git-workflow-specialist
Git expert covering branching strategies, collaboration, conflict resolution, and best practices
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install sandraschi/advanced-memory-mcp/git-workflow-specialist skilz install sandraschi/advanced-memory-mcp/git-workflow-specialist --agent opencode skilz install sandraschi/advanced-memory-mcp/git-workflow-specialist --agent codex skilz install sandraschi/advanced-memory-mcp/git-workflow-specialist --agent gemini
First time? Install Skilz: pip install skilz
Works with 22+ AI coding agents
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/sandraschi/advanced-memory-mcp cp -r advanced-memory-mcp/skills/technical/git-workflow-specialist ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
using-git-worktrees
by obraUse when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees w...
changelog-automation
by wshobsonAutomate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating rel...
git-advanced-workflows
by wshobsonMaster advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situati...
stripe-integration
by wshobsonImplement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks. Use when integrating Stri...
Agentic Skill Details
- Owner
- sandraschi (GitHub)
- Repository
- advanced-memory-mcp
- Type
- Technical
- Meta-Domain
- development
- Primary Domain
- git
- Market Score
- 89.0
Agent Skill Grade
B
Score: 89/100
Click to see breakdown
Score Breakdown
Areas to Improve
- No trigger phrases
- Conflicting confidence ratings within same file
- Description lacks explicit trigger terms
Recommendations
- Add trigger phrases to description for discoverability
- Add table of contents for files over 100 lines
Graded: 1/19/2026
Developer Feedback
I took a look at your git-workflow-specialist skill and wanted to share some thoughts.
Links:
The TL;DR
You're at 89/100 — solid B-grade territory. This is based on Anthropic's skill best practices rubric. Your strongest area is Progressive Disclosure Architecture (28/30) — the modular structure with separate files for detailed guidance really shines. The weakest spot is Spec Compliance (12/15), mainly around missing metadata that helps people discover and invoke your skill.
What's Working Well
- Architecture is clean — SKILL.md as the entry point with detailed modules in separate files is exactly how PDA should work. You're not dumping everything into one file, which keeps token usage lean.
- Strong utility focus — Your decision matrices and checklists (research-checklist.md, decision frameworks) give people actual tools to work with, not just theory. The problem-solving power here scored 8/8.
- Consistent voice — Imperative form throughout ("Do X", "Check Y") makes instructions clear without being prescriptive. The writing stays objective and instructional.
The Big One: Missing Trigger Phrases
Your description field lacks explicit trigger terms, and this is costing you 2+ points in spec compliance. Right now it reads:
"Git expert covering branching strategies, collaboration, conflict resolution..."
People invoking Claude won't know to call your skill. You need trigger phrases baked into that description. Change it to something like:
"Performs git workflow specialist operations. Use when asked to 'git workflow', 'git branching strategy', 'merge conflict resolution', 'git collaboration patterns', or 'git best practices'."
This small change makes your skill actually discoverable and invokable. It's low-effort, high-impact.
Other Things Worth Fixing
Confidence levels are mixed — modules/core-guidance.md has both 🟡 MEDIUM and 🔴 LOW confidence ratings for similar content. Pick one per section so users know what to trust.
Light on examples — You've got great conceptual guidance, but adding actual git command examples and workflow templates would bump utility from 18/20 to a solid 20/20. Show the actual commands people run.
Table of contents — For files over ~100 lines, a quick TOC at the top helps navigation. Your modules are well-structured but a
_toc.mdreference at the skill level would make it even clearer.
Quick Wins
✓ Add trigger phrases to description (frontmatter) — +2 points
✓ Consolidate confidence levels in core-guidance.md — +1 point
✓ Sprinkle in command examples (git checkout, merge commands) — +1 point
These three moves get you to 93/100 territory with minimal effort.
Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that installs skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.
Browse Category
More development Agentic SkillsReport Security Issue
Found a security vulnerability in this agent skill?