Total 55,794 skills, AI & Machine Learning has 9268 skills
Showing 12 of 9268 skills
Initialize a full ML research project control root with independent paper, code, and optional slide repositories, shared project memory, root-level agent guidance, code-owned worktree policy, and component handoffs. Use when starting a new research project, setting up a project root for agents, connecting paper/code/slides repos, or replacing a simple paper+code workspace with a lifecycle-aware research project structure.
Diagnose surprising, negative, unstable, or ambiguous ML/AI experiment results and decide whether to debug implementation, rerun experiments, change metrics or baselines, revise the algorithm, narrow the paper claim, park, or kill a direction. Use this skill whenever results do not match expectations, a method fails, metrics conflict, seeds vary, baselines beat the method, plots look suspicious, or the user asks what to do next after experimental results.
Help users replan their lives from the top level of NLP understanding hierarchy; use this when users feel confused, trapped in a daily execution loop, and don't know how to break through the current situation
[Hyper] Optimize an existing Codex skill through baseline-first experiments, binary evals, optional guards, and one-mutation-at-a-time iteration. Use for skill autoresearch, measured trigger/workflow improvement, self-optimizing a skill, benchmarking skill changes, or resuming skill experiment artifacts.
[Hyper] Test Codex/agent skills for intended triggering and behavior with realistic positive, negative, boundary, and edge-case scenarios. Use when validating a skill folder, SKILL.md, rules/references/scripts/assets, trigger precision, workflow correctness, or regression coverage before shipping skill changes.
[Hyper] Use when the user explicitly wants Anthropic Claude Code CLI (`claude`) for an isolated session, non-interactive (`-p`) run, session resume by ID or name, or a CI-friendly `--bare` invocation. Trigger phrases: "use claude code", "ask claude", "run claude", "continue the last claude session", "resume the auth-refactor claude session", or "use Anthropic's CLI to inspect or fix this repo".
[Hyper] Analyze bugs, present repair options, then implement and verify the user-selected fix path. Routes simple bugs directly; tracks complex multi-phase investigations via .hypercore/bug-fix/ JSON flow.
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbiased assessment. Detects score inflation, forces devil's advocate reasoning, and persists scores across sessions.
Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated, no cross-pollination), critic analysis, synthesis, founder review, and decision extraction. Use when the user invokes /cs:board, calls a board meeting, or wants structured multi-perspective executive deliberation on a strategic question.
Show federation health — peers, sessions, trust levels, and message metrics
Design and execute multi-step media workflows with genmedia. Use this for pipelines that combine planning, generation, editing, image or video utilities, audio, subtitles, batching, and final delivery manifests.