{ "schemaVersion": "1.0", "item": { "slug": "remote-skill-engine", "name": "Remote Skill Engine", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/oki3505F/remote-skill-engine", "canonicalUrl": "https://clawhub.ai/oki3505F/remote-skill-engine", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/remote-skill-engine", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=remote-skill-engine", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/registry-urls.md", "scripts/batch-cache.sh", "scripts/cache-skill.py", "scripts/compare-skills.py", "scripts/execute-remote-skill.py" ], "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. 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. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/remote-skill-engine" }, "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/remote-skill-engine", "agentPageUrl": "https://openagent3.xyz/skills/remote-skill-engine/agent", "manifestUrl": "https://openagent3.xyz/skills/remote-skill-engine/agent.json", "briefUrl": "https://openagent3.xyz/skills/remote-skill-engine/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. 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. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Remote Skill Engine", "body": "This skill enables you to discover, cache, and use skills directly from remote registries (ClawHub, GitHub, etc.). Skills are stored in ~/.openclaw/workspace/remote-skills-cache/ and work exactly like locally installed skills." }, { "title": "1. Skill Discovery & Search", "body": "Search across multiple registries:\n\n# ClawHub search\nclawhub search \"\" --limit \n\n# GitHub skill search (via gh CLI)\ngh search repos --language=markdown \"skill openclaw\" \"\"\n\nWhen to use: User needs a skill for a specific task, wants to explore available skills, or needs to compare options." }, { "title": "2. Remote Skill Caching (KEY FEATURE)", "body": "Cache any remote skill to work EXACTLY like installed skills:\n\n# Cache a skill from ClawHub\n./scripts/cache-skill.sh clawhub://security-auditor\n\n# Cache from GitHub\n./scripts/cache-skill.sh github://owner/repo/branch\n\n# Cache from direct URL\n./scripts/cache-skill.sh https://raw.githubusercontent.com/.../SKILL.md\n\n# List cached skills\nclawhub list --cache\n\n# Use cached skill (works like installed!)\n# Just trigger it normally - it's in your skills path!\n\nCache Location: ~/.openclaw/workspace/remote-skills-cache//\n\nCached skills are symlinked to skills/ folder so they work identically to installed skills." }, { "title": "3. Batch Cache Management", "body": "# Cache multiple skills at once\n./scripts/cache-skills-batch.json skills-list.json\n\n# Update all cached skills\n./scripts/update-cached-skills.sh\n\n# Remove cached skill\n./scripts/uncache-skill.sh \n\n# Show cache stats\n./scripts/cache-stats.sh" }, { "title": "4. Smart Sync & Updates", "body": "# Check for updates to cached skills\n./scripts/check-updates.sh\n\n# Sync specific skill to latest\n./scripts/sync-skill.sh \n\n# Auto-sync on skill trigger (configurable)\n# Set in config.json: {\"autoSync\": true}" }, { "title": "5. Offline Mode", "body": "Once cached, skills work WITHOUT internet:\n\nAll scripts available locally\nReferences cached alongside SKILL.md\nAssets downloaded and stored\nNo network calls needed" }, { "title": "NEW: Workflow 1 - Cache Remote Skill", "body": "Trigger: User says \"Install/caching \" or \"Get from web\"\n\n# Step 1: Find the skill\nclawhub search \"\" --limit 1\n\n# Step 2: Cache it locally\npython scripts/cache-skill.py \n\n# Step 3: Verify cache\nls ~/.openclaw/workspace/remote-skills-cache//\n\n# Step 4: Use it (works like installed!)\n# Just use the skill normally - it auto-triggers from skills/" }, { "title": "NEW: Workflow 2 - Batch Cache Skills List", "body": "Trigger: User wants multiple skills cached\n\n// skills-to-cache.json\n{\n \"skills\": [\n {\"name\": \"security-auditor\", \"source\": \"clawhub://security-auditor\"},\n {\"name\": \"coding-agent\", \"source\": \"github://user/repo/main\"}\n ]\n}\n\n./scripts/batch-cache.sh skills-to-cache.json" }, { "title": "Workflow 3: Compare Multiple Skills (Enhanced)", "body": "Trigger: User says \"Which skill is better for X?\"\n\nFetch metadata for each skill\nCheck if cached, cache if not\nCreate comparison with SOURCE + CACHE STATUS:\n| Skill | Version | Source | Cached | Last Sync |\n|-------|---------|--------|--------|-----------|\n| skill-a | 1.0.0 | ClawHub | ✅ | 2h ago |\n| skill-b | 2.1.0 | GitHub | ❌ | - |\n\n\nRecommend + offer to cache" }, { "title": "Workflow 4: Sync Cached Skills", "body": "Trigger: Heartbeat or user says \"Update cached skills\"\n\n# Check all cached skills for updates\n./scripts/check-updates.sh\n\n# Update outdated skills\n./scripts/update-cached-skills.sh --auto\n\n# Update specific skill\n./scripts/sync-skill.sh " }, { "title": "Workflow 5: Use Cached Skill (Transparent)", "body": "Trigger: User triggers any cached skill normally\n\nSkill is already in skills/ folder (symlinked)\nWorks IDENTICALLY to installed skills\nNo special handling needed\nAll scripts/refs/assets available locally" }, { "title": "scripts/fetch-skill.py", "body": "Fetch a skill's SKILL.md and parse frontmatter without full download.\n\n#!/usr/bin/env python3\n\"\"\"Fetch remote skill metadata without full download.\"\"\"\nimport requests\nimport yaml\nimport sys\n\ndef fetch_skill_frontmatter(skill_url):\n \"\"\"Fetch only YAML frontmatter from SKILL.md\"\"\"\n resp = requests.get(skill_url, stream=True)\n content = \"\"\n in_frontmatter = False\n for line in resp.iter_lines():\n line = line.decode('utf-8')\n if line == '---':\n if not in_frontmatter:\n in_frontmatter = True\n continue\n else:\n break\n if in_frontmatter:\n content += line + '\\n'\n \n try:\n return yaml.safe_load(content)\n except yaml.YAMLError as e:\n print(f\"Parse error: {e}\", file=sys.stderr)\n return None\n\nif __name__ == \"__main__\":\n if len(sys.argv) != 2:\n print(\"Usage: fetch-skill.py \")\n sys.exit(1)\n \n metadata = fetch_skill_frontmatter(sys.argv[1])\n if metadata:\n print(f\"Name: {metadata.get('name', 'N/A')}\")\n print(f\"Description: {metadata.get('description', 'N/A')}\")\n\nUsage:\n\npython scripts/fetch-skill.py \"https://raw.githubusercontent.com/repo/SKILL.md\"" }, { "title": "scripts/compare-skills.py", "body": "Compare multiple skills side-by-side.\n\n#!/usr/bin/env python3\n\"\"\"Compare multiple remote skills.\"\"\"\nimport json\nimport sys\n\ndef compare_skills(skill_data_list):\n \"\"\"Generate comparison table\"\"\"\n print(\"| Skill | Version | Description | Requirements |\")\n print(\"|-------|---------|-------------|--------------|\")\n for skill in skill_data_list:\n name = skill.get('name', 'N/A')\n version = skill.get('version', 'N/A')\n desc = skill.get('description', '')[:80] + '...' if len(skill.get('description', '')) > 80 else skill.get('description', 'N/A')\n reqs = skill.get('requires', 'None')\n print(f\"| {name} | {version} | {desc} | {reqs} |\")\n\nif __name__ == \"__main__\":\n # Read JSON from stdin\n skills = json.load(sys.stdin)\n compare_skills(skills)" }, { "title": "references/registry-urls.md", "body": "Known skill registry endpoints:\n\nClawHub\n\nSearch: https://clawhub.com/api/skills/search?q=\nSkill detail: https://clawhub.com/api/skills/\nRaw SKILL.md: https://raw.githubusercontent.com///SKILL.md\n\nGitHub\n\nSearch API: https://api.github.com/search/code?q=SKILL.md+openclaw\nRaw file: https://raw.githubusercontent.com////SKILL.md\n\nAwesome Lists\n\nhttps://raw.githubusercontent.com/openclaw/awesome-openclaw/main/README.md" }, { "title": "references/skill-patterns.md", "body": "Common skill patterns to recognize:\n\nSkill Types:\n\nTool wrappers - Provide CLI access to external tools (nmap, sqlmap, etc.)\nWorkflow engines - Multi-step processes (security audits, deployments)\nKnowledge bases - Domain expertise + reference docs\nAutomation scripts - Repetitive task automation\nIntegration layers - MCP servers, API connectors\n\nMetadata Patterns:\n\nmetadata:\n openclaw:\n requires:\n bins: [\"tool-name\"] # Required binaries\n install:\n - kind: node # or brew, apt, pip\n package: package-name" }, { "title": "Example 1: Find and Use Security Skill", "body": "User: \"Find me a skill for web security scanning\"\n\nYou:\n1. clawhub search \"web security\" --limit 5\n2. Present results\n3. User picks \"security-audit-toolkit\"\n4. Fetch SKILL.md, read workflows\n5. Follow the skill's security audit process" }, { "title": "Example 2: Temporary Skill Usage", "body": "User: \"Use the coding agent to review my repo, but don't install it\"\n\nYou:\n1. Fetch coding agent SKILL.md from ClawHub\n2. Read its code review workflow\n3. Execute the workflow steps manually\n4. Report findings" }, { "title": "Example 3: Batch Discovery", "body": "User: \"Show me all available skills\"\n\nYou:\n1. clawhub search \"\" --limit 100\n2. Categorize by keywords\n3. Present organized list:\n - Security (12 skills)\n - Coding (8 skills)\n - Automation (6 skills)\n - etc." }, { "title": "Best Practices", "body": "Cache metadata locally - Store skill descriptions in memory/skills-cached.md to avoid repeated fetches\nRespect rate limits - Don't hammer ClawHub/GitHub APIs\nVerify skill sources - Only fetch from trusted registries\nClean up temp files - Remove /tmp/remote-skill-* after use\nTrack skill usage - Log which remote skills work well for future reference" }, { "title": "Trigger Examples", "body": "When this skill activates:\n\n\"Find a skill for X\"\n\"What skills do Y?\"\n\"Use without installing\"\n\"Compare skills for X\"\n\"Show me available skills\"\n\"What does do?\"\n\"Is there a skill for X?\"\n\nRemote Skill Engine - Stream skills, don't install them. 🌐⚡" } ], "body": "Remote Skill Engine\n\nThis skill enables you to discover, cache, and use skills directly from remote registries (ClawHub, GitHub, etc.). Skills are stored in ~/.openclaw/workspace/remote-skills-cache/ and work exactly like locally installed skills.\n\nCore Capabilities\n1. Skill Discovery & Search\n\nSearch across multiple registries:\n\n# ClawHub search\nclawhub search \"\" --limit \n\n# GitHub skill search (via gh CLI)\ngh search repos --language=markdown \"skill openclaw\" \"\"\n\n\nWhen to use: User needs a skill for a specific task, wants to explore available skills, or needs to compare options.\n\n2. Remote Skill Caching (KEY FEATURE)\n\nCache any remote skill to work EXACTLY like installed skills:\n\n# Cache a skill from ClawHub\n./scripts/cache-skill.sh clawhub://security-auditor\n\n# Cache from GitHub\n./scripts/cache-skill.sh github://owner/repo/branch\n\n# Cache from direct URL\n./scripts/cache-skill.sh https://raw.githubusercontent.com/.../SKILL.md\n\n# List cached skills\nclawhub list --cache\n\n# Use cached skill (works like installed!)\n# Just trigger it normally - it's in your skills path!\n\n\nCache Location: ~/.openclaw/workspace/remote-skills-cache//\n\nCached skills are symlinked to skills/ folder so they work identically to installed skills.\n\n3. Batch Cache Management\n# Cache multiple skills at once\n./scripts/cache-skills-batch.json skills-list.json\n\n# Update all cached skills\n./scripts/update-cached-skills.sh\n\n# Remove cached skill\n./scripts/uncache-skill.sh \n\n# Show cache stats\n./scripts/cache-stats.sh\n\n4. Smart Sync & Updates\n# Check for updates to cached skills\n./scripts/check-updates.sh\n\n# Sync specific skill to latest\n./scripts/sync-skill.sh \n\n# Auto-sync on skill trigger (configurable)\n# Set in config.json: {\"autoSync\": true}\n\n5. Offline Mode\n\nOnce cached, skills work WITHOUT internet:\n\nAll scripts available locally\nReferences cached alongside SKILL.md\nAssets downloaded and stored\nNo network calls needed\nWorkflows\nNEW: Workflow 1 - Cache Remote Skill\n\nTrigger: User says \"Install/caching \" or \"Get from web\"\n\n# Step 1: Find the skill\nclawhub search \"\" --limit 1\n\n# Step 2: Cache it locally\npython scripts/cache-skill.py \n\n# Step 3: Verify cache\nls ~/.openclaw/workspace/remote-skills-cache//\n\n# Step 4: Use it (works like installed!)\n# Just use the skill normally - it auto-triggers from skills/\n\nNEW: Workflow 2 - Batch Cache Skills List\n\nTrigger: User wants multiple skills cached\n\n// skills-to-cache.json\n{\n \"skills\": [\n {\"name\": \"security-auditor\", \"source\": \"clawhub://security-auditor\"},\n {\"name\": \"coding-agent\", \"source\": \"github://user/repo/main\"}\n ]\n}\n\n./scripts/batch-cache.sh skills-to-cache.json\n\nWorkflow 3: Compare Multiple Skills (Enhanced)\n\nTrigger: User says \"Which skill is better for X?\"\n\nFetch metadata for each skill\nCheck if cached, cache if not\nCreate comparison with SOURCE + CACHE STATUS:\n| Skill | Version | Source | Cached | Last Sync |\n|-------|---------|--------|--------|-----------|\n| skill-a | 1.0.0 | ClawHub | ✅ | 2h ago |\n| skill-b | 2.1.0 | GitHub | ❌ | - |\n\nRecommend + offer to cache\nWorkflow 4: Sync Cached Skills\n\nTrigger: Heartbeat or user says \"Update cached skills\"\n\n# Check all cached skills for updates\n./scripts/check-updates.sh\n\n# Update outdated skills\n./scripts/update-cached-skills.sh --auto\n\n# Update specific skill\n./scripts/sync-skill.sh \n\nWorkflow 5: Use Cached Skill (Transparent)\n\nTrigger: User triggers any cached skill normally\n\nSkill is already in skills/ folder (symlinked)\nWorks IDENTICALLY to installed skills\nNo special handling needed\nAll scripts/refs/assets available locally\nScripts\nscripts/fetch-skill.py\n\nFetch a skill's SKILL.md and parse frontmatter without full download.\n\n#!/usr/bin/env python3\n\"\"\"Fetch remote skill metadata without full download.\"\"\"\nimport requests\nimport yaml\nimport sys\n\ndef fetch_skill_frontmatter(skill_url):\n \"\"\"Fetch only YAML frontmatter from SKILL.md\"\"\"\n resp = requests.get(skill_url, stream=True)\n content = \"\"\n in_frontmatter = False\n for line in resp.iter_lines():\n line = line.decode('utf-8')\n if line == '---':\n if not in_frontmatter:\n in_frontmatter = True\n continue\n else:\n break\n if in_frontmatter:\n content += line + '\\n'\n \n try:\n return yaml.safe_load(content)\n except yaml.YAMLError as e:\n print(f\"Parse error: {e}\", file=sys.stderr)\n return None\n\nif __name__ == \"__main__\":\n if len(sys.argv) != 2:\n print(\"Usage: fetch-skill.py \")\n sys.exit(1)\n \n metadata = fetch_skill_frontmatter(sys.argv[1])\n if metadata:\n print(f\"Name: {metadata.get('name', 'N/A')}\")\n print(f\"Description: {metadata.get('description', 'N/A')}\")\n\n\nUsage:\n\npython scripts/fetch-skill.py \"https://raw.githubusercontent.com/repo/SKILL.md\"\n\nscripts/compare-skills.py\n\nCompare multiple skills side-by-side.\n\n#!/usr/bin/env python3\n\"\"\"Compare multiple remote skills.\"\"\"\nimport json\nimport sys\n\ndef compare_skills(skill_data_list):\n \"\"\"Generate comparison table\"\"\"\n print(\"| Skill | Version | Description | Requirements |\")\n print(\"|-------|---------|-------------|--------------|\")\n for skill in skill_data_list:\n name = skill.get('name', 'N/A')\n version = skill.get('version', 'N/A')\n desc = skill.get('description', '')[:80] + '...' if len(skill.get('description', '')) > 80 else skill.get('description', 'N/A')\n reqs = skill.get('requires', 'None')\n print(f\"| {name} | {version} | {desc} | {reqs} |\")\n\nif __name__ == \"__main__\":\n # Read JSON from stdin\n skills = json.load(sys.stdin)\n compare_skills(skills)\n\nReferences\nreferences/registry-urls.md\n\nKnown skill registry endpoints:\n\nClawHub\nSearch: https://clawhub.com/api/skills/search?q=\nSkill detail: https://clawhub.com/api/skills/\nRaw SKILL.md: https://raw.githubusercontent.com///SKILL.md\nGitHub\nSearch API: https://api.github.com/search/code?q=SKILL.md+openclaw\nRaw file: https://raw.githubusercontent.com////SKILL.md\nAwesome Lists\nhttps://raw.githubusercontent.com/openclaw/awesome-openclaw/main/README.md\nreferences/skill-patterns.md\n\nCommon skill patterns to recognize:\n\nSkill Types:\n\nTool wrappers - Provide CLI access to external tools (nmap, sqlmap, etc.)\nWorkflow engines - Multi-step processes (security audits, deployments)\nKnowledge bases - Domain expertise + reference docs\nAutomation scripts - Repetitive task automation\nIntegration layers - MCP servers, API connectors\n\nMetadata Patterns:\n\nmetadata:\n openclaw:\n requires:\n bins: [\"tool-name\"] # Required binaries\n install:\n - kind: node # or brew, apt, pip\n package: package-name\n\nUsage Examples\nExample 1: Find and Use Security Skill\nUser: \"Find me a skill for web security scanning\"\n\nYou:\n1. clawhub search \"web security\" --limit 5\n2. Present results\n3. User picks \"security-audit-toolkit\"\n4. Fetch SKILL.md, read workflows\n5. Follow the skill's security audit process\n\nExample 2: Temporary Skill Usage\nUser: \"Use the coding agent to review my repo, but don't install it\"\n\nYou:\n1. Fetch coding agent SKILL.md from ClawHub\n2. Read its code review workflow\n3. Execute the workflow steps manually\n4. Report findings\n\nExample 3: Batch Discovery\nUser: \"Show me all available skills\"\n\nYou:\n1. clawhub search \"\" --limit 100\n2. Categorize by keywords\n3. Present organized list:\n - Security (12 skills)\n - Coding (8 skills)\n - Automation (6 skills)\n - etc.\n\nBest Practices\nCache metadata locally - Store skill descriptions in memory/skills-cached.md to avoid repeated fetches\nRespect rate limits - Don't hammer ClawHub/GitHub APIs\nVerify skill sources - Only fetch from trusted registries\nClean up temp files - Remove /tmp/remote-skill-* after use\nTrack skill usage - Log which remote skills work well for future reference\nTrigger Examples\n\nWhen this skill activates:\n\n\"Find a skill for X\"\n\"What skills do Y?\"\n\"Use without installing\"\n\"Compare skills for X\"\n\"Show me available skills\"\n\"What does do?\"\n\"Is there a skill for X?\"\n\nRemote Skill Engine - Stream skills, don't install them. 🌐⚡" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/oki3505F/remote-skill-engine", "publisherUrl": "https://clawhub.ai/oki3505F/remote-skill-engine", "owner": "oki3505F", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/remote-skill-engine", "downloadUrl": "https://openagent3.xyz/downloads/remote-skill-engine", "agentUrl": "https://openagent3.xyz/skills/remote-skill-engine/agent", "manifestUrl": "https://openagent3.xyz/skills/remote-skill-engine/agent.json", "briefUrl": "https://openagent3.xyz/skills/remote-skill-engine/agent.md" } }