Total 50,634 skills, AI & Machine Learning has 8486 skills
Showing 12 of 8486 skills
Autonomous research agent that reads RESEARCH.md, infers what's needed, dynamically adjusts TODOs, and delegates to the right skill. Supports opt-in BFS mode for autonomous design space search. Respects a configurable supervision policy (presets: manual / checkpointed / autonomous / wild) governing notifications, approval gates, resource limits, and idea-change handling. Proactively surfaces gaps and asks before acting. Trigger phrases: "start research", "continue project", "what's next?", "explore design space", "autoresearch".
Runs ML experiments reproducibly — single runs or autonomous BFS batches. Single mode: isolated venv, time-budgeted, failure-handled, logs to RESEARCH.md. BFS mode (opt-in): designs N hypotheses, runs each for a fixed budget, compares via a single verifiable metric, keeps improvements and git-resets failures — fully autonomous until done. Respects the RESEARCH.md supervision policy for notifications, approvals, and stop limits. Trigger phrases: "run experiment", "train model", "explore design space", "find best config", "autoresearch".
Configure the project's supervision policy in RESEARCH.md. Uses a preset-first flow (`manual`, `checkpointed`, `autonomous`, `wild`), then lets the user adjust notification events, approval gates, stop limits, resource rules, and idea-change handling. Trigger phrases: "configure supervision", "set supervision", "automation settings", "change autonomy", "/supervision".
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.
使用 parallel sub-agents 为 module 生成多个 radically different interface designs。Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Start a project-driven learning journey for any technical topic — programming languages, tools, frameworks, or concepts. Teaches through real projects, Diffity tours, and interactive conversation, adapting to the learner's pace.
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.
This spell is archaeology, not history research. It operates on specific artifacts from a specific dead system to answer specific questions. It is NOT general tech history, NOT interviewing living people, and NOT monitoring live systems.
Day-one data bootstrapping for a new brain. Sequences the highest-leverage data sources to go from empty brain to useful brain in one session. Uses ClawVisor for safe credential handling — the agent never holds raw API keys. Covers Gmail import, calendar sync, contacts seeding, X/Twitter archive, conversation imports, and file archives. Use when a user has just finished gbrain setup and asks "now what?"
Generic framework for converting external events (SMS, meetings, social mentions) into brain-ingestible signals. Define a transform function, register a webhook URL, and incoming events get processed through the brain pipeline.
Use when multiple subtasks have no shared files or dependencies and can be executed simultaneously.