Skip to content

Buscar habilidades.../

Agent Skill Search Engine

Buscar

Buscar
Categorías
Ocupaciones

About

About
Privacy
Terms

© 2026 Skills Pool. Todos los derechos reservados.

Coherence Review | Skills Pool

Archivo del skill

Coherence Review

Review cross-specialist coherence. Verify API contracts, database schemas, auth middleware, and CI/CD alignment across all services. Triggers: coherence, integration review, cross-team review, consistency check, alignment review

knofler0 estrellas5 mar 2026

Ocupación
Categorías: Depuración

Contenido de la habilidad

Coherence Review Playbook

1. Gather Current State

Read state/STATE.md for active features and their status.
Identify all services/modules under review.
List the specialists who contributed (frontend, API, DB, security, DevOps).

2. Verify API Contracts

Compare frontend API calls against backend route definitions.
Check request/response shapes match on both sides.
Verify error codes and error response formats are consistent.
Flag any endpoint the frontend calls that the backend does not expose.

3. Verify Database Schema Alignment

Compare Mongoose/Prisma schemas against service query patterns.
Check that indexes support the queries being executed.
Verify migration files are up to date with schema definitions.

Skills relacionados

Instalación rápida

Coherence Review

npx skillvault add knofler/knofler-a-thousand-lamps-ai-skills-coherence-review-skill-md

Descargar Skill Abrir repositorio

Autor: knofler
estrellas: 0
Actualizado: 5 mar 2026
Ocupación

En esta página

01Coherence Review Playbook

4. Check Auth Middleware Alignment

Verify auth middleware is applied to all protected routes.
Confirm token format and claims match between auth service and consumers.
Check RBAC roles in middleware match the roles defined in security spec.

5. Verify CI/CD Coverage

Confirm every deployable service has a CI pipeline.
Check that test, lint, build, and deploy stages exist.
Verify environment variables are documented and present in CI config.

6. Identify Integration Gaps

List any mismatches found in steps 2-5.
Categorize each gap: breaking (will fail at runtime) vs drift (works but inconsistent).
Prioritize breaking gaps first.

7. Create Fix Tasks

For each gap, create a concrete fix task with:
- What to change, in which file, by which specialist.
Update state/STATE.md with the gap summary and fix tasks.
Log findings in logs/claude_log.md.

8. Review Checklist

API contracts verified (frontend vs backend).
DB schema matches service queries.
Auth middleware covers all protected routes.
CI/CD pipelines exist for all services.
All gaps documented with fix tasks.

02

1. Gather Current State

032. Verify API Contracts

043. Verify Database Schema Alignment

054. Check Auth Middleware Alignment

065. Verify CI/CD Coverage

076. Identify Integration Gaps

087. Create Fix Tasks

098. Review Checklist

Desarrolladores de software

Session Logs

Search and analyze your own session logs (older/parent conversations) using jq.

OpenClaw Test Heap Leaks

Investigate `pnpm test` memory growth, Vitest worker OOMs, and suspicious RSS increases in OpenClaw using the `scripts/test-parallel.mjs` heap snapshot tooling. Use when Codex needs to reproduce test-lane memory growth, collect repeated `.heapsnapshot` files, compare snapshots from the same worker PID, triage likely transformed-module retention versus likely runtime leaks, and fix or reduce the impact by patching cleanup logic or isolating hotspot tests.

Node Connect

Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.

Openclaw Qa Testing

Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.

Openclaw Secret Scanning Maintainer

Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.

Flags

Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.

Desarrolladores de software