Reusable, tool-agnostic AI engineering skills, workflows, templates, and evaluation playbooks for AI coding agents.
Skill Claude CodeCodex
Use this skill to design single-agent or multi-agent AI systems with defined boundaries, tools, memory, state, planning, and guardrails. Activates when building an AI agent, autonomous workflow, or multi-agent orchestration system. Ensures agent scope, permissions, and failure modes are explicitly designed.
Skill Claude CodeCodex
Use this skill to audit an AI system for security vulnerabilities including prompt injection, sensitive data exposure, excessive agent permissions, unsafe tool calls, and insecure output handling. Grounded in OWASP GenAI LLM Top 10 (2026). Activates before production deployment of any LLM-based application, agent, or…
Skill Claude CodeCodex
Use this skill to enforce high-density, zero-filler, token-efficient communication. Strips conversational fluff, polite preamble, redundant summaries, and repetitive apologies to maximize reasoning density, reduce latency, and conserve context window budget.
Skill Claude CodeCodex
Use this skill to systematically manage what information goes into an LLM context window — selecting, compressing, and prioritizing content to maximize response quality within token budget constraints. Activates when building or optimizing LLM applications, RAG systems, or agent workflows that face context window…
Skill Claude CodeCodex
Use this skill to evaluate the quality of a RAG pipeline on faithfulness, answer relevancy, context precision, context recall, and hallucination rate. Activates after a RAG system is implemented or when retrieval quality is in question. Produces a structured evaluation report with measurable results.
Skill Claude CodeCodex
Use this skill to verify that an AI system is ready for production before deployment. Covers model abstraction, cost/latency, retries, fallbacks, structured logging, tracing, observability, evaluation in CI/CD, monitoring, and rollback planning. Activates as a mandatory gate before production deployment of any AI/LLM…
Skill Claude CodeCodex
Use this skill to design end-to-end Retrieval-Augmented Generation (RAG) systems including ingestion, chunking, embedding, retrieval, reranking, and context construction. Activates when building a document Q&A system, knowledge base, or any LLM application that retrieves information at query time.
Skill Claude CodeCodex
Use this skill to design system architecture with documented trade-offs and decisions before any implementation begins. Activates when a feature, system, or component requires non-trivial structural decisions about how components interact, what data stores to use, or how to decompose a problem.
Skill Claude CodeCodex
Use this skill to build disposable, rapid proof-of-concept prototypes and spikes to test feasibility, validate API designs, or explore library capabilities before committing to a full production architecture.
Skill Claude CodeCodex
Use this skill to systematically review code changes for correctness, security, performance, maintainability, and test coverage. Activates after implementation, before merging, or when asked to review a pull request or code change. Produces a structured review report with findings categorized by severity.
Skill Claude CodeCodex
Use this skill to systematically diagnose the root cause of a bug before attempting a fix. Activates when a bug is reported, a test is failing, or unexpected behavior is observed. Prevents guess-and-check debugging that introduces additional bugs while chasing symptoms.
Skill Claude CodeCodex
Use this skill to systematically explore an unfamiliar codebase before making any changes. Activates when starting work in an unknown repository, adding a new feature, debugging without prior context, or when no CONTEXT.md exists. Produces a grounded understanding of architecture, conventions, and constraints.
Skill Claude CodeCodex
Use this skill to compress and serialize the current engineering session state into a structured handoff document. Captures completed work, modified files, key architectural decisions, test status, open blockers, and exact next steps for another agent or future session to resume work without context loss.
Skill Claude CodeCodex
Use this skill to convert an approved architecture into a safe, ordered, reviewable implementation plan before writing any code. Activates after architecture has been designed and approved. Produces a step-by-step plan that the human can review and approve before implementation begins.
Skill Claude CodeCodex
Use this skill to break down complex feature specifications, PRDs, or architectural designs into small, atomic, independently verifiable tasks and tickets. Ensures each task has clear acceptance criteria, dependencies, and validation steps.
Skill Claude CodeCodex
Use this skill to conduct an intensive, interactive requirements interview with the human. Interrogates assumptions, edge cases, domain models, data shapes, error states, and UX subtleties before any specification or design is finalized.
Skill Claude CodeCodex
Use this skill to conduct an interactive requirements grilling session that builds a shared ubiquitous domain language, updates CONTEXT.md with domain glossaries, and records hard-to-explain architectural decisions into ADRs.
Skill Claude CodeCodex
Use this skill to detect and resolve specific requirement ambiguities through structured questioning. Activates when requirements contain vague language, conflicting statements, unstated assumptions, or missing decisions. Run after requirements-analysis identifies gaps, or before design begins.
Skill Claude CodeCodex
Use this skill to analyze, structure, and document ambiguous or incomplete requirements before any design or implementation work begins. Activates when the human has described a feature, task, or problem that needs to be built, but the requirements are not yet fully specified or structured.
Skill Claude CodeCodex
Use this skill to systematically triage, categorize, prioritize, and label incoming issues, bug reports, and feature requests. Verifies reproducibility, identifies affected components, and assigns standardized workflow labels.
Skill Claude CodeCodex
Use this skill to enforce strict safety boundaries on git operations, branch management, and destructive shell commands. Prevents accidental force pushes, hard resets, secret commits, unstashed code loss, and unauthorized production branch modifications.
Skill Claude CodeCodex
Use this skill to practice test-driven development — writing tests before implementation, using tests to drive design, and validating implementation against pre-written tests. Activates when implementing new functionality, refactoring code, or fixing bugs where regression coverage is needed.
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: