builder-workflow
npx skills add https://github.com/darraghh1/my-claude-setup --skill builder-workflow
Agent 安装分布
Skill 文档
Builder Phase Workflow
You have been assigned a full phase to implement. Your spawn prompt contains the phase file path and plan folder. This skill teaches you how to handle the entire phase end-to-end.
Why This Workflow Exists
The user experienced builders that guessed at patterns, skipped tests, and produced inconsistent code. Each step below prevents a specific failure:
| Step | Prevents |
|---|---|
| Read phase completely | Missing requirements, user has to re-explain |
| Pre-flight test check | Cascading failures from broken previous phases |
| Find reference file | Guessing at patterns, code doesn’t match codebase |
| Invoke domain skill | Missing project-specific conventions |
| TDD first (Step 0) | Untested code, bugs discovered in production |
Step 1: Read the Phase
Read the phase file from your spawn prompt. Extract:
- Prerequisites & Clarifications â check for unanswered questions first
- Requirements (Functional + Technical)
- Implementation Steps (Step 0 through Step N)
- Acceptance Criteria (your success metrics)
If ANY prerequisite question is unanswered:
SendMessage({
type: "message",
recipient: "team-lead",
content: "Phase has unanswered prerequisite questions. Cannot proceed.",
summary: "Blocked: unanswered prerequisites"
})
Then STOP and wait for instructions.
Step 2: Pre-Flight Test Check
Skip for Phase 01 â no previous phases exist.
For Phase 02+:
pnpm test
- Exit code 0 â proceed to Step 3
- Exit code â 0 â check if failures are from current phase’s TDD (expected) or previous phases
- Previous phase failures: fix them first, re-run to confirm green, then proceed
- Current phase TDD failures: expected, proceed
IMPORTANT â “pre-existing” is not an excuse. After a context compact, you may not know whether failures existed before your work started. It doesn’t matter. You own every failure present when you report completion. If tests or typecheck are failing, fix them â regardless of who caused them.
Step 3: Invoke Domain Skill and Find Reference
Your spawn prompt includes a Skill: field (extracted from the phase frontmatter by the orchestrator). If present, use that value. Otherwise, check the phase frontmatter for a skill field, or determine from content:
| Phase Focus | Skill | Reference Glob |
|---|---|---|
| Database schema, migrations, RLS | postgres-expert |
supabase/migrations/*.sql |
| Server actions, services, API | server-action-builder |
app/home/[account]/**/*server-actions*.ts |
| React forms with validation | react-form-builder |
app/home/[account]/**/_components/*.tsx |
| E2E tests | playwright-e2e |
e2e/tests/**/*.spec.ts |
| React components, pages | vercel-react-best-practices |
app/home/[account]/**/_components/*.tsx |
| UI/UX | web-design-guidelines |
app/home/[account]/**/_components/*.tsx |
| Service layer | service-builder |
app/home/[account]/**/*service*.ts |
- Glob the reference pattern â read ONE file
- Extract 3-5 key patterns: function signatures, imports, naming, error handling, post-operation hooks
- Invoke the domain skill:
Skill({ skill: "skill-name" })
The reference file is your ground truth. Your code must structurally match it.
Step 4: Create Internal Task List
Create tasks via TaskCreate for each implementation step. This is not optional â tasks survive context compacts and are your only recovery mechanism if context is compacted mid-phase. Without them, you must restart the entire phase from scratch.
Prefix all task subjects with [Step] to distinguish from the orchestrator’s phase-level tasks in the shared team task list. Mark each task in_progress before starting and completed when done.
Task descriptions must be self-contained:
- File paths to create/modify
- Function signatures, key parameters
- Which services/actions to call
- Acceptance criteria for that step
Bad: "Create the dropdown component"
Good: "[Step] Create change-role-dropdown.tsx at app/home/[account]/roles/_components/. Props: { membershipId, accountSlug }. Fetch roles via listRolesAction, filter by hierarchy_level. Use @/components/ui Select, Badge."
Always start with Step 0: TDD.
Step 5: Implement
- Step 0 (TDD) first â write failing tests before implementation code
- Remaining steps sequentially â follow the phase document exactly
- After each step: run
pnpm test, fix failures before moving on - Mark each task completed via
TaskUpdateas you finish it
Scope boundary â implement ONLY what’s in the phase:
- Do NOT add improvements not specified in the phase
- Do NOT refactor adjacent code
- Do NOT create documentation files
Key project patterns:
- Server actions: validate with Zod, verify auth before processing
- Services:
createXxxService(client)factory wrapping private class,import 'server-only' - Imports: path aliases, ordering: React > third-party > internal > local
- After mutations:
revalidatePath('/home/[account]/...')
IMPORTANT: Before using the Write tool on any existing file, you MUST Read it first or the write will silently fail. Prefer Edit for modifying existing files.
Step 6: Final Verification
Run the full verification before reporting:
pnpm test
pnpm run typecheck
Both must pass. Fix any failures before proceeding.
Conditional Testing by Phase Type
The phase’s skill: frontmatter field determines which additional tests to run:
| Phase Skill | Extra Test | Command |
|---|---|---|
react-form-builder |
E2E tests | pnpm test:e2e (scoped) |
vercel-react-best-practices |
E2E tests | pnpm test:e2e (scoped) |
web-design-guidelines |
E2E tests | pnpm test:e2e (scoped) |
playwright-e2e |
E2E tests | pnpm test:e2e (scoped) |
postgres-expert |
DB tests | pnpm test:db |
server-action-builder |
Unit tests sufficient | â |
service-builder |
Unit tests sufficient | â |
E2E test scoping:
- Extract keywords from the phase title/slug (e.g.,
notes,billing,auth) - Glob for
e2e/**/*{keyword}*.spec.ts - If matches found:
pnpm test:e2e -- [matched spec files] - If no matches:
pnpm test:e2e(full suite)
Graceful skip: If a test command doesn’t exist (exit code from missing script), skip it and note in your completion report. Projects without E2E or DB tests should not fail verification.
All extra tests must pass before reporting completion.
Scope boundary: Your job ends here. Do NOT run /code-review â an independent validator teammate will review your work after you report. This separation ensures blind spots are caught by a fresh set of eyes.
Step 7: Report Completion
Send completion message to the orchestrator:
SendMessage({
type: "message",
recipient: "team-lead",
content: "Phase [NN] implementation complete â ready for review.\n\nFiles created/modified:\n- [list]\n\nTests: passing\nTypecheck: passing\n\nAcceptance criteria met:\n- [list key criteria]",
summary: "Phase NN implemented â ready for review"
})
Then go idle. The orchestrator will either assign the next phase or send a shutdown request.
Resuming After Context Compact
If your context was compacted mid-phase:
TaskListâ find thein_progressor firstpendingtaskTaskGeton that task â read the self-contained description- Continue from that task â don’t restart the phase
- The task list is your source of truth, not your memory
Troubleshooting
Tests fail but code looks correct
Cause: Reference patterns may have changed since the phase was written. Fix: Re-read the reference file (Step 3). If the phase’s code blocks differ from the current reference, follow the reference â it’s the ground truth.
Domain skill not found
Cause: Skill name in phase frontmatter doesn’t match available skills. Fix: Check the table in Step 3 for the correct skill name. If the phase focus doesn’t match any skill, skip skill invocation and rely on the reference file.