Stats
Actions
Tags
From go-backend-skills
Code review via Codex CLI plugin. Use when user types /review or asks for a code review of recent work. Requires the openai-codex plugin to be installed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/go-backend-skills:codex-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run an automated code review by delegating to the Codex CLI plugin.
Run an automated code review by delegating to the Codex CLI plugin.
Install the openai-codex plugin:
/install-plugin openai-codex/codex
Create a review prompt at .codex/review-prompt.md in your repo root. This
file defines what Codex checks for — conventions, correctness rules, known
drift patterns, and output format. Example structure:
# Code Review Instructions
Apply project skills and conventions to the diff.
## Known Drift Patterns
- [list rules that have caused repeated issues]
## Review Checklist
### Convention Violations
- [project-specific patterns]
### Correctness
- Missing error checks, nil pointer risks, auth assumptions
- Multi-system ordering: external side effects before DB commits
- Required-vs-optional failures: log-and-continue only when truly optional
### Test Coverage
- New endpoints must have tests
Read the review prompt:
cat .codex/review-prompt.md
Determine the review scope:
Dispatch to the codex:rescue subagent with the review prompt and scope:
/codex:rescue Review the <scope> diff. <contents of .codex/review-prompt.md>
Present findings as-is. Do not filter or summarize.
If Codex found issues that map to a pattern not yet in the review prompt under "Known Drift Patterns", suggest adding it.
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.
npx claudepluginhub klaidliadon/skills