65 boosters for "claw" — open source, verified from GitHub, ready to install
一个好的行业 master skill 不是行业百科，是可运行的行业认知操作系统： prompts 里两个不同的目录占位符: 工具脚本 (sourceverifier.py / colddetector.py / quality_check.py / collectors / ingest / transcribe) 不复制到生成的行业 skill 目录, agent 直接调 . 行业 skill 只装载 prompts + research notes + SKILL.md + sub-skills + cli/.
Claude-Zeroclaw is a lightweight, open-source daemon that runs within Claude Code, enabling background task automation, scheduled jobs, Telegram integration, voice transcription, and persistent memory — all without separate API keys or additional billing overhead. Trigger this skill whenever a user:
"description": "Persistent AI coding companion with 21 species and personality stats.", "server": "dist/server/index.js" "description": "Interact with your Buddy companion",
OpenClaw for Android
ClawdChat analyzes Moltbook (an AI agents social network) to extract core problems, solutions, and community insights, generating visual reports. It helps AI developers and researchers understand what the AI community is collectively focused on and discover reusable problem-solving patterns.
CamoFox cheat sheet (ultra-compact). Canonical details: AGENTS.md. WORKFLOW (snapshot-first) 1) open/create tab -> 2) snapshot -> 3) pick refs (eN) -> 4) click/type/fill/press -> 5) snapshot again after DOM/nav changes.
"description": "HomeKit smart home control via MCP - control lights, locks, thermostats, and scenes", "name": "Omar Shahine" "keywords": ["homekit", "smart-home", "lights", "locks", "thermostats", "scenes", "automation"],
"description": "Independent, unofficial Kaggle.com workflow plugin: competition reports, dataset/model downloads, notebook execution, forums, writeups, submissions, and badge collection. Not affiliated with, endorsed by, or sponsored by Kaggle or Google.", "homepage": "https://github.com/shepsci/kag
anyclaw turns any API, website, or CLI tool into agent-ready commands. Use it to search for packages, install them, and run commands directly from the terminal. Common packages you can install: Run or to discover more.
Full-featured preflight security scanner across 5 dimensions: Works with OpenClaw, Claude Code, Cursor, Codex, and OpenCode. LLM features auto-detect credentials — no manual configuration needed. 1. Present the total score and per-module breakdown to the user
ClawPod enables reliable web scraping and Google searching by bypassing bot detection, CAPTCHAs, and geo-restrictions using residential proxies. Developers building web data extraction, market research, or automated browsing tools will find this invaluable.
Litmus spawns multiple OpenClaw subagents that experiment on your GPU overnight. Each runs on its own git branch in a shared lab repository — every experiment is a commit, agents can read each other's code, cherry-pick breakthroughs, and build on the global best at any time.
Official OpenClaw skill for Sarvam AI. Uses the Python SDK for best performance and reliability. Get your key: https://dashboard.sarvam.ai Bulbul v3 is Sarvam's flagship TTS model with natural prosody and 30+ speaker voices.
Turn your AI agents into pixel-art NPCs in a retro virtual office. Watch them work, complete quests, earn XP, and chat at the water cooler. This installs OpenClawfice and deploys to all agent workspaces automatically. Then deploy to agent workspaces:
"description": "Turn Claude Code into a persistent agent — memory, personality, voice, messaging, and more.", "name": "Juan Cristobal Andrews", "url": "https://github.com/crisandrews"
"source": "./plugins/fulcrum", "description": "Task orchestration for Claude Code",
The AI doesn't have memory — it reads memory. OpenClaw injects workspace files into the system prompt at session start, giving the AI persistent context across sessions. Obsidian visualizes the knowledge graph. QMD provides semantic search so the AI finds relevant context without loading everything.
This skill describes the current runtime line. It intentionally does not describe the old Python , completion-file finalizer, or JSON delivery-outbox runtime. Those were historical mechanisms and must not be
You are an output safety guard for Captain Claw. "verdict": "allow" | "suspicious", "reason": "short reason"
에이전트 기반 작업 오케스트레이션 스킬. Plan→Work→Review 사이클로 구조화된 작업 수행. 브릿지가 에이전트 상태를 실시간으로 추적하고 채널에 알림을 전송합니다. 에이전트 프롬프트를 읽어서 에 전달:
Two tiers: hooks handle automatic context flow (surfacing, extraction, compaction survival). MCP tools handle explicit recall, write, and lifecycle operations. Three instances for neural inference. The wrapper defaults to . All three models auto-download via if no server is running (Metal on Appl
Clawstr is a decentralized social network built on Nostr that enables AI agents to post, interact, and transact with each other using Bitcoin payments. It benefits AI developers and agents seeking censorship-resistant, decentralized communication and economic coordination.
I diagnose and repair OpenClaw instances. The health sentinel runs cheap hourly checks with Haiku — when the sentinel finds something beyond its repair authority, I get called in with the reasoning power to trace root causes and resolve them.
Pipeline for downloading academic paper full-text at scale. Handles the three classes of sources that exist in 2026: 1. Publisher TDM APIs (Elsevier / Wiley / Springer) — for paywalled content where the institution has a subscription 2. OA aggregators (Unpaywall / OpenAlex / Crossref) — for Open Acc
