All Skills
Filter by source, category, or keyword. Read the internal summary first — then decide if the original page is worth your time.
Read first. Jump out only when you're ready.
Internal summaries, source signals, and category context — all in one place. Open the original listing only when you already know why it's worth your time.
AI · Tencent SkillHub
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Best for broad discovery and market coverage, then narrow down using category and source signal.
2619 skills
Click any card to read internal detail before jumping to source.
Continuity Framework
Asynchronous reflection and memory integration for genuine AI development. Use on heartbeat to reflect on recent sessions, extract structured memories with confidence scores, generate follow-up questions, and surface those questions when the user returns. Transforms passive logging into active development.
Contract Review
Legal contract analysis using CUAD dataset (41 risk categories). Supports NDA, SaaS, M&A, employment, payment/merchant, and finder/broker agreements. Identif...
Convex
Build and maintain Convex backends with schema-safe modeling, query and mutation patterns, auth guards, and production rollout checks.
Copilot Money Skill
Query Copilot Money personal finance data (accounts, transactions, net worth, holdings, asset allocation) and refresh bank connections. Use when the user asks about finances, account balances, recent transactions, net worth, investment allocation, or wants to sync/refresh bank data.
CopilotKit-Runtime-Patterns
Server-side runtime patterns for CopilotKit. Use when setting up CopilotKit runtime endpoints (Express, Hono, Next.js), configuring remote agent endpoints, a...
CopilotKit-agent-patterns
Patterns for building AI agents that integrate with CopilotKit. Use when designing agent architecture, implementing AG-UI event streaming, managing shared st...
Cord Trees
Dynamic task tree orchestration inspired by Cord protocol. Agent builds its own coordination tree at runtime — deciding decomposition, parallelism, and depen...
Core Prompt Patcher
Automatically reinjects the V-ULTIMATE persona into OpenClaw's core system prompt after updates or reinstallations to maintain custom behavior.
Correction Memory
Makes agent corrections persistent and reusable. When you override, reject, or correct an agent's output, this skill logs the correction and automatically in...
Cortex Protocol
Register your agent on Cortex Protocol — gasless on-chain identity (ERC-8004) on Base. One command to get a verifiable agent identity.
Cosmos
Assist with Cosmos ATOM transactions, IBC transfers, staking, and cross-chain ecosystem navigation.
Cost Prediction
Predict construction project costs using Machine Learning. Use Linear Regression, K-Nearest Neighbors, and Random Forest models on historical project data. Train, evaluate, and deploy cost prediction models.
Cost Tracker
AI spending monitor — track costs across OpenRouter models with daily, weekly, and monthly reports. Budget limits with alerts, per-model analysis, savings re...
CosyVoice3 macOS
Local text-to-speech using Alibaba's CosyVoice3 on macOS Apple Silicon. Supports Chinese, English, Japanese, Korean, and 18+ Chinese dialects. Provides zero-...
Council
Send an idea to the Council of the Wise for multi-perspective feedback. Spawns sub-agents to analyze from multiple expert perspectives. Auto-discovers agent...
Council Builder
Build a personalized team of AI agent personas for OpenClaw. Interviews the user, analyzes their workflow, then creates specialized agents with distinct pers...
Counterclaw Core
Defensive interceptor for prompt injection and basic PII masking.
Cpppselfimprovingagent123123
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
CrabPath
Memory graph engine with caller-provided embed and LLM callbacks; core is pure, with real-time correction flow and optional OpenAI integration.
CrabPet
AI pet companion — a pixel lobster that grows from your OpenClaw usage. Use when user mentions pet, crabpet, lobster pet, my crab, pet status, pet card, pet...
Crabwalk
Real-time companion monitor for OpenClaw agents
Crabwalk
Real-time companion monitor for OpenClaw agents
Craftwork
9 engineering disciplines for AI agents — TDD, debugging, code review, planning, and multi-agent coordination. Build software like it matters.
Crash Fixer
Autonomous crash analysis and bug fixing. Monitors crash reports from Cloudflare D1, deduplicates, analyzes with Codex 5.3 High, generates fixes, and creates...