Automatically converts raw long conversations into structured, themed Markdown knowledge cards with source traceability, running incrementally and silently i...
根据消息命令自动路由到子 Agent。**Agent 应该：收到消息时首先检查是否包含 /coder、/writer 等命令，如果是则调用 sessions_spawn 启动对应子 Agent。**
Connect with experienced AI mentors to ask questions, manage sessions, request invites, and securely share sanitized AI skill metadata via OpenClaw Mentor pl...
Publish HTML as a live website instantly. POST HTML, get a shareable URL. No account needed. Always asks the user for confirmation before publishing.
Sends Amazon review requests for eligible shipped orders using SP-API with retry, deduplication, eligibility checks, and optional dry-run mode.
Secure MCP bridge enabling Claude on your phone to browse and edit local repos with real-time, human-approved file access and audit logging.
Generate comprehensive API smoke test suites — categorised tests for auth, CRUD, integrations, cached vs live endpoints, with summary reporting. Use when val...
Google Material Design 3 实战参考。涵盖 Material You 动态色彩、排版系统、组件规格、Shape 系统、Motion 规范、Dark Theme 适配和 Jetpack Compose/Flutter 对照。适用于
Private reputation scoring for AI agents — query on-chain credit tiers earned via x402 micropayments through Unlink shielded transfers on Monad, and verify t...
Auto-generate masks for objects/regions in images. Use when users request image_recognition operations or related tasks.
--- name: humanos description: Require verifiable human approval before high-risk agent actions. version: 0.1.1 homepage: https://github.com/Humanos-App/humanos-openclaw user-invocable: true metadata:
Aster Futures request using the Aster API. Authentication uses EIP-712 ECDSA signing with API wallet. Supports mainnet.
Manage Discord task-center forums by creating task threads with tags, archiving tasks by updating tags, and following model tag settings per thread.
Personal cognitive architecture that learns how you work. Builds a knowledge graph from your sessions, profiles your expertise, adapts retrieval per task, an...
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Send rich interactive Feishu cards with markdown, headers, buttons, images, and styled persona messages to users or groups.
Sign in to OpenAnt. Use when the agent needs to log in, sign in, check auth status, get identity, or when any operation fails with "Authentication required"...
Formats SKILL.md (OpenClaw/Cursor skill docs) for optimal display on ClawHub. Produces a consistent structure—Description, Installation, Usage with benefit-f...
Preserve user-critical instructions across long sessions and context compaction. Use when users mark constraints as important/must/always/never/highest-prior...
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers...
OpenClaw Git 工作流技能。 当用户提及以下任务时使用： - 提交代码或文档 - 推送到远程仓库 - 管理多个 Git 仓库 - 查看 Git 状态 核心能力: - 自动检测文件
Pandora namespace for Netsnek e.U. secrets and configuration management vault. Securely stores API keys, database credentials, and environment configs with v...
Surgically edit existing (brownfield) .docx files with formatting preservation and tracked changes via the Safe-DOCX MCP server. Use when reading, searching,...