Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work should run in an observable background terminal instead of the Agent tool.
Master skill — set up the full agent harness for any repo so an agent can work it reliably: legible (map-not-manual docs + custom lints), executable (one-command dev stack), verifiable (e2e gate + a verify-before-ship loop), plus commit hygiene and entropy control. Use when onboarding a new/unfamiliar codebase to agent-driven development — "set up the harness", "make this repo agent-ready", "harness this codebase".
Use when coordinating or working inside a MetaBot Agent Team via `metabot teams`: create/list teams, spawn teammates, exchange messages, manage shared tasks, inspect runs, and report status to the lead.
Memory cleanup and organization skill for AI employees. Provides guidelines for detecting duplicates, fixing misclassified files, and removing stale information from memory storage.
Use for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired) — DataModel/Field/Input, JSON operators (+ & | ^ ~), synalinks.ops, LanguageModel/EmbeddingModel and provider prefixes (openai/anthropic/ollama/groq/openrouter/bedrock/...); the Program class and its four building APIs (Functional/Sequential/Subclassing/Mixed), save/load, summary; generation modules (Generator, ChainOfThought, SelfCritique, Identity, PythonSynthesis) and custom Module subclassing; control flow (Decision, Branch, And/Or/Xor, parallel branches, self-consistency, XOR guards); agents (FunctionCallingAgent, RecursiveLanguageModelAgent/RLM, DeepAgent, Tool, MCP, subagents); KnowledgeBase/RAG (DuckDB, EmbedKnowledge/UpdateKnowledge/RetrieveKnowledge, hybrid search); training (compile/fit/evaluate/predict, callbacks, ProgramCheckpoint); rewards & metrics (ExactMatch, CosineSimilarity, LMAsJudge, ProgramAsJudge, F1Score, custom rewards, masking); optimizers (RandomFewShot, OMEGA/DNS); datasets (gsm8k, hotpotqa, arcagi) and visualization. Synalinks is Keras-shaped, so without guidance LMs mix Keras/LangChain/DSPy syntax — this skill constrains usage to idiomatic Synalinks.
Author a custom SuperDoc LLM-tools "action" — a named, deterministic document-edit verb that plugs into the core preset's superdoc_perform_action tool. Use when the user wants to add a new action (e.g. "build an action that adds footnotes / bolds table borders / stamps a banner") or asks how to extend SuperDoc's LLM tools with their own document operation. Works with installed packages only — no SuperDoc source checkout needed or expected.
Capture a hard-won "golden path" from the current session as a reusable Agent Skill, so future sessions start already knowing it. Use it (1) right after non-trivial debugging, after working out a multi-step operational workflow, or after rediscovering project facts you didn't know up front — e.g. how to reach the dev/prod database, where credentials and env vars live, how to deploy, run migrations, or verify a change live; and (2) whenever the user says "remember this", "save this as a skill", "make a skill for this", "don't make me re-explain this next time", or otherwise wants a workflow preserved across sessions. Proactively recognize the moment even when unprompted: if a task took several attempts before it worked, used non-obvious tooling, or is likely to recur, harvest it without asking first. Delegates to a subagent when your tool supports one, or works inline, to extract the proven procedure into a new project-local or global skill.