MCP servers and skills: search, filter by where they run, and compare.
INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) instead of an LLM, or when auditing an existing agent for LLM calls that only produce a routing decision. C
OfficialSkillMIT★ 1.3k in collectionNo key
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
SkillMIT★ 30kNo key
Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya
SkillMIT★ 763No key
Agent skills for designing, training, evaluating and improving application-specific decision systems. Primitive/model selection, data assembly, export/reload and bounded hill climbing. TypeSafe Jev is
SkillMIT★ 12No key
女性高成就者决策智库 | Women High-Achievers Decision Intelligence — AI Skill for real-world decision support based on 22 real women's life cases. Works with Antigravity, Claude, and any AI agents.
SkillMIT★ 4Few starsNo key
Build and scale developer-led adoption through ecosystem programs. Use when deciding open vs curated ecosystems, building developer programs, scaling platform adoption, or designing student program pi
OfficialSkillMIT★ 40k in collectionNo key
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to e
OfficialSkillApache-2.0★ 21k in collectionNo key
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
SkillApache-2.0★ 32kNo key
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. Use when the user says "deploy my model", "create an endpoint", "make it
OfficialSkillApache-2.0★ 918 in collectionNo key
Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "run a benchmark", "test model perform
OfficialSkillApache-2.0★ 918 in collectionNo key
28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
SkillMIT★ 1.6kNo key
A skill to claude code that enables brainstorming with other LLMs (ChatGPT, Gemini) before presenting the implementation plan to the user
SkillMIT★ 471No key
pstack reworked for T3 Code: delegated subagents, worktree threads, PR watching, scheduled runs.
SkillMIT★ 155No key
A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector store, queried before each message. For cross-project recal
SkillApache-2.0★ 63No key
Jev Browser — indexed browser automation. Jev chooses the control, Playwright acts. A CodexQA skill.
SkillMIT★ 51No key
Thinking partner skill for AI agents — 150+ mental models, orientation detection, cognitive operations. Works with Claude Code, Cursor, Windsurf, Cline, GitHub Copilot.
SkillMIT★ 213No key
Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.
SkillMIT★ 30No key
Who stands behind it
