agentleFS
dprakash2101dprakash2101/dotnet-production-agent-skills/skills/git-workflow/SKILL.md

git-workflow

Skill4 starsChanged 51 days agoMITView on GitHub

Perform safe Git branch, stage, commit, and push operations for engineering work. Use only when the user requests Git operations or they are an explicit required step; never infer permission to commit or push.

  • Commits and pushes

188 other projects use a version of this.

Adopted by

Most recently taken up by

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 AzureSkill

    squad-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

  • harrissohail6Skill

    ci-cd-pipelines

    CI/CD pipeline design and implementation. Auto-activates when discussing deployment, automation, or pipelines.

    Also in 6 projects that use this

  • Microsoft AzureSkill

    architectural-proposals

    How to write comprehensive architectural proposals that drive alignment before code is written

    Also in 4 projects that use this

  • GitHubSkill

    e2e-template-testing

    End-to-end validation of coordinator and agent template changes

    Also in 3 projects that use this

  • GitHubSkill

    notification-routing

    Route agent notifications to specific channels by type — prevent alert fatigue from single-channel flooding

    Also in 3 projects that use this

  • frostneySkill

    native-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

  • +5 more from Azure
  • +1 more from github

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 165 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 2

    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
  1. Distinctive:

    Follow the repository's branch and commit naming rules.

    line 16
  2. Very specific:

    Never add Co-authored-by: trailers (case-insensitive), co-author metadata, or equivalent attribution to commits or pull requests.

    line 20
  3. Distinctive:

    Never append AI/agent signatures, credits, or footers such as "Generated with Copilot" or "Assisted by Claude" to commit messages or pull …

    line 21
  4. Very specific:

    Do not supply attribution through git commit --trailer, commit-message templates, API fields, or another indirect mechanism.

    line 22
  5. Distinctive:

    Before creating a commit or pull request, inspect the complete proposed message, including its body and trailers, and remove any …

    line 23
  6. Distinctive:

    If a hook, tool, or host adds forbidden attribution, stop before publishing and report the blocker.

    line 24
  7. Distinctive:

    Before committing, confirm required validation and scan the intended changes for secrets/artifacts.

    line 26
  8. Distinctive:

    Do not run a final status merely for ceremony.

    line 30
  9. Distinctive:

    When the exact paths and diff were reviewed, validation passed, the commit message is known, and commit plus push are both authorized, use …

    line 36
  10. Distinctive:

    Never force-push unless explicitly requested and the target/ref consequences are understood.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 165 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Fast, safe Git workflow

Apply safe-terminal before execution and on command failure. Keep the working directory in the intended project, verify the repository root when context is not established, and never recover by moving into Git's installation folder. Executable lookup does not select the repository. Split diagnostic recovery from the mutation sequence below; resume only when the cause is corrected and repository context is verified.

Minimize terminal calls and token-heavy output without weakening review. Batch compatible Git commands into the fewest practical invocations, and reuse branch, status, diff, validation, and remote facts already established in the current task when no intervening operation could have changed them. Do not issue one tool call per Git command by default.

For a fresh preflight, prefer one combined inspection such as git status --short --branch instead of separate status and branch commands. Inspect only the relevant diff; do not repeat a full diff review that was just completed.

Preserve unrelated user changes and stage explicit intended paths or hunks only. After staging, use one focused staged check that detects whitespace errors and confirms the staged scope, such as git diff --cached --check --stat. Expand to the full staged diff only when it has not already been reviewed or the staged scope is surprising.

Follow the repository's branch and commit naming rules. If the team requires a Jira ID, reuse one from the current branch or user input and never invent one. Ask only if the requested operation requires an unavailable identifier.

Strict authorship policy

  • Never add Co-authored-by: trailers (case-insensitive), co-author metadata, or equivalent attribution to commits or pull requests. This applies to every coding agent, including GitHub Copilot, Codex, Claude, and Cursor.
  • Never append AI/agent signatures, credits, or footers such as "Generated with Copilot" or "Assisted by Claude" to commit messages or pull request titles/descriptions.
  • Do not supply attribution through git commit --trailer, commit-message templates, API fields, or another indirect mechanism. Do not change the configured Git author/committer identity or use --author to credit an agent.
  • Before creating a commit or pull request, inspect the complete proposed message, including its body and trailers, and remove any automatically suggested attribution. Before pushing, inspect the new commits' complete messages with git log <base>..HEAD --format=full and verify the same policy.
  • If a hook, tool, or host adds forbidden attribution, stop before publishing and report the blocker. Do not bypass hooks, change tool configuration, amend existing commits, or rewrite published history without explicit authorization.

Before committing, confirm required validation and scan the intended changes for secrets/artifacts. Do not include unrelated changes. Do not change Git identity, credentials, credential helpers, or authentication configuration.

When the user authorizes both commit and push, treat them as one continuous workflow: do not pause between them or rerun status/branch checks unless the commit result is ambiguous, hooks changed the worktree, or another actor may have changed repository state. Push the committed current branch with git push -u <authorized-remote> HEAD; this avoids another branch-name lookup. Inspect remotes only when the destination is not already known, and obtain any host-required approval before external transfer.

Do not run a final status merely for ceremony. Commit and push output normally provide sufficient confirmation; recheck only to investigate an error, hook mutation, partial operation, or when the user explicitly requests a clean-tree report.

Group already-authorized sequential operations in one terminal invocation using &&, so execution stops at the first failure and later mutations do not run. Do not add banners, echo separators, or duplicate inspection commands that inflate output. Keep separate calls only where the result of one step must be reviewed before authorizing or deciding the next step.

Efficient default

When the exact paths and diff were reviewed, validation passed, the commit message is known, and commit plus push are both authorized, use at most two terminal invocations:

  1. git status --short --branch for the fresh preflight.
  2. A short-circuiting sequence that stages only the intended paths, checks the staged scope, commits, and pushes HEAD, for example: git add -- <paths> && git diff --cached --check --stat && git commit -m "<message>" && git push -u <authorized-remote> HEAD.

If the preflight facts are already known from the current task, skip the first invocation and run only the combined mutation sequence. For a commit without push, omit the final push segment. For read-only review, combine compatible output in one invocation or use multi-purpose forms such as git status --short --branch and git diff --check --stat instead of separate branch, status, whitespace, and summary calls.

Do not use the combined mutation sequence when staging needs hunk selection, changes have not been reviewed, validation is incomplete, the remote is unknown, push was not authorized, or the environment requires separate approvals. In those cases, split only the steps needed to resolve that uncertainty.

Never force-push unless explicitly requested and the target/ref consequences are understood. Pushing, rebasing, resetting, deleting branches/tags, and other remote or destructive actions require clear scope and authorization.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.