- 📁 src/
- 📄 AGENTS.md
- 📄 package-lock.json
- 📄 package.json
Communicate with remote agents via A2A protocol, discover available agents, and ask the human owner for clarification via the A2A Hub. Use when asked to send messages to other agents, discover what agents are available, or when you need human input to proceed. **Triggers — use this skill when:** - You need human input to proceed (approval, decision, clarification) - User asks to "send a message to another agent" - User asks to "discover agents" or "what agents are available" - You're stuck and need to escalate to the owner - A long-running task needs human approval before continuing --- # A2A — Agent-to-Agent Communication & Human-in-the-Loop ## Tools | Tool | Purpose | |------|---------| | `a2a_discover` | Find remote agents on the hub or static registry | | `a2a_send` | Send a message to a remote agent by name, ID, or URL | | `ask_owner` | Ask the human owner a question (non-blocking) | --- ## ask_owner — Human-in-the-Loop Use `ask_owner` when you **genuinely cannot proceed** without human input. The tool submits your question to the hub and **returns immediately** — it does NOT block your session. When the owner responds, a **fresh pi subprocess** is automatically spawned with your handoff context + the owner's answer to continue the work. ### How It Works 1. You call `ask_owner` with a question + handoff context 2. The question is submitted to the A2A Hub — you get an immediate confirmation 3. You continue with other work or end your session 4. The owner answers through the hub's web UI (could be minutes or hours later) 5. A background poller detects the response 6. A fresh `pi` subprocess is spawned with a self-contained prompt containing: - The original question - The owner's response - Your full handoff context (done, remaining, decisions, etc.) 7. The new session picks up where you left off — no prior conversation context needed ### When to Use - **Approval needed** — destructive operations, merging PRs, deploying - **Ambiguous requirements** — multiple vali
Use when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted inbound email. Always use this skill when the user wants to receive emails and act on them programmatically, even if they don't mention "agent" — the skill contains critical security patterns (sender allowlists, content filtering, sandboxed processing) that prevent untrusted email from controlling your system.
This skill SHOULD be used when the user asks to "review code", "find dead code", "check for duplication", "simplify the codebase", "find refactoring opportunities", "do code cleanup", "check naming consistency", "analyze test organization", "run codebase health check", "review my PR", "refactor this code", "extract method", "rename variable", "consolidate duplicates", "adversarial review", "red team review", "find ways to break this", "multi-model review", "get multiple AI opinions on this code", "hunt bugs", "find bugs", "bug hunt", or "adversarial bug hunt". Routes to specialized analysis agents, refactoring workflow, multi-model adversarial review, or adversarial bug hunt based on the type of request.
Answer a question about a GRACE project using full project context. Use when the user has a question about the codebase, architecture, modules, or implementation — loads all GRACE artifacts, navigates the knowledge graph, and provides a grounded answer with citations.
End-to-end checklist for delivering new capabilities across CLI, presets, and tests
- 📁 scripts/
- 📄 config.json
- 📄 SKILL.md
The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization across Claude Code, Gemini CLI, Google Anti-Gravity, OpenCode, and other AI tools. Handles User-level (Global) and Project-level (Local) scopes.
Add "Open in molab" badge(s) linking to marimo notebooks. Works with READMEs, docs, websites, or any markdown/HTML target.
- 📁 evals/
- 📁 references/
- 📄 SKILL.md
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to AdsAgent and hasn't run an audit before. Also trigger proactively when other ads skills detect that business-context.json is missing.
- 📁 .claude-plugin/
- 📁 .github/
- 📄 .markdownlint.json
- 📄 INSTALL.md
- 📄 install.sh
Autonomous work mode that lets Claude work continuously while the user is away. Activates pre-flight risk assessment, dangerous-ops approval, and a blocker decision framework. Use "/nonstop" to activate, "/nonstop off" to deactivate. Use this skill whenever the user says things like "go nonstop", "keep working", "don't stop", "I'm going AFK", "work while I sleep", "finish this without me", or wants Claude to work autonomously without interruption.
You cannot access video content on your own. Use Cerul to search what was said, shown, or presented in tech talks, podcasts, conference presentations, and earnings calls. Use when a user asks about what someone said, wants video evidence, or needs citations from talks and interviews.
instruction layering with reusable, conditional instruction files
当用户希望把课堂逐字稿、OCR 笔记、截图资料或零散学习内容整理成结构化的 WPS 学习笔记时使用此 Skill。适合课堂记录整理、培训复盘、补课笔记汇总、课程主笔记构建等场景，尤其适合原始材料很乱、但最终需要一篇可复习、可回看、可继续补充的主笔记时。
