Loading...
Loading...
Found 3,484 Skills
Operate `deepsky sustain` for Deepsky self-supervision. Use when the user asks the agent to keep itself alive, monitor balance or runway, inspect pricing, top up an account, retry pending top-up orders, clear auth state, or change sustain guardrails and config.
Verifies user credentials on Moca chain testnet via AIR agent sessions. Use when a user wants to verify a credential, list available verification programs, or check credential compliance.
Operates AIR agentic wallets through AIR's `/v2/wallet/agent-sign` HTTP endpoint and ERC-4337 UserOps. Use when an external agent receives an AIR handoff bundle with `userId`, `walletId`, `privyAppId`, `abstractAccountAddress`, and `airApiAgentSignUrl`, and needs to sign messages, typed data, or control the smart account onchain.
Bridge any AI agent backend to WeChat using the weixin-agent-sdk framework with simple Agent interface, login, and message loop.
Connect WeChat to AI agents (Claude, Codex, Gemini, Kimi, etc.) using the WeClaw bridge in Go.
Create or update AgentDeploy SharedInfra and Service YAML files, validate them, deploy apps with the agentdeploy CLI and Platform API, poll status and explain output, and debug structured deployment failures. Use when a user wants to deploy, redeploy, or troubleshoot an app on an AgentDeploy installation.
CLI reference for worker agents — how to claim tasks, log progress, submit for review
Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.
Decompose technical design into agent-sized implementation issues → numbered markdown files. Triggers: 'plan this,' 'break into issues,' 'create tasks,' 'ready to implement,' post-architect. Not for: designs without file paths/phases (run architect first).
Comprehensive verification with parallel test agents. Use when verifying implementations or validating changes.
Validates hook, skill, and agent counts are consistent across CLAUDE.md, hooks.json, manifests, and source directories. Use when counts may be stale after adding or removing components, before releases, or when CLAUDE.md Project Overview looks wrong.
End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.