en un clic
outcome-translator
">"
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Menu
">"
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
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 | outcome-translator |
| name | outcome-translator |
| type | flexible |
| version | 1.0.0 |
| created | 20/03/2026 |
| modified | 20/03/2026 |
| status | active |
| triggers | ["finished","ready","launch it","make it work","production ready","ready for clients","ship it","done","go live","just make it work","it's ready","we're done","release it"] |
| description | > |
Purpose: Non-technical founders speak in outcomes. Engineers speak in tasks. This skill bridges the gap — translating every outcome phrase into a provable engineering plan.
Locale: en-AU — colour, behaviour, optimisation, organised, licence (noun).
Invoke this skill BEFORE any action when the user's message contains:
Never assume the claim is true. Always translate and verify first.
Always produce the full structured output below. Do not skip any section.
OUTCOME TRANSLATION
═══════════════════════════════════════════════════════════════
Outcome: [Exact phrase the user said]
Interpreted As: [Engineering definition — be specific]
DEFINITION OF DONE
───────────────────────────────────────────────────────────────
□ [Criterion 1 — measurable, specific]
□ [Criterion 2]
□ [Criterion N]
CURRENT STATE AUDIT
───────────────────────────────────────────────────────────────
Proven:
✓ [Confirmed working item — state the evidence]
✓ [Another confirmed item]
Unknown:
? [Item that cannot be verified without action — state what action is needed]
? [Another unknown]
Missing:
✗ [Item confirmed absent or broken — state what is missing]
✗ [Another missing item]
GATED PLAN
───────────────────────────────────────────────────────────────
Phase 1: [Phase Title]
Priority: [CRITICAL / HIGH / MEDIUM]
Steps:
1. [Specific action]
2. [Specific action]
Gate: [Command or artifact that proves this phase is complete]
Rollback: [How to undo if this phase fails]
Phase 2: [Phase Title]
Priority: [CRITICAL / HIGH / MEDIUM]
Steps:
1. [Specific action]
Gate: [Proof of completion]
Rollback: [Undo path]
[Repeat for all phases]
PROOF REQUIRED
───────────────────────────────────────────────────────────────
Before claiming completion, the following artifacts must exist:
□ [Artifact 1 — e.g. "curl -I output showing HTTP 200 for production URL"]
□ [Artifact 2 — e.g. "screenshot of successful login with production credentials"]
□ [Artifact 3 — e.g. "provider dashboard showing live transaction"]
□ [Artifact N]
COMPLETION GATE
───────────────────────────────────────────────────────────────
Status: [NOT COMPLETE / COMPLETE]
Blocking: [List every criterion that is Unknown or Missing]
NEXT ACTION
───────────────────────────────────────────────────────────────
[Single most important action to take RIGHT NOW]
[Exact command or step — no ambiguity]
═══════════════════════════════════════════════════════════════
Use these definitions when interpreting outcome language. Adapt to the project's actual stack.
Requires ALL of the following:
Same as "Finished" plus:
Same as "Production Ready" plus:
Requires:
Same as "Production Ready" plus:
Proven = you have evidence. Name the evidence. Examples:
Unknown = you could verify it but haven't yet. State exactly what action would verify it. Examples:
Missing = confirmed absent. State what is missing. Examples:
This skill enforces a hard prohibition on false completion claims.
Do NOT output any of these phrases unless ALL criteria are Proven:
If ANY criterion is Unknown or Missing, output:
STATUS: NOT COMPLETE
[N] criteria require action before this can be claimed as complete.
Next required action: [specific step]
.claude/rules/human-outcome-translation.md — always-on trigger.skills/custom/blueprint-first/SKILL.md before code generation.skills/custom/verify/SKILL.md (or equivalent) after executionUser: "We're production ready, launch it"
Skill invoked: outcome-translator
Output:
OUTCOME TRANSLATION
═══════════════════════════════════════════════════════════════
Outcome: "We're production ready, launch it"
Interpreted As: Claim that all production criteria are met; instruction to deploy to production
DEFINITION OF DONE
───────────────────────────────────────────────────────────────
□ Production URL responds HTTP 200
□ Auth flow verified (register → login → dashboard)
□ Backend health check passing
□ SSL certificate valid
□ No dev environment variables in production
□ CI/CD pipeline green
□ Monitoring active
□ Rollback path documented
CURRENT STATE AUDIT
───────────────────────────────────────────────────────────────
Proven:
✓ CI pipeline green — confirmed by last run log
Unknown:
? Production URL — requires: curl -I https://your-production-url.com
? Auth flow — requires: manual test with production credentials
? SSL certificate — requires: ssl-checker.io or browser inspection
? Monitoring — requires: confirm Sentry/equivalent is configured
Missing:
✗ Rollback plan — no documented rollback procedure found
✗ Production env vars — JWT_SECRET_KEY still at default value
GATED PLAN
───────────────────────────────────────────────────────────────
Phase 1: Resolve Missing Items [CRITICAL]
Steps:
1. Rotate JWT_SECRET_KEY in production environment
2. Document rollback procedure in runbook
Gate: grep JWT_SECRET_KEY .env.production confirms non-default value
Phase 2: Verify Unknown Items [CRITICAL]
Steps:
1. curl -I https://your-production-url.com
2. Test auth flow manually
3. Confirm SSL validity
4. Confirm monitoring is receiving events
Gate: All four return expected results
Phase 3: Deploy [HIGH]
Steps:
1. Trigger production deployment via CI/CD
2. Verify post-deploy health check
Gate: Health endpoint returns 200 post-deploy
Rollback: git revert + re-deploy or platform rollback
PROOF REQUIRED
───────────────────────────────────────────────────────────────
□ curl -I output showing HTTP 200
□ Screenshot of successful login on production
□ SSL validity confirmation
□ Monitoring dashboard showing active tracking
COMPLETION GATE
───────────────────────────────────────────────────────────────
Status: NOT COMPLETE
Blocking: 2 Missing items, 4 Unknown items must be resolved
NEXT ACTION
───────────────────────────────────────────────────────────────
Rotate JWT_SECRET_KEY in production environment — this is a security blocker.
Command: Set JWT_SECRET_KEY to a new 64-character random string in your hosting platform's env config.
═══════════════════════════════════════════════════════════════