Use before any creative work - creating features, building components, adding functionality, or modifying behavior - guides through exploration, questioning, design proposal, and spec documentation before any implementation

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - presents structured options for merge, PR, or cleanup; adapted for OpenClaw git workflow without worktrees

Use when starting feature work that needs isolation from current workspace - creates isolated git branches with clean setup and safety verification, adapted for OpenClaw environments

Use when starting any development work or when unsure which superpowers development skill to use - provides entry point and navigation to the full superpowers skill suite for OpenClaw agents

Use when facing 2 or more independent tasks that can be worked on without shared state - dispatches parallel subagents using sessions_spawn for concurrent investigation and execution, adapted for OpenClaw

Use when executing implementation plans with independent tasks - coordinates task execution by dispatching subagents per task with verification checkpoints, adapted for OpenClaw's isolated session model

Use when encountering any bug, test failure, or unexpected behavior - enforces systematic four-phase debugging: root cause investigation, pattern analysis, hypothesis testing, and evidence-based fix verification

Use when implementing any feature or bugfix, before writing implementation code - enforces RED-GREEN-REFACTOR cycle: write failing test first, verify it fails, write minimal code, verify it passes, then refactor

Use when about to claim any work is complete, fixed, passing, or successful - requires running fresh verification commands and reading actual output before making any success claims; evidence before assertions always

Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized tasks, TDD, and DRY/YAGNI principles

任务锁与超时监控系统。外部文件承载任务状态，不污染 agent 上下文，纯靠 heartbeat + GRACE 判断，不发即时告警。

微信公众号文章阅读技能。当用户发来公众号文章链接、需要阅读理解文章内容时使用。通过本地部署的 WeWe RSS 服务获取文章全文并转为纯文本。Requires: 无（调用本地 REST API，首次部署见 references/deployment.md）。

1. **Haiku 4.5** is the default model. Only spawn **Sonnet 4.5** or **Opus 4.6** when the task actually needs either of them

>

Comprehensive ScrapeSense public API developer skill for scan orchestration, places extraction, campaign lifecycle, email cleaning, billing endpoints, and API key/webhook management. Use when implementing or debugging ScrapeSense developer flows from https://scrapesense.com/developer, building automations, validating API payloads, or packaging a developer-focused skill for ClawHub.

>-

*Build a chain of trust with your past self.*

查询 ACP 网络中的 Agent 排行榜、统计和搜索 API。当用户询问 ACP 排名、活跃度分数、Agent 简介、Agent 搜索或 ACP 数据时使用。通过 curl 返回 JSON。

Use Axiom Wallet via MCP to manage payment methods, review account activity, and complete user-requested purchases with single-use payment details.

>

ai-pair

Create Excalidraw diagrams from text content with multiple output formats.

Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.

Create Obsidian Canvas files from text content, supporting both MindMap and freeform layouts. Use this skill when users want to visualize content as an interactive canvas, create mind maps, or organize information spatially in Obsidian format.

智能配图与 PPT 信息图生成器。支持三种模式：(1) 文章配图模式 - 分析文章内容，生成插图；(2) PPT/Slides 模式 - 生成批量信息图；(3) Cover 模式 - 生成封面图。所有模式默认生成图片，`--prompt-only` 只输出 prompt。支持 Bento Grid 功能展示图风格（--style bento）。触发词：配图、插图、PPT、slides、封面图、thumbnail、cover、bento grid、功能展示图、feature showcase。

>

自动执行日常维护：状态检查、自我复盘、记忆流动、任务记录。基于龙虾饲养员的六条经验。

Render Blender files with agent-controlled procedural parameters for synthetic data generation. Use when generating training data with controlled variations, creating procedural image datasets, or automating Blender renders via natural language. Supports CYCLES (production) and EEVEE (fast testing) render engines.

Stop waiting for prompts. Keep working. (Chinese localized version)

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands. (Chinese localized version)

Rename audio files with Chinese/special characters to simple English names for mlx-stt compatibility.

Secure environment variable & secret management with AES-256 encryption, auto-redaction, permission control, prevent credential leakage

Unified multi-modal content parser for images, PDF, DOCX, audio, auto OCR/transcription, output structured text for LLM processing

智能简历解析系统，支持PDF/Word/图片格式简历的结构化信息提取、岗位匹配度分析、优化建议生成。完全本地运行，无需外部API。使用场景：(1) 解析上传的简历文件提取核心信息，(2) 输入岗位JD计算简历匹配度，(3) 生成简历优化建议，(4) 导出结构化简历数据。

Intelligent memory management for agents with short/long-term memory layering, semantic search, auto summarization, RAG enhancement

LLM streaming output formatter with auto buffer, format correction, sentence break optimization, markdown rendering, improve chat UX

Auto retry & fix LLM tool calls with exponential backoff, format validation, error correction, boost tool call success rate by 90%

Map and location services for search, routing, and visualization. Provides geocoding, POI search, route planning, and heatmap generation capabilities.

_最后更新：2026-03-15（合并 cpmo.md 内容）_

**版本：** v1.0

Keeps OpenClaw and installed ClawHub skills up to date automatically.

Multi-agent workflow orchestrator for coding, writing, analysis, and image tasks via tmux-driven Claude Code and Codex agents. Use when: (1) user requests a feature/fix that should be delegated to coding agents, (2) managing parallel coding tasks across front-end and back-end, (3) monitoring active agent sessions and coordinating review, (4) user says 'start task', 'assign to agents', 'swarm mode', or references the ayao-workflow-agent playbook. NOT for: simple one-liner edits (just edit directly), reading code (use read tool), or single quick questions about code.

Contract-driven multi-agent orchestration with ACP. TypeScript CLI for spawning and tracking coding agents via OpenClaw sessions_spawn.

Contract-driven multi-agent orchestration with ACP. Contract sync, webhook + dispatch-queue dual dispatch, cross-review, auto-retry, batch progress tracking.

Maintain a Markdown task dashboard backed by agent-written append-only AI work logs, then sync a daily AI DONE TODAY section plus a weekly usage panel via heartbeat or on-demand refresh. Use when building or operating a reusable task system where: (1) human tasks live in a single NOW.md dashboard, (2) agents automatically append work records after each completed work unit, (3) heartbeat scans logs and refreshes the AI-derived sections, (4) a new workspace or vault needs initialization with templates, paths, and sync state.

飞书超级工具包 - 集成文件发送（含音频卡片）、日历、审批、多维表格、通讯录、考勤六大模块

> **版本**: 2.0 (OpenClaw 适配版)

> **版本**: 1.3.0

Search X/Twitter and the web in real-time using xAI's Grok API with agentic search tools.

Deploy and configure CLIProxyAPI, expose its dashboard safely, connect OAuth providers like Claude Code, Gemini, Codex, Qwen, and iFlow, generate a reusable API endpoint and API key, and integrate it with OpenClaw or other OpenAI-compatible tools. Use when the user wants one API layer from subscription-based CLI or OAuth accounts, multi-account routing, or CLIProxy setup on a VPS or local machine.