Helps with git workflows including conventional commit messages, branching strategies, merge conflict resolution, and changelog generation. Triggers on: "git commit message", "branching strategy", "resolve conflict", "generate changelog".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Git Workflow
## Instructions
### Step 1: Identify the Task
Determine which workflow the user needs:
1. **Commit message** - writing or improving a commit message
2. **Branching strategy** - choosing or implementing a branching model
3. **Conflict resolution** - resolving merge conflicts
4. **Changelog** - generating release notes from commit history
Ask clarifying questions only if the intent is ambiguous.
### Step 2: Conventional Commits
When writing commit messages, follow the Conventional Commits specification:
```
<type>[optional scope]: <description>
[optional body]
[optional footer(s)]
```
**Types (in order of frequency):**
- `feat` - new feature (correlates with MINOR in semver)
- `fix` - bug fix (correlates with PATCH in semver)
- `docs` - documentation only
- `style` - formatting, no code change
- `refactor` - neither fix nor feature
- `perf` - performance improvement
- `test` - adding or fixing tests
- `chore` - build process, tooling, dependencies
- `ci` - CI/CD configuration changes
**Rules:**
- Description is lowercase, no period at end, max 72 characters
- Body wraps at 72 characters, explains what and why (not how)
…
The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_a3e424pordpdpq2j
GET https://markdownregistry.com/api/v1/resolve?ref=timwukp/agent-skills-best-practice/git-workflow
GET https://markdownregistry.com/api/v1/blob/c7751180b2d4955dd1949a80db14e15e5b60e3e36845df83ec609f162fac43c3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
timwukp/agent-skills-best-practice · skills/skills/agentcore-harness-builder/SKILL.md · Build production-ready AWS Bedrock AgentCore Harness agents end to end — declarative model + prompt, managed/BYO…
timwukp/agent-skills-best-practice · skills/skills/ai-native-sdlc/SKILL.md · Drive a change through an AI-native software development lifecycle as a loop of committed, machine-readable artifacts —…
timwukp/agent-skills-best-practice · skills/skills/algorithmic-art/SKILL.md · Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users…
timwukp/agent-skills-best-practice · skills/skills/aws-well-architected-review/SKILL.md · Reviews AWS architectures, IaC, and design docs against the AWS Well-Architected Framework's six pillars, producing a…
timwukp/agent-skills-best-practice · skills/skills/brand-guidelines/SKILL.md · Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having…
timwukp/agent-skills-best-practice · skills/skills/canvas-design/SKILL.md · Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user…
