Loading...
Loading...
Found 6,626 Skills
Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem.
Create, update, refactor, explain, or review Microsoft Agent Framework solutions using shared guidance plus language-specific references for .NET and Python.
Agent harness performance system for Claude Code and other AI coding agents — skills, instincts, memory, hooks, commands, and security scanning
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
Use when one agent is implementing code and another agent must review the resulting changes, compare the summary against the actual files, decide whether to fix now or move on, and write the next tightly scoped prompt with context handoff guidance.
CrewAI architecture decisions and project scaffolding. Use when starting a new crewAI project, choosing between LLM.call() vs Agent.kickoff() vs Crew.kickoff() vs Flow, scaffolding with 'crewai create flow', setting up YAML config (agents.yaml, tasks.yaml), wiring @CrewBase crew.py, writing Flow main.py with @start/@listen, or using {variable} interpolation.
Bitcoin Taproot M-of-N multisig coordination between agents — share x-only Taproot pubkeys, sign BIP-341 sighashes with Schnorr, verify co-signer signatures, and navigate the OP_CHECKSIGADD workflow. Proven on mainnet (2-of-2 block 937,849 and 3-of-3 block 938,206).
Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.
MUST be used whenever building a chat UI with Atlas agents in a Dune app. Do NOT manually write useAtlasChat integration code — this skill handles installation, component structure, and hook wiring. Triggers: useAtlasChat, atlas chat, streaming chat, agent chat, chat interface, chat component, chat UI. For a full chat app, run skills in order: (1) integrate-atlas-chat, (2) create-client-tool (per tool), (3) setup-python-tools (if Python tools needed).
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. OCD-level review and synchronization of project documents and agent memory after a session. MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "sync up", "tidy up docs", "tidy up", "update memory", "organize", "wrap up", "this phase is done", "newcomers can start directly", or any phrase suggesting a development milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. A standalone "tidy" with prior development context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.
Use this skill when the user mentions creating a payment link, paying a paymentId / a2a_... link, or checking a2a payment status. Wraps `onchainos payment a2a-pay` agent-to-agent payment protocol: seller-side `create`, buyer-side `pay` via EIP-3009 + TEE signing, and `status` query. Buyer-side trust is delegated to upstream — the skill signs whatever the on-server challenge declares. Do NOT use for external HTTP 402 resources — use okx-x402-payment. Do NOT use for wallet balance / transfer / login — use okx-agentic-wallet.
Turn a completed experiment iteration into an honest, evidence-backed analysis — a markdown report and a portable data dump. Pulls run data via the tpc CLI, scores each task, clusters friction by root cause (with a transcript example per claim), compares arms, and closes on agent-readiness gaps. The natural companion to setup-experiment: setup → run → analyze. Trigger when users say: "analyze my experiment", "write the report", "experiment report", "analyze the results", "summarize the runs", "what happened in this iteration", "friction report", or "report gen".