figure-it-out
Designs an auditable playbook when no narrower one fits. Use for a large migration, an ambitious multi-part change, or work a human reviews later. Logs via…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Agents & models
25,385 results
swarm
Fans out N parallel workers, drains them, and returns one aggregated report. Use for swarm this, parallel coverage, races, gauntlets and exploration partitions.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").
global-chat-agent-discovery
Discover and compare MCP servers and AI agents using Global Chat's cross-protocol directory and MCP server.
lightning-channel-factories
Technical reference on Lightning Network channel factories, multi-party channels, LSP architectures, and Bitcoin Layer 2 scaling without soft forks. Covers…
recallmax
FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into…
transformers-js
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript.
yann-lecun-tecnico
Technical sub-skill of Yann LeCun. Covers CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervised…
reward
Motto: Rewards should feel earned and fitting.
loom
Designing a repository's operating layer — which project-local skills, recipes, and orchestration workflows it needs, as one system. Not for a single skill…
instant-agent-email-accounts-with-pigeonscale
Create and use real Pigeonscale mailboxes for AI agents, including bootstrap mailbox creation with human approval, signed-in mailbox creation, sending and…
prompt-engineering
Master prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts.…
oraclenet
OracleNet — claim identity, post, comment, feed. Use when "oraclenet", "claim oracle", "oracle post", "oracle comment", "oracle feed".
tmux-agents
Manage background coding agents in tmux sessions. Spawn Claude Code or other agents, check progress, get results.
craft-survey
Survey prior art for prompts, skills, or repo assets. Use for "how others do this", adopt/avoid patterns, older assets, or pre-draft research.
domain-modeling
Discover uncertain domain terms and invariants; persist only exact accepted meaning.
skill-creator
Guide for creating effective AI agent skills. Use when users want to create a new skill (or update an existing skill) that extends an AI agent's capabilities…
ship
Task entrypoint and delivery orchestrator for an Opus-class coordinator. Routes a raw task through three gates — design (design-doc), GitHub issues, dispatch…
claude-agent-sdk
This skill should be used when the user asks to "build an AI agent with Claude", "use the Claude Agent SDK", "integrate claude-agent-sdk into a project", "set…
nvidia-engineer
Senior NVIDIA Engineer mindset and technical expertise covering GPU architecture (Hopper/Blackwell), CUDA optimization, AI/ML infrastructure (DGX, H100, A100,…
systems-engineer
Aerospace systems engineer specializing in requirements management, system integration, verification & validation, and MBSE methodologies.
eventmodeling-brainstorming-events
Step 1 of Event Modeling - Brainstorm all domain events from requirements. Extract every state-changing event the system could have. Use when starting event…
creating-skills
Create, edit, evaluate, and optimize agent skills for Codex and Claude Code. Use when the user wants to author a new skill, refactor an existing one, run evals…
agenta
LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted…