skills/checkout/SKILL.md
Analyze Git changes and create a new branch with an appropriate name.
npx skillsauth add thkt/dotclaude checkoutInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
$ARGUMENTS may contain context or a ticket number. Trim whitespace; if empty, analyze the Git changes alone. If non-empty, treat it as a hint for the branch name scope or ticket ID.
git status and git diff in parallel to read the changes$ARGUMENTSAskUserQuestion and let the user pick onegit checkout -b <selected name>Determine the type from the changes and assemble the branch name in this format. Each type's trigger is in the table below.
<type>/<scope>-<description>
<type>/<ticket>-<description>
| Prefix | Purpose | Trigger | | --------- | -------------------- | --------------------- | | feature/ | New functionality | New files, components | | fix/ | Bug fixes | Error corrections | | refactor/ | Code improvements | Restructuring | | docs/ | Documentation | .md files, README | | test/ | Test additions/fixes | Test files | | chore/ | Maintenance | Dependencies, config | | perf/ | Performance | Optimization, caching |
$ARGUMENTS has a ticket ID, include it at the <ticket> position; do not include dates| Error | Action | | ----------------- | --------------------------- | | No changes | Report there are no changes | | Branch exists | Suggest an alternative name | | No git repository | Report it is not a git repo |
Report the created branch name on a single line.
tools
Delegate implementation to codex (coder) via the herdr-agentchat plugin and drive a two-pane conversation to completion.
development
Extract recurring patterns from past closed PRs/issues and the research findings in workspace/research/, verify them against the latest code, and propose them to docs/wiki/ via PR.
development
Create Decision Records (DR) in MADR v4 format with auto-numbering.
development
Detect flaky tests by shaking them — repeated runs under varied order, parallelism, and seed — plus a static smell scan that flags latent flakiness in tests that currently pass. Classify each target as confirmed-flaky, latent-flaky, or stable and fix the root cause without weakening the test. Do NOT use to fix a confirmed single bug (use /fix) or for static-only code review (use /audit).