A free retention check for one published short video: paste your average percentage viewed and get a PASS / REWORK / REBUILD verdict with the threshold shown, plus the single biggest retention leak named and one concrete fix.
Catches cascade failures that partial checks miss — pre-check names the risk before editing, post-check demands evidence values after, then auto-repairs in a loop while rereading the entire file every cycle until zero errors remain.
A kickoff protocol (agent skill) for multi-step tasks. Before writing any code, the agent must: run a spec interview, batch every human-authorization step into one checklist, build a self-verification loop (log sink + verify script + dry-run) *before* the feature itself, and build comparable variants instead of blocking on third-party decisions.
영상 첫 대사·첫 장면만 붙여넣으면, 촬영 전에 "3초 안에 왜 이탈하는지"를 결함 등급별로 짚고 바로 쓸 훅 2개를 다시 써줍니다. 실제 훅만 채점하며 없는 훅을 지어내지 않습니다.
앞두고 있는 결정을 붙여넣으면, "6개월 뒤 이미 실패했다"고 가정하고 실패 원인을 역설계해 위험 순위·조기경보 신호·사전 가드까지 지도로 만들어줍니다. 결정은 대신 내려주지 않습니다.
Turn video scripts into structured retention audits — map hook failures, desertion windows, and re-engagement fixes using attention psychology.
Forces AI agents to prove a task is actually done before declaring it complete. 4-phase gate: instruction reconciliation, evidence anchoring (values only readable from the actual output), self-scoring (A/B/C/D), and reverse witness check. Eliminates "done" declarations that aren't.
Paste PostgreSQL migration SQL, an ORM migration, or a PR diff. Get a PASS/REVISE/BLOCK review with statement-level lock and rewrite risks, safer DDL, zero-downtime rollout steps, rollback boundaries, monitoring SQL, and a paste-ready PR comment.
Upload pg_stat_activity and pg_locks CSVs. Get blocker chains, long transactions, a 15-minute action plan, and a reviewed cancel-versus-terminate record.