aboutsummaryrefslogtreecommitdiff
path: root/start-work
Commit message (Collapse)AuthorAgeFilesLines
* refactor(skills): convert 16 user-invoked skills to commandsCraig Jennings2026-05-061-269/+0
| | | | | | | | I converted 16 user-invoked skills to commands. Skills cost ~150-300 tokens each per session for descriptions the model uses to auto-route. Commands cost nothing until you type the slash. These 16 are workflows I always trigger deliberately. The auto-routing wasn't earning its keep. This reclaims ~4-5k tokens per session. Nine skills stayed where auto-routing genuinely helps: debug, root-cause-trace, five-whys, add-tests, frontend-design, humanizer, playwright-js, playwright-py, and pairwise-tests. Pairwise-tests stays a skill because its helper files don't fit a single-file command shape. For arch-decide, I preserved the upstream MIT LICENSE alongside the command at .claude/commands/arch-decide.LICENSE so attribution stays intact.
* refactor: scope start-work refactor audit to every touched fileCraig Jennings2026-04-231-13/+17
| | | | The old "refactor pass" framed the step as a polish over new code. Expanded to "refactor audit" — walks each touched file against the checklist, top to bottom, and every finding lands somewhere: fixed on this branch or filed as a ticket. Drops "skip" as a first-class disposition. Tightens Phase 6 gate 3 to require filed ticket IDs, not just surfaced intent.
* feat(skills): add start-workCraig Jennings2026-04-221-0/+265
A workflow for picking up a specific task (Linear ticket, GitHub issue, todo.org heading, or a described scope) and carrying it through to handoff. Seven phases, three user-approval gates. The phases in order: - Claim: mark in-progress, assign, label, verify project. - Justify (gate 1): benefits, costs, impact, urgency, effort, alternatives, ticket quality. - Approach (gate 2): root cause, risk, test strategy, migration, flag, commit decomposition, branch name. - Implement (TDD): red, green, edge cases, and a refactor pass with a nine-point language-agnostic checklist. - Verify: end-to-end or scripted manual test in the local environment. Playwright for web projects, step-by-step walkthrough for everything else. Never production. - Ready to commit (gate 3): report, deviations from the approach, any follow-ups spotted. - Hand off to the Review-and-Publish flow in commits.md. Cross-referenced from testing.md, commits.md, subagents.md, review-code, brainstorm, arch-design, arch-decide, debug, pairwise-tests, playwright-js, and playwright-py.