yao-gametheory-skill
Route CEO-facing competition, negotiation, channel, pricing, platform, M&A, financing, competitor-response, alliance, and regulator problems through an applied…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-29 00:09
Agents & models
25,059 results
decision-prompt-builder
Build one compact choice card at a genuine mathematical-modeling judgment point. Use before method screening, after a meaningful experiment, or before final…
auto-claude-optimization
Auto-Claude performance optimization and cost management. Use when optimizing token usage, reducing API costs, improving build speed, or tuning agent…
bedrock-agentcore-multi-agent
Amazon Bedrock AgentCore multi-agent orchestration with Agent-to-Agent (A2A) protocol. Supervisor-worker patterns, agent collaboration, and hierarchical…
ai-provider-openai-sdk
Official OpenAI SDK patterns for TypeScript/Node.js — client setup, Chat Completions, Responses API, streaming, structured outputs, function calling,…
bitflow-limit-order
Agent-powered limit orders on Bitflow — set price targets, auto-execute swaps when conditions are met.
memory
Working memory management, context prioritization, and knowledge retention patterns for AI agents. Use when you need to maintain relevant context and avoid…
manage-project
Manage an AI-agent project from request through decomposition, preparation, routing, execution, monitoring, review, and closure using durable task records. Use…
polaris-protocol
Load for complex, multi-step, high-stakes, or long-horizon work where premature completion or goal drift is a risk.
wfgy-method
Applies WFGY (Wan Fa Gui Yi) drift control to multi-step agent work: compares each step against the stated goal, checkpoints before risky steps, and records…
multi-agent-coordinator
Orchestrates multiple parallel OpenClaw agents — tracks health, detects timeouts, reconciles conflicting outputs, and manages structured handoffs
training-mfu-calculator
Large model training MFU (Model FLOPs Utilization) calculation tool. Automatically applied when users need to calculate MFU, evaluate training efficiency, analyze model performance, or mention FLOPs, throughput, or hardware utilization. Supports Dense and MoE models and provides detailed performance analysis reports.
stakr-protocol
Interact with the Stakr protocol — ERC-4626 vaults with multi-reward staking. Use when the user or an agent needs to work with Stakr vaults, add or modify…
bggg-skill-taotie
Skill Evolver (Taotie) — Strengthens a target skill by "devouring" and analyzing the strengths of other skills. When the user wants to: integrate two skills, use one skill to optimize another, comparatively analyze the pros and cons of two skills, distill the strengths of one skill into another skill, or say "feed X to Y," "use X to optimize Y," …
planning
Planning workflows for clarifying ambiguous build requests, running spec/work-package delivery, and managing Linear lifecycle transitions.
litestream-k8s
Run SQLite with Litestream replication to S3-compatible storage (Cloudflare R2, etc.) on Kubernetes. Use when adding persistent SQLite to a containerized app,…
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or…
delegated-review-loop
Run a delegated build-review-improve loop when the user explicitly invokes this skill or explicitly asks to have sub-agents build and iteratively review the…
ccxt-rust
CCXT cryptocurrency exchange library for Rust developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to…
init-pipeline
Infrastructure skill for scaffolding pipeline enforcement into a project. Sets up Claude Code hooks (TDD classification gate, git guardrails, optional quality…
eliteforge-agent-doctor
Check whether the development environment is fully configured; if not, first confirm the Chongqing/Beijing office location, identify the current operating system, system tools, package managers, and eliteforge-* skill environment variable declarations, and report them classified as missing_required, missing_conditional, or optional_unset, then attempt to automatically install the required commands and complete hosts, Git…
wrap-up-ritual
Structured session ending ritual that captures completed work, pending tasks, and learnings before a session ends. Writes a handoff note to .claude/handoff.md…
uploadthing-elements
Install UploadThing file upload components from the Elements registry. Use when user needs file uploads, drag-and-drop dropzones, avatar uploads, file cards,…
skillkit
Local-first analytics for AI agent skills. Use when user asks about skill usage, analytics, health, context budget, cost/burn rate, trigger conflicts, dead…