{ "schemaVersion": "1.0", "item": { "slug": "claw-clawbridge", "name": "ClawBridge - Find Connections", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/moltlife/claw-clawbridge", "canonicalUrl": "https://clawhub.ai/moltlife/claw-clawbridge", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/claw-clawbridge", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=claw-clawbridge", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "schema/connection_brief.json", "venues/moltbook.md", "venues/communities.md", "venues/web.md", "package.json" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/claw-clawbridge" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/claw-clawbridge", "agentPageUrl": "https://openagent3.xyz/skills/claw-clawbridge/agent", "manifestUrl": "https://openagent3.xyz/skills/claw-clawbridge/agent.json", "briefUrl": "https://openagent3.xyz/skills/claw-clawbridge/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "claw-clawbridge", "body": "The Intelligent Connection Bridge: A high-signal scouting agent that runs nightly to bridge you with the right people." }, { "title": "Overview", "body": "Clawbridge transforms a simple human prompt into a persistent, nightly scouting operation. It doesn't just find leads; it builds a bridge between your goals and the people who can help you achieve them.\n\nHuman Intent: You define what you offer and who you're looking for once.\nNightly Scouting: Every night, the agent scours Moltbook, professional communities, and the open web.\nSmart Matching: It filters and ranks candidates based on intent signals, credibility, and recent activity.\nConnection Brief: It delivers a daily \"Connection Brief\" with evidence-backed matches and personalized outreach drafts.\nHuman-in-the-Loop: You review the matches and decide whether to approach, maintaining full control over the final \"bridge.\"" }, { "title": "Via ClawHub (Recommended)", "body": "# Install the ClawHub CLI\nnpm install -g clawhub\n\n# Install this skill\nclawhub install claw-clawbridge" }, { "title": "Via Legacy clawdbot CLI", "body": "# From registry\nclawdbot skills install claw-clawbridge\n\n# From GitHub\nclawdbot skills install github:YOUR_USERNAME/clawbridge-skill" }, { "title": "Manual", "body": "Clone and copy to your OpenClaw workspace:\n\ngit clone https://github.com/YOUR_USERNAME/clawbridge-skill.git ~/.openclaw/workspace/skills/claw-clawbridge\nopenclaw gateway restart" }, { "title": "Inputs", "body": "The skill requires the following inputs:" }, { "title": "1. Project Profile (required)", "body": "offer: \"What your agency/company offers\"\nask: \"What you want (partners, clients, co-marketing, advisors)\"\nideal_persona: \"Exact target persona(s)\"\nverticals:\n - \"keyword1\"\n - \"keyword2\"\n - \"keyword3\"\ngeo_timezone: \"optional - geographic/timezone preferences\"\ndisallowed:\n - \"do not contact constraints\"\ntone: \"Short style guidance for draft messages\"" }, { "title": "2. Constraints (optional)", "body": "no_spam_rules:\n - \"No cold outreach to competitors\"\n - \"Respect unsubscribe requests\"\nregions:\n - \"US\"\n - \"EU\"\navoid_list:\n - \"competitor@example.com\"\n - \"@spam_account\"" }, { "title": "3. Targets (optional)", "body": "venues:\n - \"moltbook\"\n - \"web\"\n - \"communities\"\nquery_templates:\n - \"{vertical} + hiring + partner\"\n - \"{vertical} + looking for + {ask}\"" }, { "title": "4. Run Budget (optional)", "body": "max_searches: 20\nmax_fetches: 50\nmax_minutes: 10" }, { "title": "Tools Used", "body": "This skill uses the following OpenClaw tools:\n\nToolPurposeWhen Usedweb_searchDiscover candidate pagesFast venue scanningweb_fetchExtract page contentReading candidate profilesbrowserJS-heavy sitesOnly when fetch fails" }, { "title": "Security Requirements", "body": "⚠️ MUST follow these security defaults:\n\nKeep secrets out of prompts - Pass via env/config only\nUse strict tool allowlists - Only enable web_* tools when actively scouting\nHuman-in-the-loop - NEVER auto-send outreach in MVP\nRate limiting - Respect run budget constraints\nAvoid list enforcement - Never contact entries in avoid_list" }, { "title": "Execution Flow", "body": "┌─────────────────────────────────────────────────────────────────┐\n│ DISCOVERY PHASE │\n│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │\n│ │web_search│───▶│ Filter │───▶│ Dedupe │ │\n│ │ (venues) │ │ Results │ │ & Queue │ │\n│ └──────────┘ └──────────┘ └──────────┘ │\n└─────────────────────────────────────────────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────────────────────────────┐\n│ ENRICHMENT PHASE │\n│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │\n│ │web_fetch │───▶│ Extract │───▶│ Validate │ │\n│ │ (pages) │ │ Signals │ │ Evidence │ │\n│ └──────────┘ └──────────┘ └──────────┘ │\n└─────────────────────────────────────────────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────────────────────────────┐\n│ RANKING PHASE │\n│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │\n│ │ Score │───▶│ Rank │───▶│ Top K │ │\n│ │ Heuristic│ │ Sort │ │ Selection│ │\n│ └──────────┘ └──────────┘ └──────────┘ │\n└─────────────────────────────────────────────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────────────────────────────┐\n│ DRAFTING PHASE │\n│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │\n│ │ Draft │───▶│ Review │───▶│ Output │ │\n│ │ Messages │ │ Tone │ │ Brief │ │\n│ └──────────┘ └──────────┘ └──────────┘ │\n└─────────────────────────────────────────────────────────────────┘" }, { "title": "Output", "body": "The skill outputs a Connection Brief in two formats:" }, { "title": "1. Structured JSON (run.json)", "body": "See schema/connection_brief.json for the full schema." }, { "title": "2. Human-Readable Markdown (run.md)", "body": "See examples/sample_run.md for a sample report." }, { "title": "Hard Requirements (discard if missing)", "body": "✅ At least 2 evidence URLs per candidate\n✅ Clear reason mapping to your ask\n✅ Last activity within N days (configurable, default 30)" }, { "title": "Risk Flags", "body": "Candidates are flagged if they exhibit:\n\n🟡 low_evidence - Fewer than expected signals\n🟡 spammy_language - Promotional or suspicious content\n🟡 unclear_identity - Cannot verify who they are\n🟡 too_salesy - Overly promotional content\n🟡 irrelevant - Weak connection to your ask" }, { "title": "Ranking Heuristic (v1)", "body": "Each candidate is scored on:\n\nFactorWeightDescriptionRelevance30%Match to keywords + askIntent25%Actively building/hiring/seekingCredibility20%Consistent footprint across sourcesRecency15%Recent activity signalsEngagement10%Mutual interests/communities\n\nOutput: Top K candidates (default K=3, configurable 5-10)" }, { "title": "Examples", "body": "See the examples/ directory for:\n\nsample_run.json - Full JSON output example\nsample_run.md - Human-readable report example" }, { "title": "Prompts", "body": "The skill uses modular prompts located in prompts/:\n\ndiscovery.md - How to search for candidates\nfiltering.md - How to apply hard requirements\nranking.md - How to score and rank candidates\ndrafting.md - How to write outreach messages" }, { "title": "Venues", "body": "Venue-specific search strategies are in venues/:\n\nmoltbook.md - Moltbook platform scouting\nweb.md - General web search strategies\ncommunities.md - Community/forum discovery" }, { "title": "Environment Variables", "body": "# Optional: Override defaults\nCLAWBRIDGE_TOP_K=5 # Number of candidates to return\nCLAWBRIDGE_RECENCY_DAYS=30 # Activity recency threshold\nCLAWBRIDGE_MAX_SEARCHES=20 # Max search queries per run\nCLAWBRIDGE_MAX_FETCHES=50 # Max page fetches per run" }, { "title": "Workspace Configuration", "body": "The skill reads workspace config from the runner or vault:\n\nworkspace_id: \"ws_abc123\"\nworkspace_token: \"tok_...\" # For vault uploads\ndelivery_target: \"discord\" # or \"slack\" or \"email\"" }, { "title": "License", "body": "MIT License - See LICENSE file for details." }, { "title": "Contributing", "body": "Contributions welcome! Please read the prompts carefully and ensure any changes maintain:\n\nDeterministic output schema\nNo secrets in prompts\nHuman-in-the-loop requirement\nEvidence-based candidate selection" } ], "body": "claw-clawbridge\n\nThe Intelligent Connection Bridge: A high-signal scouting agent that runs nightly to bridge you with the right people.\n\nOverview\n\nClawbridge transforms a simple human prompt into a persistent, nightly scouting operation. It doesn't just find leads; it builds a bridge between your goals and the people who can help you achieve them.\n\nHuman Intent: You define what you offer and who you're looking for once.\nNightly Scouting: Every night, the agent scours Moltbook, professional communities, and the open web.\nSmart Matching: It filters and ranks candidates based on intent signals, credibility, and recent activity.\nConnection Brief: It delivers a daily \"Connection Brief\" with evidence-backed matches and personalized outreach drafts.\nHuman-in-the-Loop: You review the matches and decide whether to approach, maintaining full control over the final \"bridge.\"\nInstallation\nVia ClawHub (Recommended)\n# Install the ClawHub CLI\nnpm install -g clawhub\n\n# Install this skill\nclawhub install claw-clawbridge\n\nVia Legacy clawdbot CLI\n# From registry\nclawdbot skills install claw-clawbridge\n\n# From GitHub\nclawdbot skills install github:YOUR_USERNAME/clawbridge-skill\n\nManual\n\nClone and copy to your OpenClaw workspace:\n\ngit clone https://github.com/YOUR_USERNAME/clawbridge-skill.git ~/.openclaw/workspace/skills/claw-clawbridge\nopenclaw gateway restart\n\nInputs\n\nThe skill requires the following inputs:\n\n1. Project Profile (required)\noffer: \"What your agency/company offers\"\nask: \"What you want (partners, clients, co-marketing, advisors)\"\nideal_persona: \"Exact target persona(s)\"\nverticals:\n - \"keyword1\"\n - \"keyword2\"\n - \"keyword3\"\ngeo_timezone: \"optional - geographic/timezone preferences\"\ndisallowed:\n - \"do not contact constraints\"\ntone: \"Short style guidance for draft messages\"\n\n2. Constraints (optional)\nno_spam_rules:\n - \"No cold outreach to competitors\"\n - \"Respect unsubscribe requests\"\nregions:\n - \"US\"\n - \"EU\"\navoid_list:\n - \"competitor@example.com\"\n - \"@spam_account\"\n\n3. Targets (optional)\nvenues:\n - \"moltbook\"\n - \"web\"\n - \"communities\"\nquery_templates:\n - \"{vertical} + hiring + partner\"\n - \"{vertical} + looking for + {ask}\"\n\n4. Run Budget (optional)\nmax_searches: 20\nmax_fetches: 50\nmax_minutes: 10\n\nTools Used\n\nThis skill uses the following OpenClaw tools:\n\nTool\tPurpose\tWhen Used\nweb_search\tDiscover candidate pages\tFast venue scanning\nweb_fetch\tExtract page content\tReading candidate profiles\nbrowser\tJS-heavy sites\tOnly when fetch fails\nSecurity Requirements\n\n⚠️ MUST follow these security defaults:\n\nKeep secrets out of prompts - Pass via env/config only\nUse strict tool allowlists - Only enable web_* tools when actively scouting\nHuman-in-the-loop - NEVER auto-send outreach in MVP\nRate limiting - Respect run budget constraints\nAvoid list enforcement - Never contact entries in avoid_list\nExecution Flow\n┌─────────────────────────────────────────────────────────────────┐\n│ DISCOVERY PHASE │\n│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │\n│ │web_search│───▶│ Filter │───▶│ Dedupe │ │\n│ │ (venues) │ │ Results │ │ & Queue │ │\n│ └──────────┘ └──────────┘ └──────────┘ │\n└─────────────────────────────────────────────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────────────────────────────┐\n│ ENRICHMENT PHASE │\n│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │\n│ │web_fetch │───▶│ Extract │───▶│ Validate │ │\n│ │ (pages) │ │ Signals │ │ Evidence │ │\n│ └──────────┘ └──────────┘ └──────────┘ │\n└─────────────────────────────────────────────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────────────────────────────┐\n│ RANKING PHASE │\n│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │\n│ │ Score │───▶│ Rank │───▶│ Top K │ │\n│ │ Heuristic│ │ Sort │ │ Selection│ │\n│ └──────────┘ └──────────┘ └──────────┘ │\n└─────────────────────────────────────────────────────────────────┘\n │\n ▼\n┌─────────────────────────────────────────────────────────────────┐\n│ DRAFTING PHASE │\n│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │\n│ │ Draft │───▶│ Review │───▶│ Output │ │\n│ │ Messages │ │ Tone │ │ Brief │ │\n│ └──────────┘ └──────────┘ └──────────┘ │\n└─────────────────────────────────────────────────────────────────┘\n\nOutput\n\nThe skill outputs a Connection Brief in two formats:\n\n1. Structured JSON (run.json)\n\nSee schema/connection_brief.json for the full schema.\n\n2. Human-Readable Markdown (run.md)\n\nSee examples/sample_run.md for a sample report.\n\nCandidate Selection Rules\nHard Requirements (discard if missing)\n✅ At least 2 evidence URLs per candidate\n✅ Clear reason mapping to your ask\n✅ Last activity within N days (configurable, default 30)\nRisk Flags\n\nCandidates are flagged if they exhibit:\n\n🟡 low_evidence - Fewer than expected signals\n🟡 spammy_language - Promotional or suspicious content\n🟡 unclear_identity - Cannot verify who they are\n🟡 too_salesy - Overly promotional content\n🟡 irrelevant - Weak connection to your ask\nRanking Heuristic (v1)\n\nEach candidate is scored on:\n\nFactor\tWeight\tDescription\nRelevance\t30%\tMatch to keywords + ask\nIntent\t25%\tActively building/hiring/seeking\nCredibility\t20%\tConsistent footprint across sources\nRecency\t15%\tRecent activity signals\nEngagement\t10%\tMutual interests/communities\n\nOutput: Top K candidates (default K=3, configurable 5-10)\n\nExamples\n\nSee the examples/ directory for:\n\nsample_run.json - Full JSON output example\nsample_run.md - Human-readable report example\nPrompts\n\nThe skill uses modular prompts located in prompts/:\n\ndiscovery.md - How to search for candidates\nfiltering.md - How to apply hard requirements\nranking.md - How to score and rank candidates\ndrafting.md - How to write outreach messages\nVenues\n\nVenue-specific search strategies are in venues/:\n\nmoltbook.md - Moltbook platform scouting\nweb.md - General web search strategies\ncommunities.md - Community/forum discovery\nConfiguration\nEnvironment Variables\n# Optional: Override defaults\nCLAWBRIDGE_TOP_K=5 # Number of candidates to return\nCLAWBRIDGE_RECENCY_DAYS=30 # Activity recency threshold\nCLAWBRIDGE_MAX_SEARCHES=20 # Max search queries per run\nCLAWBRIDGE_MAX_FETCHES=50 # Max page fetches per run\n\nWorkspace Configuration\n\nThe skill reads workspace config from the runner or vault:\n\nworkspace_id: \"ws_abc123\"\nworkspace_token: \"tok_...\" # For vault uploads\ndelivery_target: \"discord\" # or \"slack\" or \"email\"\n\nLicense\n\nMIT License - See LICENSE file for details.\n\nContributing\n\nContributions welcome! Please read the prompts carefully and ensure any changes maintain:\n\nDeterministic output schema\nNo secrets in prompts\nHuman-in-the-loop requirement\nEvidence-based candidate selection" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/moltlife/claw-clawbridge", "publisherUrl": "https://clawhub.ai/moltlife/claw-clawbridge", "owner": "moltlife", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/claw-clawbridge", "downloadUrl": "https://openagent3.xyz/downloads/claw-clawbridge", "agentUrl": "https://openagent3.xyz/skills/claw-clawbridge/agent", "manifestUrl": "https://openagent3.xyz/skills/claw-clawbridge/agent.json", "briefUrl": "https://openagent3.xyz/skills/claw-clawbridge/agent.md" } }