agents-langchain
LangChain framework for building LLM apps with agents, chains, and RAG across providers. Use for chatbots, tool-calling agents, and retrieval workflows in…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
dispatching-parallel-agents
Use when splitting complex work into parallelizable tasks and coordinating multiple agents. Focus on clear task boundaries, shared context, and consolidation…
senior-prompt-engineer
Prompt engineering workflow for building reliable assistants and agents: task decomposition, instruction hierarchy, tool-use patterns, safety constraints, and…
gsd-plan-milestone-gaps
Create phases to close all gaps identified by milestone audit
memory-systems
Design agent memory architectures for cross-session persistence. Use for building learning systems, maintaining entity consistency, and temporal knowledge…
parallel-dispatch
Dispatch multiple independent agent tasks for concurrent execution. Use when multiple unrelated failures or features need simultaneous work. Based on…
session-start-routine
Execute work session initialization routine at conversation start. Identifies new skills, researches improvements for existing skills, and updates skill…
source-command-compound-extended
Run cross-agent memory bridge. Sync learnings between machine agents, update shared knowledge. Phase 5 of #1760.
skill-02-smart-contract-interaction
Interacts with smart contracts via ABI encode/decode, read/write calls, deployment, proxy patterns, and multicall batching. Use when calling contract…
skill-11-oracle-data-feeds
Integrates oracle and data feed services including Chainlink and Pyth price feeds, VRF randomness, and Chainlink Automation keepers. Use when consuming…
skill-13-rwa-tokenization
Handles real-world asset tokenization including treasuries, real estate, bonds on-chain, ERC-3643 compliance tokens, and yield distribution. Use for…
skill-14-social-reputation
Integrates Web3 social protocols including Lens, Farcaster, Frames, reputation scores, and prediction markets. Use for social graph queries, on-chain…
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and…
using-superpowers
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage,…
grill-me
Relentlessly interview the user about a plan, design, or architectural decision — one question at a time, each with your recommended answer, exploring the…
ai-python-telemetry
Use when adding telemetry, tracing, or OpenTelemetry export to AI SDK for Python, or when reporting spans from durable or serverless execution.
tmux-agent-lane-orchestrator
Monitor and coordinate one tmux agent lane, reconstruct worker state from panes and recent Codex logs, classify progress and blockers, and produce concise…
improve-orchestrator-system
Use when: auditing one or more finished or stopped sessions of an installed orchestrator agentic system, by session id, for wasted tokens, drift from the…
agents-md-evals
Evaluate and optimize AGENTS.md/CLAUDE.md instruction files through A/B testing. Use when the user says "eval my agents.md", "test my claude.md", "optimize my…
claude-vigil
Use when about to make risky changes — refactors, migrations, destructive bash commands, schema changes, or experimental approaches that might need reverting.…
oz-child-agent-orchestration
Internal Oz child-agent orchestration playbook for Claude Code child runs. Invoke only when the Oz harness system prompt tells you to coordinate with a lead…
loom-ask-user
Primary workflow-independent agent-facing consumer of shared XO Ask capability in AO/SO runtime binaries. Turns a caller's questions into one structured ask…
unity-game-balance
Numeric design role for Unity games. Use when designing, simulating, configuring, or validating tunable systems such as difficulty, economy, progression, drops, combat, and pacing.
openai-docs
Use when answering questions about OpenAI platform features, guides, and concepts: Responses API usage, agents, function calling, text generation, vision,…