git-workflow
Skill4 starsChanged 7 months agoMITView on GitHub
Use when doing any git operations (branching, committing, pushing) so the repo history stays clean and matches the preferred workflow
- Deletes or force-pushes
- Commits and pushes
187 other projects use a version of this.
Adopted by
Most recently taken up by
- avpit/claude-skillstheir own version, first seen Nov 16, 2026
- AlejandroGodius/claude-skillstheir own version, first seen Nov 16, 2026
- RichardMcQuiston01/unofficial-claude-skill-examplestheir own version, first seen Nov 16, 2026
- AndresArreguy/ecc-pi-porttheir own version, first seen Nov 16, 2026
- fabioc-aloha/Alex_ACT_ONEtheir own version, first seen Nov 15, 2026
- juninmd/skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use squad-commands, ci-cd-pipelines and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Microsoft AzureSkillsquad-commands
Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.
Also in 5 projects that use this
harrissohail6Skillci-cd-pipelines
CI/CD pipeline design and implementation. Auto-activates when discussing deployment, automation, or pipelines.
Also in 6 projects that use this
Microsoft AzureSkillarchitectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
Also in 4 projects that use this
frostneySkillnative-nostalgia-stack
Applies the user's FreePascal toolchain and its build, formatting, hook, and test contracts while leaving project-specific mechanics local. Use when scaffolding or working in a FreePascal project that follows this toolchain.
Also in 3 projects that use this
AGMO-IncSkillplugin-review
Use to analyze plugin usage patterns and suggest improvements. Triggers on "플러그인 리뷰", "plugin review", "사용 패턴 분석".
Also in 3 projects that use this
Galaxy-DawnSkillresults-report
This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.
Also in 3 projects that use this
- +6 more from Azure
Other versions187 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 187
- langfuse/langfuse★ 37ksame name
- modelcontextprotocol/typescript-sdk★ 14ksame name
- JetBrains/ideavim★ 10ksame name
- jokob-sk/NetAlertX★ 7.4ksame name
- netalertx/NetAlertX★ 7.4ksame name
- Galaxy-Dawn/claude-scholar★ 5.9ksame name
- github/gh-aw★ 5.6ksame name
- modelcontextprotocol/csharp-sdk★ 4.6ksame name
- antonbabenko/pre-commit-terraform★ 3.8ksame name
- github/squad★ 3.4ksame name
177 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- continuous-developmentSkill
- continuous-improvementSkill
- rubyllmSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
25 rules. 0 are common, 22 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 164 edited versions we read keep these.
22
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 14
Only stop to report progress under exactly two conditions:
- Distinctive: line 22
Do not create branches “just in case”.
- Distinctive: line 23
If asked to create a branch, use a plain branch name with no tool/model prefixes.
- Very specific: line 24
Do not prefix with codex/, claude/, agent/, etc.
- Distinctive: line 25
Commit only complete slices: done, verified, and ready to ship.
- Very specific: line 26
Commit messages are short plain sentences (no feat:, chore:, etc.).
- Distinctive: line 27
Prefer a single sentence.
- Distinctive: line 28
If needed, use 2–3 short sentences total (no paragraphs).
- Distinctive: line 29
Never use git add .. Always stage by explicit filenames to avoid accidental commits.
- Distinctive: line 41
Check working tree state: git status
- Distinctive: line 46
Only create a branch when explicitly asked.
- Distinctive: line 47
Keep branch names simple and descriptive, like:
- Distinctive: line 55
Do not commit partial work, experiments, or “WIP” unless the human explicitly asks.
- Distinctive: line 56
If a change is essentially “more of the same” as the most recent commit (tight follow-up, fixup, small adjustment), prefer amending the …
- Distinctive: line 57
If it is unclear whether to amend vs make a new commit, ask.
- Very specific: line 58
Do not add co-authoring trailers (no Co-authored-by:).
- Distinctive: line 76
Pushing to
mastertriggers a deploy: Treat git push as a production operation. - Distinctive: line 80
Do not push to master unless you are intentionally deploying to production.
- Distinctive: line 84
Only push to master when all unpushed commits are complete, verified, and safe for production.
- Distinctive: line 85
Do not push if there are missing dependencies, unfinished work, or “it should work” assumptions.
- Distinctive: line 86
If the change set is not ready to deploy, keep commits local until it is ready.
- Distinctive: line 87
If the work is finished and verified, prefer pushing and deploying rather than accumulating completed work locally without a reason.
- Distinctive: line 91
Only push to master when ready to release a new version.
- Distinctive: line 96
Never run destructive git commands (git reset --hard, forced checkouts, force pushes) unless explicitly requested and confirmed.
- Distinctive: line 97
If unrelated changes exist in the worktree, do not revert them unless asked.
“Common” is measured: kept by at least 6 in 10 of the 164 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Git Workflow
Overview
This skill defines the default git workflow for this environment: work directly on master unless explicitly asked otherwise, keep branches unprefixed, and commit only complete, verified slices with short commit messages.
Important: git work (staging/committing/pushing, etc) is not a signal to stop or report progress. After any commit, immediately return to the continuous loop: pick the next top-most unchecked PLAN.md Now item and keep going.
Only stop to report progress under exactly two conditions:
- All
PLAN.mdNow work is complete, or - A hard blocker / high-risk gate / product decision is encountered.
Defaults (Rules)
- Work on
masterunless the human explicitly asks for a new branch. - Do not create branches “just in case”.
- If asked to create a branch, use a plain branch name with no tool/model prefixes.
- Do not prefix with
codex/,claude/,agent/, etc.
- Do not prefix with
- Commit only complete slices: done, verified, and ready to ship.
- Commit messages are short plain sentences (no
feat:,chore:, etc.).- Prefer a single sentence.
- If needed, use 2–3 short sentences total (no paragraphs).
- Never use
git add .. Always stage by explicit filenames to avoid accidental commits.
Before Any Commit
Confirm the slice is complete:
- The intended outcome is achieved.
- Verification was run (tests or the project’s chosen verification step).
- Any required checklist/docs updates for the slice are included.
Then:
- Check working tree state:
git status - Review diff:
git diff(andgit diff --stagedafter staging)
Branching Rules
- Only create a branch when explicitly asked.
- Keep branch names simple and descriptive, like:
fix-login-timeoutbilling-webhook-hardeningupgrade-rails-8
Commit Rules
- One commit per completed slice whenever feasible.
- Do not commit partial work, experiments, or “WIP” unless the human explicitly asks.
- If a change is essentially “more of the same” as the most recent commit (tight follow-up, fixup, small adjustment), prefer amending the most recent commit instead of making a new commit.
- If it is unclear whether to amend vs make a new commit, ask.
- Do not add co-authoring trailers (no
Co-authored-by:). The human is the sole author.
Commit Message Style
Good:
Fix login redirect loopAdd read-only admin audit viewReduce flaky checkout test timeouts
Avoid:
feat: add admin audit viewchore: stuff- Long multi-paragraph explanations
Pushing
Pushing to master triggers a deploy. Treat git push as a production operation.
Hard gate:
- Do not push to
masterunless you are intentionally deploying to production.
Rules:
- Only push to
masterwhen all unpushed commits are complete, verified, and safe for production. - Do not push if there are missing dependencies, unfinished work, or “it should work” assumptions.
- If the change set is not ready to deploy, keep commits local until it is ready.
- If the work is finished and verified, prefer pushing and deploying rather than accumulating completed work locally without a reason.
Gems/libraries:
- Only push to
masterwhen ready to release a new version. - It is acceptable to keep collecting local commits until release-ready.
Safety Defaults
- Never run destructive git commands (
git reset --hard, forced checkouts, force pushes) unless explicitly requested and confirmed. - If unrelated changes exist in the worktree, do not revert them unless asked. Keep your work focused.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

