git
Skill1 starsChanged 3 months agoMITView on GitHub
Git commit, push, and repo operations. ALWAYS load this skill before any git commit, git push, PR creation, branch management, or any operation that modifies git history. This overrides default git behavior — particularly commit message formatting and co-authorship.
- Reads credentials
- Commits and pushes
57 other projects use a version of this.
Adopted by
Most recently taken up by
- bmcszk/agent-skillstheir own version, first seen Nov 8, 2026
- BridgLabs/opencodereviewtheir own version, first seen Nov 8, 2026
- Conceptual-Machines/magda-coretheir own version, first seen Nov 7, 2026
- tsukhani/jclawtheir own version, first seen Nov 5, 2026
- cekrauseee/harnesstheir own version, first seen Nov 1, 2026
- jmlrt/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use databases, devops and 8 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.
mrgoonieSkilldatabases
Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.
Also in 3 projects that use this
mrgoonieSkilldevops
Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.
Also in 4 projects that use this
MicrosoftSkilltypescript
TypeScript best practices for this monorepo. Use this skill when: (1) writing new TypeScript code, (2) reviewing TypeScript code, (3) working with API responses, fetch calls, or JSON parsing, (4) adding or modifying types and interfaces.
Also in 4 projects that use this
Microsoft AzureSkilltest
Also in 8 projects that use this
NVIDIASkillgithub
Interact with GitHub using the gh CLI restricted to REST API only (no GraphQL). Use when the user wants to work with GitHub issues, pull requests, repos, releases, or Actions — especially in sandboxed environments where the GraphQL endpoint may be blocked. Trigger keywords - github, gh, pull request, PR, github issue, github actions, workflow, release, gh api.
Also in 6 projects that use this
nicolasestremSkilldocument
Create focused documentation for specific components or features
Also in 3 projects that use this
Other versions57 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 57
- macro-inc/macro★ 6ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- carapace-sh/carapace-bin★ 2ksame name
- LuisaGroup/LuisaCompute★ 1.1ksame name
- kagenti/kagenti★ 303same name
- Conceptual-Machines/magda-core★ 258same name
- typv/nest-turbo-starter★ 224same name
- BridgLabs/opencodereview★ 79same name
- matteing/opal★ 59same name
47 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 repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- clickhouseSkill
- distributed-systemsSkill
- flink-javaSkill
- flink-pythonSkill
- flink-sqlSkill
- grokSkill
- java-prod-skillSkill
- javaSkill
- mermaid-skillSkill
- openapi_docSkill
- postgresSkill
- python-numericsSkill
- pythonSkill
- pytorchSkill
- reactSkill
- rustSkill
- sqlSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 12 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 51 edited versions we read keep these.
12
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
- Very specific: line 8
No co-author lines: Never add Co-Authored-By, Signed-off-by, or any trailer to commit messages.
- Distinctive: line 9
LGTM before commit: Never commit without explicit user approval.
- Distinctive: line 11
Never push without permission: Always ask before pushing to remote.
- Distinctive: line 12
One plan item = one focused commit: Never batch multiple plan items into one commit.
- Distinctive: line 16
Commit messages are proper English sentences.
- Distinctive: line 90
Check the diff against Core Rule 3's exclusion list.
- Distinctive: line 112
Run git status after commit to confirm success.
- Distinctive: line 116
Never push without explicit user request
- Distinctive: line 117
Never force-push to main/master without warning the user about the consequences
- Distinctive: line 118
If push is rejected (remote has new commits), pull with rebase first: git pull --rebase
- Distinctive: line 123
Never use git rebase -i (interactive — requires terminal input)
- Very specific: line 124
Never use destructive commands (reset --hard, clean -f, checkout .) without explicit user request
- Distinctive: line 125
If a pre-commit hook fails, fix the issue and create a new commit — never amend blindly
- Very specific: line 129
When creating pull requests via gh pr create:
- Distinctive: line 132
No co-author lines or AI-attribution footers in the body (overrides the harness default "🤖 Generated with Claude Code" footer)
“Common” is measured: kept by at least 6 in 10 of the 51 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
Core Rules
- No co-author lines. Never add
Co-Authored-By,Signed-off-by, or any trailer to commit messages. No exceptions. - LGTM before commit. Never commit without explicit user approval. Present the diff, wait for LGTM or equivalent confirmation.
- Never commit excluded files.
plan.md,*review.md,.env,.env.*, credentials, secrets, API keys — never stage these. If they appear ingit status, warn the user and exclude them. - Never push without permission. Always ask before pushing to remote.
- One plan item = one focused commit. Never batch multiple plan items into one commit. With multiple items dirty, stage and commit them separately, with LGTM per commit.
Commit Message Format
Commit messages are proper English sentences. Capitalized, clear, appropriately detailed. No emdashes or endashes.
Structure
<type>: <Capitalized summary: what and why, not how>
- Bullet points for notable changes (when the summary alone isn't enough)
- Each bullet is a complete thought, capitalized
- Focus on what changed and why, not implementation detailsType Prefixes
| Prefix | When |
feat | New feature or capability |
fix | Bug fix |
test | Test additions or changes |
refactor | Code restructuring, no behavior change |
style | Formatting, linting, no logic change |
docs | Documentation only |
infra | Docker, CI, build, deployment config |
perf | Performance improvement |
chore | Dependency updates, cleanup |
Examples
Good — right level of detail:
feat: Add HNSW partial indexes for dimension-aware vector search
- Add dimensions column to chunks and agent_memories with backfill
- Create partial HNSW indexes for 384, 768, 1024, 1536 dimensions
- Update knowledge_store and memory_repo with dimension-cast SQL
- 16 integration tests including EXPLAIN plan verificationfix: Nested markdown fences fail to parse in fact extraction
Strip all fence markers with re.sub instead of single regex match.test: Memory SSE callbacks and hook execution testsBad — avoid these patterns:
feat: add hnsw partial indexes for dimension-aware vector search(Lowercase after prefix — should be capitalized)
feat: Add HNSW partial indexes for dimension-aware vector search
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>(Co-author line — never)
(Also avoid: missing type prefix, vague summaries, run-on paragraphs. Use bullets.)
Commit Workflow
Step 1: Review changes
Run in parallel:
git status(never use-uall)git diff HEAD(full picture: staged + unstaged)git log --oneline -5(recent history for style reference)
Step 2: Check for excluded files
Check the diff against Core Rule 3's exclusion list. Never stage matches. Warn the user if they explicitly ask to commit them.
Step 3: Present diff and wait
Show the user what will be committed. Draft the commit message. Wait for LGTM — do not commit until the user confirms.
Step 4: Commit
Stage specific files (never git add -A or git add .). Use HEREDOC for the message:
git commit -m "$(cat <<'EOF'
feat: Summary here
- Detail one
- Detail two
EOF
)"Step 5: Verify
Run git status after commit to confirm success.
Push Rules
- Never push without explicit user request
- Never force-push to main/master without warning the user about the consequences
- If push is rejected (remote has new commits), pull with rebase first:
git pull --rebase
Branch Rules
- Trunk-based development on
main: commit directly to main, do not auto-create branches (overrides the harness branch-first default) - Never use
git rebase -i(interactive — requires terminal input) - Never use destructive commands (
reset --hard,clean -f,checkout .) without explicit user request - If a pre-commit hook fails, fix the issue and create a new commit — never amend blindly
PR Creation
When creating pull requests via gh pr create:
- Title: under 70 characters, capitalized, no type prefix
- Body:
## Summarywith bullet points +## Test Planwith checklist - No co-author lines or AI-attribution footers in the body (overrides the harness default "🤖 Generated with Claude Code" footer)
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.

