codex-howto

In the author's own words, from each skill's SKILL.md.

• build-backend

  Build or modify backend APIs, services, jobs, persistence, and integrations while preserving contracts, authorization, data integrity, and failure behavior. Use for server-side features, database changes, background processing, backend defects, and service refactors; do not use for frontend-only or infrastructure-only work.

  skills/build-backend/SKILL.md on GitHub (opens in a new tab)

• build-frontend

  Build or modify frontend interfaces using repository-native components while preserving accessibility, responsive behavior, state handling, and visual verification. Use for UI features, design implementation, forms, client-side defects, and frontend refactors; do not use for backend-only or infrastructure-only work.

  skills/build-frontend/SKILL.md on GitHub (opens in a new tab)

• engineering-loop

  Implement a repository code or configuration change through reproduction, focused checks, review, and evidence. Use for end-to-end features and fixes; not for explanation-only, review-only, research, content publishing, or production operations.

  skills/engineering-loop/SKILL.md on GitHub (opens in a new tab)

• maintain-codex-wiki

  Maintain a review-first Markdown knowledge base for Codex practices with source provenance, engineering capture, citation-aware queries, explicit archive and promotion, and deterministic linting. Use when asked to capture a durable engineering lesson, ingest Codex research, query or archive what the repository knows, check wiki health, reconcile conflicting guidance, or promote verified knowledge.

  skills/maintain-codex-wiki/SKILL.md on GitHub (opens in a new tab)

• operate-devops

  Plan and implement infrastructure, CI/CD, container, deployment, observability, and operational configuration changes with least privilege, staged validation, and rollback awareness. Use for pipelines, infrastructure as code, Kubernetes, containers, release automation, monitoring, and production-readiness work; do not use to perform destructive production actions without explicit authorization.

  skills/operate-devops/SKILL.md on GitHub (opens in a new tab)

• orchestrate-engineering

  Coordinate complex engineering work across bounded subagents while protecting the main context, preventing edit conflicts, and measuring whether delegation was worthwhile. Use when the user asks to delegate, parallelize, orchestrate, use subagents, fan out a review, or handle a large task with independent workstreams; do not use for small, tightly coupled, or inherently sequential tasks.

  skills/orchestrate-engineering/SKILL.md on GitHub (opens in a new tab)

• review-code

  Review code changes for correctness defects, regressions, security risks, data-integrity problems, concurrency hazards, and missing meaningful tests. Use for pull requests, branches, commits, patches, or working-tree reviews; do not use for implementation unless the user separately requests fixes.

  skills/review-code/SKILL.md on GitHub (opens in a new tab)

• review-security

  Review application and infrastructure changes for exploitable security risks by tracing assets, trust boundaries, attacker-controlled input, authorization, sensitive data, and dangerous sinks. Use for security reviews, threat-focused PR reviews, authentication or authorization changes, input handling, secrets, dependencies, and infrastructure permissions; do not use to exploit live systems or mod…

  skills/review-security/SKILL.md on GitHub (opens in a new tab)

• test-software

  Design, implement, and evaluate risk-based software tests across unit, integration, contract, end-to-end, and regression layers. Use when adding tests, reproducing bugs, improving coverage, diagnosing flaky tests, or defining a test strategy; do not use to change production behavior unless the user also requests implementation.

  skills/test-software/SKILL.md on GitHub (opens in a new tab)

• choose-engineering-flow

  Select the smallest useful Codex engineering workflow from this repository's existing skills. Use when a task spans multiple engineering concerns, the user is unsure which skill to invoke, or loading every specialist would waste context; return a recommendation only and do not execute the engineering task.

  examples/skills/choose-engineering-flow/SKILL.md on GitHub (opens in a new tab)

• evidence-review

  Review a small code or documentation change and return only evidence-backed correctness findings. Use in the Codex How To local plugin lab; do not modify files or post remote comments.

  examples/plugin-marketplace/plugins/engineering-review/skills/evidence-review/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• gentle-aiby Gentleman-Programming Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Or… 8.5k stars · 20 skills
• stop-that-shitby lennney Stop That Shit（别再造史了）｜面向 Codex/GPT 场景的多平台 Hook + Skill Guard：拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for… 3.7k stars · 2 skills
• loopyby Forward-Future A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows. 3.2k stars · 2 skills
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 111k stars · 1 skill
• archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. 94.2k stars · 5 skills
• agentic-awesome-skillsby sickn33 2,926+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection… 49.3k stars · 30 skills