원클릭으로
verification-first
Hard verification gate — no task is complete without proof it works (Next.js/Supabase stack)
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Hard verification gate — no task is complete without proof it works (Next.js/Supabase stack)
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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.
| name | verification-first |
| category | verification |
| version | 2.0.0 |
| description | Hard verification gate — no task is complete without proof it works (Next.js/Supabase stack) |
| author | Unite Group (ported from NodeJS-Starter-V1) |
| priority | 1 |
| auto_load | true |
| triggers | ["any_code_change","post-implementation","pre-commit"] |
| context | fork |
A task is NOT complete until verification passes. "Almost working" = broken.
No self-attestation. No assumed success. Evidence required.
Every code change MUST be verified before moving on:
When something fails:
Before attempting any fix:
The agent that wrote the code MUST NOT verify its own work.
Route to [[verification]] agent. No exceptions.
# TypeScript type check
pnpm run type-check
# Lint
pnpm run lint
# Unit tests (Vitest)
pnpm vitest run
# Full pipeline
pnpm run type-check && pnpm run lint && pnpm vitest run
# Health check (comprehensive)
.\scripts\health-check.ps1
Note:
turboCLI is NOT available globally — usepnpm runscripts directly.
Trigger: After every code generation
pnpm build)Trigger: Before git commit
Trigger: Feature additions, migrations
Trigger: Before any production deploy
All verification reports MUST use this format:
## Verification: [Task Description]
### Status: [PASS | FAIL | BLOCKED]
### Tier: [A | B | C | D]
### Results:
- type-check: [PASS/FAIL] — [error if failed]
- lint: [PASS/FAIL] — [error if failed]
- unit-tests: [PASS/FAIL] — [X/Y passed]
- build: [PASS/FAIL] — [error if failed]
- manual: [PASS/FAIL] — [what was checked]
### Evidence:
[Actual command output, test results, or screenshot path]
### Next Steps:
[If PASS → what's next]
[If FAIL → root cause + proposed fix]
Verification is automatically enforced by:
post-code.hook.md — Runs Tier A after code generationpre-commit.hook.md — Runs Tier B before git commitpre-deploy.hook.md — Runs Tier D before deploymentFor any user-facing output, also verify:
When verification fails:
Stacking fixes creates the same problem as never testing: you don't know which change broke what.