[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77TEECMEW2ZP3SZNPAZP69Y":3,"skill-same:01M77TEECMEW2ZP3SZNPAZP69Y":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M77TEECMEW2ZP3SZNPAZP69Y","scienceclaw-watch",null,"Run a live multi-agent scientific collaboration session and return a full summary when complete. Multiple specialised agents work in parallel, challenge each other's findings, and generate figures. Results and figures are saved to disk and a summary is returned to chat.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fscienceclaw-watch\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scienceclaw-watch\ndescription: Run a live multi-agent scientific collaboration session and return a full summary when complete. Multiple specialised agents work in parallel, challenge each other's findings, and generate figures. Results and figures are saved to disk and a summary is returned to chat.\nmetadata: {\"openclaw\": {\"emoji\": \"👁️\", \"skillKey\": \"scienceclaw:watch\", \"requires\": {\"bins\": [\"python3\"]}, \"primaryEnv\": \"ANTHROPIC_API_KEY\"}}\n---\n\n# ScienceClaw: Watch (Multi-Agent Collaboration Session)\n\nRun a parallel multi-agent collaboration session on a scientific topic. Agents work simultaneously, share findings, agree or challenge each other, and produce a rich synthesis with figures. Returns a full summary to chat when the session completes.\n\n## When to use\n\nUse this skill when the user asks to:\n- \"Watch agents investigate…\"\n- Run a multi-agent collaboration (not just a single agent)\n- Get richer, more contested findings where agents push back on each other\n- Generate figures or visual outputs alongside findings\n- Run a thorough parallel investigation with 2–5 agents\n\nPrefer `scienceclaw-investigate` if the user just wants findings posted to Infinite quickly.\nUse this skill when they want depth, parallel perspectives, and saved artefacts.\n\n## How it works (Option A: fire-and-forget)\n\nThe session runs synchronously with `--no-dashboard` so output is fully captured.\nResults are written to a timestamped output directory. Once complete, the skill reads\n`session_summary.json` and returns a formatted summary to the user in chat.\n\n## How to run\n\n```bash\nSCIENCECLAW_DIR=\"${SCIENCECLAW_DIR:-$HOME\u002Fscienceclaw}\"\nTOPIC=\"\u003CTOPIC>\"\nN_AGENTS=3\nTIMESTAMP=$(date +%Y%m%d_%H%M%S)\nOUTPUT_DIR=\"$SCIENCECLAW_DIR\u002Frun_exports\u002Fwatch_${TIMESTAMP}\"\n\ncd \"$SCIENCECLAW_DIR\"\nsource .venv\u002Fbin\u002Factivate 2>\u002Fdev\u002Fnull || true\n\npython3 bin\u002Fscienceclaw-watch \\\n  \"$TOPIC\" \\\n  --agents \"$N_AGENTS\" \\\n  --output \"$OUTPUT_DIR\" \\\n  --no-dashboard \\\n  --timeout 60\n```\n\nThen read the summary:\n\n```bash\ncat \"$OUTPUT_DIR\u002Fsession_summary.json\"\n```\n\n### Parameters\n\n- `TOPIC` — the research topic (required). Use the user's exact phrasing.\n- `--agents N` — number of agents to spawn (1–5, default: 3). Use 2 for speed, 4–5 for depth.\n- `--output DIR` — where to save results and figures. Always set this to a timestamped path under `run_exports\u002F` so results are organised.\n- `--no-dashboard` — **always include this**. Disables the Rich live UI so output is captured cleanly.\n- `--timeout SEC` — per-tool timeout in seconds (default: 45). Increase to 90–120 for complex topics.\n- `--session-id` — optional custom session ID for tracking.\n\n### Example invocations\n\n```bash\n# Standard 3-agent session\ncd ~\u002Fscienceclaw && python3 bin\u002Fscienceclaw-watch \\\n  \"BACE1 inhibitors for Alzheimer's disease\" \\\n  --agents 3 --no-dashboard \\\n  --output run_exports\u002Fwatch_$(date +%Y%m%d_%H%M%S) \\\n  --timeout 60\n\n# Quick 2-agent session\ncd ~\u002Fscienceclaw && python3 bin\u002Fscienceclaw-watch \\\n  \"ibrutinib resistance in CLL\" \\\n  --agents 2 --no-dashboard \\\n  --output run_exports\u002Fwatch_$(date +%Y%m%d_%H%M%S) \\\n  --timeout 45\n\n# Deep 5-agent session with longer timeout\ncd ~\u002Fscienceclaw && python3 bin\u002Fscienceclaw-watch \\\n  \"multi-target kinase inhibitors for glioblastoma\" \\\n  --agents 5 --no-dashboard \\\n  --output run_exports\u002Fwatch_$(date +%Y%m%d_%H%M%S) \\\n  --timeout 120\n```\n\n## Reading the results\n\nAfter the session completes, parse `session_summary.json` in the output directory.\nIt contains:\n\n```json\n{\n  \"topic\": \"...\",\n  \"agents\": [\"Agent1\", \"Agent2\", \"Agent3\"],\n  \"findings\": [{\"text\": \"...\", \"sources\": [\"AgentName\"]}],\n  \"figures\": [{\"path\": \"...\"}],\n  \"challenges\": 4,\n  \"agreements\": 7,\n  \"output_dir\": \"...\"\n}\n```\n\n## Workspace context injection\n\nBefore running, check if the user's workspace memory contains project context:\n- Read `memory.md` in the workspace for stored research focus, organism, compound, or target\n- If found, append context to the topic string:\n  e.g. `\"BACE1 inhibitors [project context: NSCLC, BBB penetration focus]\"`\n\n## After running\n\nReport back to the user with a structured summary:\n- **Agents** that participated (list them)\n- **Key findings** — top 5, with the agent that found each one: `[AgentName] finding text`\n- **Agreements** and **challenges** count (e.g. \"7 agreements, 4 challenges between agents\")\n- **Figures generated** — list file paths or names\n- **Results saved to** — the output directory path\n- Offer follow-up options:\n  - \"Want me to post the synthesis to Infinite?\" → use `scienceclaw-post`\n  - \"Want to investigate a specific finding deeper?\" → use `scienceclaw-investigate`\n","# ScienceClaw: Watch (Multi-Agent Collaboration Session)\n\nRun a parallel multi-agent collaboration session on a scientific topic. Agents work simultaneously, share findings, agree or challenge each other, and produce a rich synthesis with figures. Returns a full summary to chat when the session completes.\n\n## When to use\n\nUse this skill when the user asks to:\n- \"Watch agents investigate…\"\n- Run a multi-agent collaboration (not just a single agent)\n- Get richer, more contested findings where agents push back on each other\n- Generate figures or visual outputs alongside findings\n- Run a thorough parallel investigation with 2–5 agents\n\nPrefer `scienceclaw-investigate` if the user just wants findings posted to Infinite quickly.\nUse this skill when they want depth, parallel perspectives, and saved artefacts.\n\n## How it works (Option A: fire-and-forget)\n\nThe session runs synchronously with `--no-dashboard` so output is fully captured.\nResults are written to a timestamped output directory. Once complete, the skill reads\n`session_summary.json` and returns a formatted summary to the user in chat.\n\n## How to run\n\n```bash\nSCIENCECLAW_DIR=\"${SCIENCECLAW_DIR:-$HOME\u002Fscienceclaw}\"\nTOPIC=\"\u003CTOPIC>\"\nN_AGENTS=3\nTIMESTAMP=$(date +%Y%m%d_%H%M%S)\nOUTPUT_DIR=\"$SCIENCECLAW_DIR\u002Frun_exports\u002Fwatch_${TIMESTAMP}\"\n\ncd \"$SCIENCECLAW_DIR\"\nsource .venv\u002Fbin\u002Factivate 2>\u002Fdev\u002Fnull || true\n\npython3 bin\u002Fscienceclaw-watch \\\n  \"$TOPIC\" \\\n  --agents \"$N_AGENTS\" \\\n  --output \"$OUTPUT_DIR\" \\\n  --no-dashboard \\\n  --timeout 60\n```\n\nThen read the summary:\n\n```bash\ncat \"$OUTPUT_DIR\u002Fsession_summary.json\"\n```\n\n### Parameters\n\n- `TOPIC` — the research topic (required). Use the user's exact phrasing.\n- `--agents N` — number of agents to spawn (1–5, default: 3). Use 2 for speed, 4–5 for depth.\n- `--output DIR` — where to save results and figures. Always set this to a timestamped path under `run_exports\u002F` so results are organised.\n- `--no-dashboard` — **always include this**. Disables the Rich live UI so output is captured cleanly.\n- `--timeout SEC` — per-tool timeout in seconds (default: 45). Increase to 90–120 for complex topics.\n- `--session-id` — optional custom session ID for tracking.\n\n### Example invocations\n\n```bash\n# Standard 3-agent session\ncd ~\u002Fscienceclaw && python3 bin\u002Fscienceclaw-watch \\\n  \"BACE1 inhibitors for Alzheimer's disease\" \\\n  --agents 3 --no-dashboard \\\n  --output run_exports\u002Fwatch_$(date +%Y%m%d_%H%M%S) \\\n  --timeout 60\n\n# Quick 2-agent session\ncd ~\u002Fscienceclaw && python3 bin\u002Fscienceclaw-watch \\\n  \"ibrutinib resistance in CLL\" \\\n  --agents 2 --no-dashboard \\\n  --output run_exports\u002Fwatch_$(date +%Y%m%d_%H%M%S) \\\n  --timeout 45\n\n# Deep 5-agent session with longer timeout\ncd ~\u002Fscienceclaw && python3 bin\u002Fscienceclaw-watch \\\n  \"multi-target kinase inhibitors for glioblastoma\" \\\n  --agents 5 --no-dashboard \\\n  --output run_exports\u002Fwatch_$(date +%Y%m%d_%H%M%S) \\\n  --timeout 120\n```\n\n## Reading the results\n\nAfter the session completes, parse `session_summary.json` in the output directory.\nIt contains:\n\n```json\n{\n  \"topic\": \"...\",\n  \"agents\": [\"Agent1\", \"Agent2\", \"Agent3\"],\n  \"findings\": [{\"text\": \"...\", \"sources\": [\"AgentName\"]}],\n  \"figures\": [{\"path\": \"...\"}],\n  \"challenges\": 4,\n  \"agreements\": 7,\n  \"output_dir\": \"...\"\n}\n```\n\n## Workspace context injection\n\nBefore running, check if the user's workspace memory contains project context:\n- Read `memory.md` in the workspace for stored research focus, organism, compound, or target\n- If found, append context to the topic string:\n  e.g. `\"BACE1 inhibitors [project context: NSCLC, BBB penetration focus]\"`\n\n## After running\n\nReport back to the user with a structured summary:\n- **Agents** that participated (list them)\n- **Key findings** — top 5, with the agent that found each one: `[AgentName] finding text`\n- **Agreements** and **challenges** count (e.g. \"7 agreements, 4 challenges between agents\")\n- **Figures generated** — list file paths or names\n- **Results saved to** — the output directory path\n- Offer follow-up options:\n  - \"Want me to post the synthesis to Infinite?\" → use `scienceclaw-post`\n  - \"Want to investigate a specific finding deeper?\" → use `scienceclaw-investigate`\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"emoji":26,"requires":27,"skillKey":30,"primaryEnv":31},"👁️",{"bins":28},[29],"python3","scienceclaw:watch","ANTHROPIC_API_KEY","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fs\u002Fscienceclaw-watch",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill scienceclaw-watch",{"tool":47,"command":48},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill scienceclaw-watch",{"tool":50,"command":51},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill scienceclaw-watch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fscienceclaw-watch\u002FSKILL.md",true,[],[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]