JPeetz/agent-skills / skills/git-release/git-workflow-and-versioning
git-workflow-and-versioning
VerifiedUse this skill when making any code change — committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or organizing work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 613 B |
| LICENSE | other | 810 B |
| SKILL.md | skill md | 11.2 KB |
| evals/evals.json | config | 3.0 KB |
evals/evals.json
View on GitHub{
"skill_name": "git-workflow-and-versioning",
"evals": [
{
"id": 1,
"prompt": "I just finished implementing the login feature. It touches auth.ts, login-form.tsx, styles.css, and I also fixed a typo in the README. Commit it all.",
"expected_output": "The skill should NOT commit everything together. It should split: (a) feat: login form component, (b) feat: auth API endpoint, (c) chore: fix typo in README — three separate atomic commits with descriptive messages.",
"expectations": [
"Splits the work into logical atomic commits, not one bulk commit",
"Each commit message follows the type: description format",
"README typo fix is separated as chore/docs, not mixed with feature work"
]
},
{
"id": 2,
"prompt": "I need to fix a critical production bug but I have half-finished work on my branch. What do I do?",
"expected_output": "Commit or stash the current work, create a fix branch from the last known-good commit on main, apply the hotfix, merge, then return to the feature branch.",
"expectations": [
"Recommends stashing or committing in-progress work first",
"Creates a fix branch from main or the last stable commit",
"Does not suggest mixing the hotfix into the feature branch"
]
},
{
"id": 3,
"prompt": "Our main branch has a bug that was introduced sometime in the last 30 commits. How do I find which commit caused it?",
"expected_output": "Use git bisect: mark current HEAD as bad, a known-good commit as good, and let git narrow down the offending commit by testing each midpoint.",
"expectations": [
"Recommends git bisect with the correct workflow",
"Explains how to mark bad/good commits",
"Suggests a script or manual test at each bisect step"
]
},
{
"id": 4,
"prompt": "Release v2.0.0: we added a breaking API change (removed deprecated endpoints) and fixed 3 bugs since v1.9.0. What version and what changelog entry?",
"expected_output": "Version 2.0.0 (breaking change = major bump). Changelog with Added/Changed/Fixed sections, a migration note for the removed endpoints, and a deprecation window reference.",
"expectations": [
"Bumps to 2.0.0, not 1.10.0 or 1.9.4",
"Changelog has a migration note for the breaking change",
"Separates breaking changes from bug fixes in the changelog structure"
]
},
{
"id": 5,
"prompt": "I need two agents to work on different features in the same repo at the same time without stepping on each other.",
"expected_output": "Use git worktrees: create separate worktree directories for each feature branch. Each agent works in isolation. Merge sequentially.",
"expectations": [
"Recommends git worktrees, not just separate branches in the same working tree",
"Explains the worktree create/remove workflow",
"Notes that changes remain isolated until explicitly merged"
]
}
]
}Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |