

The body is a detailed, well-sequenced multi-agent workflow with concrete tool calls and flag handling, but it is verbose, relies on template placeholders rather than executable examples, and is monolithic with no progressive disclosure into reference files.

Suggestions

Cut the extended-thinking preamble and generic "Use this skill when / Do not use this skill when / Instructions" boilerplate; assume Claude knows orchestration basics and keep only task-specific guidance.

Move the long per-phase agent prompt templates into a references/ file (e.g. prompts.md) and reference it one level deep, so SKILL.md stays a lean overview.

Add an explicit validation feedback loop around the destructive steps (e.g. after pre-push validation: if checks fail, fix and re-run before proceeding) to reach the top workflow-clarity anchor.

Dimension	Reasoning	Score
Conciseness	The body carries verbose filler such as the extended-thinking preamble explaining multi-agent orchestration and generic boilerplate ("Clarify goals, constraints, and required inputs", "Use this skill when... working on complete git workflow...") that explains concepts Claude already knows, placing it between the verbose and mostly-efficient anchors but closer to verbose.	1.5 / 3
Actionability	It gives concrete guidance — Task tool calls with specific subagent_type values, full prompt templates, flag definitions, branch-naming patterns, and revert commands — but the prompts are templates with placeholders like "[insert issues summary]" rather than copy-paste executable code, so it is just below the fully-executable anchor.	2.5 / 3
Workflow Clarity	A clear five-phase sequence with numbered steps and per-step "Context from previous" / "Expected output" plus a Success Criteria checklist gives strong sequencing, but destructive batch operations (push, merge, revert) lack an explicit validate→fix→retry feedback loop, keeping it below the top anchor.	2.5 / 3
Progressive Disclosure	There are no bundle files (references/scripts/assets absent) and no external file references; the large embedded agent-prompt templates and reference tables all live inline in one monolithic SKILL.md that could be split out, so it sits between the monolithic and lightly-structured anchors.	1.5 / 3
	Total	8 / 12 Passed

Description

58%Weight 40%Scale 1-3

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 names a concrete domain and several real actions but is padded with marketing language, lacks any explicit "Use when" trigger guidance, and is truncated mid-sentence. It is serviceable for activation but well short of the strongest examples.

Suggestions

Complete the truncated sentence and drop buzzword filler ("comprehensive", "leveraging specialized agents", "modern") so the description reads as concrete actions only.

Add an explicit trigger clause, e.g. "Use when the user asks to take changes from review through a pull request, or wants a multi-step git workflow with quality checks, tests, and PR creation."

Include natural user variations such as "pull request", "commit", and "merge" alongside "PR" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Quotes concrete actions such as "code review through PR creation" and "quality assurance, testing, and deployment readiness" within a named git domain, matching the "multiple specific concrete actions" anchor; not a 3 because buzzword padding ("comprehensive", "leveraging specialized agents", "modern") dilutes precision.	2.5 / 3
Completeness	It states what the skill does but provides no "Use when..." or equivalent trigger guidance, and the sentence is truncated mid-way ("...implements modern g"), so per the guideline a missing explicit trigger clause caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Terms like "git workflow", "code review", and "PR creation" are relevant but framed as marketing ("Orchestrate a comprehensive...") rather than natural user phrasing, and common variations (pull request, commits, merge) are missing, so it sits at the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	The git-workflow-through-PR niche has distinct triggers and is unlikely to fire for unrelated skills, fitting the top anchor; it does not fully reach 3 because "comprehensive git workflow" is broad enough to overlap with simpler git/commit skills.	2.5 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/git-pr-workflows-git-workflow/SKILL.md
Commit: e63f7dd

Reviewed: 13 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.