Total 55,448 skills, AI & Machine Learning has 9214 skills
Showing 12 of 9214 skills
Use when a locally-served model misbehaves in an agent harness — wrong/empty tool calls, truncated output, context overflow, or slow generation. Diagnoses whether the fault is the model tier, the serving config, or the harness wiring, using the agentic repo's probe and model matrix.
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register, opener-POS profile, punctuation rates) and gates drafts against the fingerprint as bands, not vibes.
Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices.
What the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when.
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like hui while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "hui mode", "talk like hui", "use hui", "less tokens", "be brief", or invokes /hui. Also auto-triggers when token efficiency is requested.
Select available tools based on research tasks, data, and operating environment; works without a preset local research-lab. Use when the user asks for "which tool to use for research tasks", "help me choose research tools", "is this repo useful", or requests the rw-research-lab-router workflow. Runs without a private local workspace or preset research-lab; uses user-provided materials and bundled public-source methods.
AI SDLC evidence-backed retrospective workflow. Use when delivery work is complete or paused and an AI assistant needs to capture observations, connect them to validation or artifact evidence, formulate reviewable process or policy improvement proposals, assign ownership, and preserve the rule that policy changes require an accepted decision. Supports `--quick-flow` for focused learning and `--full-flow` for strict evidence and decision gates.
Build NPC AI in Unreal Engine 5 with Behavior Trees and Blackboards: composites (Selector/Sequence), tasks, decorators, services, and running the tree from an AIController. Use when creating enemy/NPC AI, BT_/BB_ assets, custom BTTask or BTService nodes, or when the user mentions Behavior Tree, Blackboard, AIController, BTTask, decorator, or service.
Compatibility router for LangWatch evaluation requests. Use only when the user asks for evaluations without making it clear whether they mean pre-deployment experiments or production online evaluations. Routes the request to the focused companion skill and does not implement either workflow itself.
Delegate a coding task to the Pi coding agent CLI (`pi`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Pi - phrasings like "have Pi implement X", "delegate this to pi", "run it through Pi", or "use pi to implement/fix/refactor" - or wants to run a queue of coding tasks through Pi while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Apply fixes from an /age report, finding list, or CI failure, then run the project's test/lint/build gates and hand a clean cure to /plate for commit/publication. Use when the user wants selected findings resolved. Do NOT use for review (route to /age), test authoring (route to /press), or direct publication (route to /plate).
Use when generating Claude Code enforcement hooks from a repo's docs/ structure.