Agent skills for OpenAI Agents SDK

How the nWave buddy agent reads a project to answer questions — detection, order of inspection, and citation discipline.

Turn a completed or paused body of work into an evidence-based retrospective covering goals, outcomes, decisions, pivots, effective…

Generates a complete, compilable project scaffold -- directory structure, entry point, config, Makefile, README -- for a new Go (or other…

Initializes and updates project-specific AGENTS.md files and concise engineering documentation grounded strictly in repository facts.

Cross-framework project status aggregator — discovers contributors from installed frameworks, runs declarative detection, produces a…

Standardizes software project layouts and directory hierarchies across various programming languages and frameworks.

Generates 15-second vertical promo videos for social media from mastered audio.

Generates platform-specific social media copy from album themes, track concepts, and lyrics.

Adversarially reviews a draft prompt against a versioned rule set to find what will make it underperform — archetype mismatch, wrong…

Transforms a rough idea into a detailed design document with implementation plan.

Universal prompt engineering techniques for any LLM.

Audits a prompt against the actual codebase, docs, and strategy files — separates fact from invention, finds what's already built…

Meta's 86M prompt injection and jailbreak detector.

Optimizes AI prompt creation through model-specific strategies and multi-layered architectures for Claude, GPT, and Gemini.

Publish, read, comment on, or edit markdown in Proof.

Validates entire engineering proof chain.

Writes rigorous mathematical proofs for ML/AI theory.

Compare up to 3 UK properties side by side — comparable sales, EPC ratings, rental yields, stamp duty, and a relative ranking.

Chorus Proposal workflow — create proposals with document and task drafts, manage dependency DAG, validate and submit for review.

Stress-tests product proposals, architecture designs, and technical plans through structured adversarial questioning and failure mode…

Develop, compare, and recommend among multiple plausible fixes for a problem.