plugins/teamcraft-auto/skills/refresh-project-rules/SKILL.md
Re-evaluate what Claude needs to be told about this project as the codebase evolves. Some gotchas become obvious from the code (remove them). New gotchas emerge. Decisions change. Use when the user says 'refresh the rules', 'update Claude's context', 'are the rules still accurate', 'clean up claude rules', or after significant codebase changes.
npx skillsauth add codingthefuturewithai/claude-code-primitives teamcraft-auto:refresh-project-rulesInstall 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.
Re-evaluate .claude/rules/ and CLAUDE.md to ensure they still contain exactly what Claude needs — no more, no less. As the codebase evolves, some constraints become obvious from the code (and should be removed from rules), new constraints emerge (and should be added), and existing decisions may have changed.
1. Read the current rules. Read every file in .claude/rules/ and CLAUDE.md. Understand what each rule claims.
2. Check each rule against reality. For every rule, constraint, or decision documented:
package.json. "We require integration tests for all DB-touching code because of a Q1 incident" is NOT obvious from the code.3. Check for missing rules. Read /docs/decisions/ if it exists. Are there decisions with constraints that should be in .claude/rules/ but aren't? Look for recent additions to the codebase that introduce non-obvious patterns — things a new Claude session might get wrong.
Before promoting a constraint out of a decisions file, check that file's Teamcraft certification (see ../references/doc-provenance.md). If the decisions doc you're sourcing from is UNVERIFIED, say so when you propose the promotion — a constraint pulled from uncertified, possibly-inherited content shouldn't land in the always-loaded layer on uninformed approval. Don't block; surface it so the developer approves with eyes open. (This skill never stamps anything — it only reads the stamp to inform what it promotes.)
4. Check the project manifest. Is .teamcraft/project.md still accurate? Project name, repo identity.
Show the developer a clear diff of what you'd change:
The developer approves each change individually. Never auto-update — this is the developer's configuration.
For each change the developer approves, make the edit. Commit the updated files.
Confirm what changed in .claude/rules/ / CLAUDE.md and why. Then point the developer to the natural next step: /check-project-context to confirm Claude now reads the project correctly with the refreshed rules, or straight back to the work — /pick-next-issue or /build-issue <id>.
.claude/rules/ and CLAUDE.md — not about /docs/ or .teamcraft/work/. Those are managed by their own skills./docs/decisions/..claude/rules/ small. Every line is loaded every session. If it's growing, that's a signal to evaluate whether each rule truly needs to be always-loaded.development
Launch (or re-launch) the user's live, multi-project work board. The dashboard is a single HTML file copied to a stable user-side location at ~/.claude/teamcraft-board.html and opened in the user's default browser. It has two views via a header toggle — a drag-and-drop Kanban Board and a live Status tab with analytics (work by status, throughput, cycle time, aging, blocked chains, recomputed on every poll). Each project is added via a header dropdown; the dashboard polls each project's .teamcraft/work directly from the browser and updates in real time. Use when the user says 'show me the kanban', 'work board', 'open the board', 'board view', 'kanban view', 'live dashboard', 'visual dashboard', 'live status dashboard', 'status dashboard', 'project metrics', 'throughput/cycle-time view', 'HTML view of work items', 'drag-and-drop board', or asks to see/move/track work visually.
development
Run a retrospective — AI compiles evidence from recent work, facilitates human reflection, and captures process decisions back into living docs. Use when the user says 'run a retro', 'let's do a retrospective', 'run a retrospective on the last 2 weeks', 'let's reflect on how that feature went', or 'time for a retro'.
development
Report project status from work items and git history — either as a quick, interpreted read here in the session, or by pointing the developer to the live Status dashboard (the work board's Status tab). Covers work by status, what's in flight, cycle times, throughput, backlog priorities, aging alerts, blocked chains, and how commit activity lines up with the board. Use when the user says 'project status', 'show me the project status', 'what's the status of the work items', 'how are we doing', 'generate a status report', or asks for a status dashboard.
development
Plan a time-boxed iteration (sprint, cycle, milestone) from the backlog and the PRD/roadmap behind it — gather the goal, the window, and the team's real capacity, then select, sequence, and size a committed set of work items to fit. Writes an `iteration` label onto each chosen work item. Use when the user says 'plan a sprint', 'plan the next iteration', 'plan our cycle', 'sprint planning', 'iteration planning', 'plan the next two weeks', 'set up a milestone', 'what should we take on this sprint', 'plan from the PRD', or otherwise wants to commit a scoped, time-boxed batch of work rather than create issues one at a time. This is the planning layer between requirements and the build loop — distinct from create-issue (one item) and pick-next-issue (pick one to build now).