By Bang-isme
Enforce a spec-first, quality-gated development workflow for AI-assisted coding projects: generate specs before code, run security and lint checks before commits, automate git branching and PR creation, maintain project memory across sessions, and apply TDD practices.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when a project has 50+ files, missing context, or explicit $codex-genome request; generates multi-layer project context to reduce hallucination.
Use for DESIGN.md visual identity contracts; author, scaffold, lint, diff, and export design contracts with the upstream spec and CLI.
Use for UI, frontend, styling, landing page, or component creation; injects palettes, typography, layouts, motion, and anti-generic design rules.
Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Production-ready instruction framework for Codex - deterministic workflows, deliberate reasoning, domain routing, strict quality gates, and persistent project memory.
CodexAI Skill Pack turns Codex from an ad-hoc code assistant into a structured engineering partner. Instead of relying on prompt luck, the pack enforces a repeatable flow:
Intent -> Spec -> Plan -> Route -> Implement -> Verify -> Persist -> Commit
The pack is designed for 3 outcomes:
| Metric | Value |
|---|---|
| Core Skills | 28 |
| Entry-point Scripts | 69 |
| Shared Helpers | 2 |
| Reference Docs | 188+ |
| Starter Templates | 29 |
| Artifact Templates | 9 |
| Agent Personas | 8 |
| Workflow Aliases | 8 |
| Verification | 341 unit + 71 smoke = 412 tests |
| Codex Native Plugin | .codex-plugin/plugin.json + .agents/plugins/marketplace.json |
| Claude Code Plugin | .claude-plugin/plugin.json + hooks/hooks.json |
| GitHub Automation | GitHub CLI (gh) + gh auth login for PR/release workflows |
| CI/CD | .github/workflows/ci.yml + .github/workflows/release.yml |
| Weakness in default AI workflows | What this pack adds |
|---|---|
| Vague task interpretation | codex-intent-context-analyzer locks goal, scope, and ambiguity before code |
| Plans that sound good but do not guide execution | codex-plan-writer creates verifiable, dependency-aware task breakdowns |
| Design output drifts between sessions | codex-design-system plus codex-design-md turn design intent into reusable vocabulary and a lintable DESIGN.md contract |
| Generic output with no proof | codex-reasoning-rigor plus output_guard.py force evidence-backed deliverables |
| AI-safe writing that still feels synthetic | editorial_review.py scores tone, decision clarity, tradeoffs, and scanability |
| Documents that make readers infer too much | codex-document-writer forces purpose, audience, structure, complete sentences, and reliability wording |
| No final gate before declaring done | codex-execution-quality-gate runs lint, tests, security, output quality, editorial quality, UX, and trend tracking |
| Context lost between sessions | codex-role-docs preserves role-scoped project docs, while codex-project-memory stores decisions, summaries, genome, handoffs, and changelog inputs |
| Tacit knowledge stays invisible | build_knowledge_index.py turns genome, role docs, decisions, commits, and configs into .codex/knowledge/INDEX.md |
| Fullstack prototypes start from vague prompts | codex-spec-driven-development forces spec-first acceptance criteria before $plan and implementation |
| Scrum roles live only in people's heads | codex-scrum-subagents installs project .agent kits and native .codex/agents custom agents |
| Skills only work in one agent app | Dual Codex + Claude plugin metadata lets both agents load the same skills/<name>/SKILL.md contracts |
Pull request and release automation use GitHub CLI (gh). Install and authenticate once before using commit/PR helpers or wrapping this pack in a project CLI:
gh auth login
gh auth status
Use GitHub CLI credential storage locally, or GH_TOKEN / GITHUB_TOKEN in CI. Never commit tokens into plugin manifests, skill docs, generated artifacts, or source files.
The repository ships a senior baseline GitHub Actions setup:
ci.yml: plugin validators, pack health, tool contracts, prompt-router corpus, memory-at-scale (medium), Python 3.12–3.13 × Linux/Windows matrix, Python 3.11 on main, trust harness smoke, advisory security scan, and GitHub CLI contract checks.scale-nightly.yml: weekly large-tier memory scale gate (8000 synthetic files) with JSON report artifact.release.yml: optional manual ZIP build (workflow_dispatch only).CI validates this plugin pack only. CI/CD scripts and plugin-tools.json are capabilities for your Project CLI to invoke locally against any project-root — not a production deploy pipeline for this repo.
Local pack check (optional, before sharing a ZIP):
python skills/.system/scripts/local_release_gate.py --format json
python skills/.system/scripts/local_release_gate.py --apply --format json
See skills/.system/references/deploy-promotion.md.
npx claudepluginhub bang-isme/codexai---skillsComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.