Git workflows, branching strategies, and version control automation skills
303 skills found
GitHub CLI operations via `gh` command. Use when working with GitHub repositories, pull requests, issues, code search, releases, or any GitHub API operation. This skill replaces the GitHub MCP server with direct CLI calls. Triggers on: GitHub, PR, pull request, issue, repo, branch, release, tag, commit, fork, merge, review, gh.
Review all currently unreviewed open pull requests, newest first, using the om-auto-review-pr skill and respecting in-progress claim locks.
Close the tracker issues that recently merged PRs authoritatively fixed — via `fixes`/`closes`/`resolves` keywords or `closingIssuesReferences` — and post informational comments on issues whose PRs were closed without merging or merged into a non-base branch. Use for post-merge housekeeping and release prep. Respects claim locks and never acts on bare `#N` mentions.
Claude Security: scan the codebase (the whole repository or a scoped part of it), scan changes (this branch's or a pull request's diff, or one commit), or suggest patches (findings turned into targeted patch files, each verified by a panel of agents, that you apply when you choose). Use when the user asks to scan, audit or check code with Claude Security, to scan their changes with Claude Security, or to fix or patch Claude Security findings.
Use when working in a checked-out PR stack, handling dependent PRs or branch layers, or planning to split work into stacked PRs.
Use when asked to tag or cut a patch, minor, or major release.
Use when asked to merge all open PRs or land a specified set of PRs together.
Patterns for invoking the GitHub CLI (gh) from agents. Covers structured output, pagination, repo targeting, search vs list, gh api fallback.
Turn a PR into tracked follow-up work — paste a PR or PR-comment link to extract the actionable ask and open a follow-up issue assigned to the @-mention or PR author; for a PR adding a design doc, it opens the missing `Implement:` tracking issue instead. Use for "make a follow-up issue", "create an issue for this", or a pasted PR/comment link with that intent.
Read-only triage gate for an autofix chain. Decides whether a tracker issue is a real, still-unfixed defect on the current branch. Stops the chain cleanly with NO_ACTION_NEEDED when the issue is already fixed, already in progress by someone else, already covered by an open PR, or not actually a bug.
One-time pipeline configurator. Inspects the repo (default branch, validation scripts, labels), asks a few questions, writes .ai/agentic.config.json — the file every other skill reads — installs the tracker descriptor, and generates missing project docs (SDLC.md, CODE_REVIEW.md, BACKWARD_COMPATIBILITY.md, AGENTS.md starter). Re-run when the toolchain or label taxonomy changes. Verifies cross-skill coverage and prints the install command for missing skills.
Mid-session save point: create a descriptive git commit and a brief handoff note, then keep working. Use before a risky change or refactor, when switching tasks, or to bank progress without ending the session. Triggers on: /checkpoint, "checkpoint", "save progress", "commit and handoff", "save state", "pause here", "before a risky change". For the full end-of-session ritual with learning extraction, use /wrap-up instead.
