メニュー
">"
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Apply this skill for Unite-Hub Supabase migrations, PostgREST/Data API visibility, founder-scoped Playwright journeys, or errors such as PGRST205, access=denied, stale Supabase linked refs, or migration history drift. Prevents repeating the SQL/cache/auth loop by enforcing the exact verification sequence for core journeys.
The compass for Unite-Hub's road to /shipit. Defines the single NorthStar (a real, comprehensive, working founder CRM in production, every section GREEN), the binding definition of GREEN, and the No-Invaders Manifest that keeps the build honest and surgical. Consult BEFORE deciding what to build/skip/finish — it resolves "200 ≠ real" temptations and scope-creep pressure. P1, auto-loaded.
Apply this skill WHEN scaffolding a new cron "pull" route that syncs external/derived data into Supabase on a schedule (Vercel cron). Encodes the Unite-Hub cron invariants: CRON_SECRET auth, FOUNDER_USER_ID actor, overlap safety, idempotent upsert, last-sync timestamp, and failure surfacing. Generic `cron-scheduler` covers scheduling; this covers the PULL handler body. P3.
Apply this skill WHEN verifying that a route, page, or integration serves REAL data and not silent mock/placeholder data. Detects the "false-green" failure mode: an endpoint returns 200 (or a page renders) while the underlying data is fabricated because a provider is unconnected. Trigger WHENEVER classifying a section's readiness, reviewing integration wrappers, or before marking anything GREEN. P2 — load on audit/verify tasks.
Manifest-first context isolation — each subagent receives only its scope, never the full codebase
Apply this skill for ANY decision with non-obvious tradeoffs: architectural choices, debugging without a clear root cause, performance strategies, security decisions, feature design with competing constraints, refactoring scope decisions. Forces multi-perspective analysis before committing to a solution. P1 auto-load — always active on complex reasoning tasks.
| id | finished-audit |
| name | finished-audit |
| type | Capability Uplift |
| version | 1.0.0 |
| created | 20/03/2026 |
| modified | 20/03/2026 |
| status | active |
| triggers | ["are we done","is this finished","audit completion","verify done","check if complete","is it ready","can we ship","can we close this"] |
| description | > |
Purpose: Systematically verify that "finished" is actually true. No vague summaries. No optimistic assumptions. Evidence only.
Use this skill when:
The following phrases indicate a false completion claim. Never output them:
| Banned Phrase | Reason |
|---|---|
| "Done!" | No evidence |
| "That's complete." | No evidence |
| "Everything is working." | No evidence |
| "You're production ready." | No evidence |
| "Finished." | No evidence |
| "It's ready." | Subjective |
| "Should be working." | Unverified |
| "Looks good." | Subjective |
| "Tests are passing." | No output shown |
definition-of-done-builder or provided)If no DoD exists: activate definition-of-done-builder first.
If DoD exists: use it as the audit checklist.
For each criterion in the DoD:
| Status | Meaning | Accepted as proof? |
|---|---|---|
| PROVEN | Evidence exists, verified | Yes |
| CLAIMED | Evidence claimed but not shown | No |
| UNKNOWN | Not verified either way | No |
| MISSING | Confirmed absent or broken | No |
Completion % = (PROVEN count / total criteria count) × 100
If ALL criteria = PROVEN:
→ Output: COMPLETION APPROVED
If ANY criterion = UNKNOWN, CLAIMED, or MISSING:
→ Output: NOT COMPLETE
→ List every blocking criterion
→ Specify exact next action per blocker
FINISHED AUDIT
═══════════════════════════════════════════════════
Task: [task description]
Audit Date: [DD/MM/YYYY]
Completion: [N]% ([proven]/[total] criteria PROVEN)
STATUS: NOT COMPLETE
BLOCKING CRITERIA
─────────────────
[criterion] — Status: UNKNOWN
Required: [exact action to verify]
[criterion] — Status: MISSING
Required: [exact remediation]
[criterion] — Status: CLAIMED (evidence not shown)
Required: [show exact output/screenshot]
NEXT ACTION
─────────────
[Single most important thing to do right now]
═══════════════════════════════════════════════════
FINISHED AUDIT
═══════════════════════════════════════════════════
Task: [task description]
Audit Date: [DD/MM/YYYY]
Completion: 100% ([N]/[N] criteria PROVEN)
STATUS: COMPLETION APPROVED
PROOF ARTIFACTS
─────────────────
[criterion] — Proof: [artifact description + path/output]
[criterion] — Proof: [artifact]
...
APPROVED FOR: [merge/deploy/close/ship — as appropriate]
═══════════════════════════════════════════════════
Before accepting a PROVEN status:
| Failure | Recovery |
|---|---|
| No DoD exists | Activate definition-of-done-builder first |
| Proof is a screenshot of wrong state | Request updated screenshot |
| Proof is from a different environment | Request production environment proof |
| Developer argues criterion is "not needed" | Escalate to PM Agent — DoD is non-negotiable |
Input: "I've shipped the auth feature, it's done."
Audit output: NOT COMPLETE — 6/9 criteria PROVEN. 3 criteria UNKNOWN (no production URL proof, no rate limiting proof, JWT secret check missing).
Input: "The feature is complete." Output: "Great! Looks like it's done." — REJECTED (no audit performed)