Skill Claude CodeCodex
Use when asked to evaluate PR test coverage or explicitly asked to run the pr-test-analyzer subagent.
This repository also configures its own agents. See what codex-skills tells them →
Skill Claude CodeCodex
Use when asked to evaluate PR test coverage or explicitly asked to run the pr-test-analyzer subagent.
Skill Claude CodeCodex
Use before starting implementation - research repository documentation, codebase patterns, and external resources to inform the approach.
Skill Claude CodeCodex
MANDATORY for all work - the project board is THE source of truth. This skill provides verification functions and gates that other skills MUST call. No work proceeds without project board compliance.
Skill Claude CodeCodex
Use to keep GitHub Project fields synchronized with actual work state - updates status, verification, criteria counts, and other project-specific fields.
Skill Claude CodeCodex
Use after 2 consecutive failed attempts at solving a problem - STOP guessing and research documentation, codebase, and online resources before resuming.
Skill Claude CodeCodex
HARD GATE before PR creation - verifies review artifact exists in issue comments, all findings addressed or tracked, blocks PR creation if requirements not met.
Skill Claude CodeCodex
Use before code review - determine if change is minor (review new code only) or major (review impacted code too).
Skill Claude CodeCodex
MANDATORY for security-sensitive code changes - OWASP-based security review with dedicated checklist, required before PR for auth, input handling, API, database, or credential code.
Skill Claude CodeCodex
Use when explicitly asked to run the security-reviewer subagent or when another skill requires the security-reviewer agent card.
Skill Claude CodeCodex
Use at the beginning of every work session - establishes context by checking GitHub project state, reading memory, verifying environment, and orienting before starting work.
Skill Claude CodeCodex
Use when asked to detect silent failures/weak error handling or explicitly asked to run the silent-failure-hunter subagent.
Skill Claude CodeCodex
Use when writing code in typed languages - enforces full typing with no any/unknown/untyped escapes, even if it requires extra time.
Skill Claude CodeCodex
Use when writing code - follow Google style guides where available, otherwise follow established best practices for the language.
Skill Claude CodeCodex
Use when implementing features or fixes - test-driven development with RED-GREEN-REFACTOR cycle and full code coverage requirement.
Skill Claude CodeCodex
MANDATORY when working with time-series data, hypertables, continuous aggregates, or compression - enforces TimescaleDB 2.24.0 best practices including lightning-fast recompression, UUIDv7 continuous aggregates, and Direct Compress.
Skill Claude CodeCodex
Use when asked to evaluate type design/invariants or explicitly asked to run the type-design-analyzer subagent.
Skill Claude CodeCodex
Use before merging PR - final gate ensuring all tests pass, review complete, CI green, and acceptance criteria verified.
Skill Claude CodeCodex
Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills. Use this when receiving any new work request.
Skill Claude CodeCodex
Use to spawn isolated worker processes for autonomous issue work. Creates git worktrees, constructs worker prompts, and handles worker lifecycle.
Skill Claude CodeCodex
Defines context handover format when workers hit turn limit. Posts structured handover to GitHub issue comments enabling replacement workers to continue seamlessly.
Skill Claude CodeCodex
Defines behavior protocol for spawned worker agents. Injected into worker prompts. Covers startup, progress reporting, exit conditions, and handover preparation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: