完成任务、实现重要功能或合并前使用，用于验证工作成果是否符合要求

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.

Mobile game development principles. Touch input, battery, performance, app stores.

Test pull requests with comprehensive validation and generate structured test results

API — ACO — 30 abstractions. Folder event handlers and use cases.

Chunking, embeddings, and RAG pipeline integration

Turn changelog-scan output into polished, categorized release notes draft. Propose only.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Command: changeset

Next.js expert for App Router, SSR/SSG, API routes, middleware, and deployment

Figma design expert for components, auto-layout, design systems, and developer handoff

Ansible automation expert for playbooks, roles, inventories, and infrastructure management

PUA team status alias for Codex. Codex subcommand mapping for Claude Code /pua:team-status style usage; invoke with $pua-team-status.

PUA flavor alias for Codex. Codex subcommand mapping for Claude Code /pua:flavor style usage; invoke with $pua-flavor.

Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators, maintains a debt register, and recommends repayment scheduling.

Skill for analyzing trace files and finding hard causal links across threads and processes (using waker_utid).

Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent skill files. Discover community skills across 160+ provider categories, evaluate relevance with heuristic scoring, check for malware or hardcoded secrets, and install into Hermes, Claude Code, Gemini CLI, or OpenCode agent directories.

Option P&L analysis methodology: payoff diagrams, breakeven calculation, multi-leg strategy visualization, and Greeks-based scenario analysis.