Anyone can call an LLM.
Operating one needs evidence.
A demo becomes a production system only when its decisions are inspectable: evaluation, gates, readiness checks and observability.
AI Coding OS is a separate companion skills pack, not a course or a Full Harness track. The Full Harness is the collection of eight course tracks; this pack instead provides a portable library of SKILL.md contracts for Claude Code, Cursor and Codex.
Generating code was never the hard part.
Changing a model is only one decision. A production workflow still needs an inspectable way to review code, tests, gates and security evidence before it promotes, holds or rolls back a change.
- Every skill has a usage boundary — no overlap, no guessing.
- Quality gates decide promote / hold / rollback on evidence.
- Anti-patterns and an output contract in every workflow.
Concretely: portable skills you own.
A SKILL.md file
Markdown + frontmatter with a usage boundary, workflow, promote/hold/rollback gates, anti-patterns and an output contract. Structure, not vibes.
Drop it in your skills folder
Copy into ~/.claude/skills (or your Cursor/Codex setup). No new tool, no CI rewiring, no server.
A library, not a SaaS
Portable files you can keep, read and adapt. Access terms are confirmed directly while checkout is not yet public.
A curated library, not a prompt dump.
The coding, agent, operations and review skills used to build real products — plug-and-play in your agent of choice.
Design → run → harden
Architecture, implementation, runtime reliability, red-teaming and standards so your agent rules work across tools.
Ship on evidence
Readiness scoring, eval lifecycle, dogfooding loops and controlled prompt/policy experiments.
Production-grade
Observability/SRE, security guardrails, web security and retrieval reliability.
Defend the codebase
Layered PR review, deep code-quality audits and end-to-end release orchestration.
The PR review skill is free.
Run it on a real pull request and inspect the methodology: layered review, quality gates and a clear merge verdict. Public download is not open yet; request the sample through the contact form.
pr-review
Structured, evidence-driven PR review against your project docs and quality gates. Works in Claude Code, Cursor and Codex.
Built on published research.
The evaluation, gates, release and security discipline in these skills is grounded in the field's published research and the standards of record — the same public work the courses cite, not invented for a landing page.
AGENTS.md — the open standard for the repo-level file every coding agent reads
Read the standard → guidance · agentsBuilding effective agents — why non-deterministic agents need deterministic gates around them
Read the guidance → standard · securityOWASP Top 10 for LLM & Agentic Applications
Read the list → framework · securityMITRE ATLAS — the adversarial threat landscape for AI systems
Read the framework → research · deliveryDORA — DevOps Research & Assessment delivery metrics
Read the research →Stop prototyping. Start operating.
The library is prepared for Claude Code, Cursor and Codex. Checkout is not public yet; use the contact form to request access or the free sample.