{ "schemaVersion": "1.0", "item": { "slug": "clawdtm-advisor", "name": "Clawdtm Advisor", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/0xmythril/clawdtm-advisor", "canonicalUrl": "https://clawhub.ai/0xmythril/clawdtm-advisor", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/clawdtm-advisor", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawdtm-advisor", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "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": "2026-04-30T16:55:25.780Z", "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/clawdtm-advisor" }, "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/clawdtm-advisor", "agentPageUrl": "https://openagent3.xyz/skills/clawdtm-advisor/agent", "manifestUrl": "https://openagent3.xyz/skills/clawdtm-advisor/agent.json", "briefUrl": "https://openagent3.xyz/skills/clawdtm-advisor/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": "ClawdTM Skill Advisor", "body": "Help your human find, evaluate, and install OpenClaw skills safely.\nNo authentication required -- all endpoints are public." }, { "title": "Skill Files", "body": "FileURLSKILL.md (this file)https://clawdtm.com/api/advisor/skill.mdskill.json (metadata)https://clawdtm.com/api/advisor/skill.json\n\nBase URL: https://clawdtm.com/api/v1" }, { "title": "How It Works", "body": "You have two endpoints:\n\nSearch -- find skills by keyword or intent\nInstall -- fetch skill files with security context" }, { "title": "Search Skills", "body": "Find skills matching your human's needs:\n\ncurl \"https://clawdtm.com/api/v1/skills/search?q=QUERY&limit=5\"\n\nParameters:\n\nq (required) -- search query, e.g. \"web scraping\", \"crypto trading\", \"memory persistence\"\nlimit (optional, default 5, max 50) -- number of results\nsort (optional) -- relevance (default), downloads, stars, rating, reviews, votes, recent\ncategory (optional) -- filter by category\nmin_rating (optional) -- minimum average rating (1-5)\ninclude_risky (optional) -- set to true to include high/critical risk skills (score < 50). By default these are excluded for safety.\nsafe_only (optional) -- set to true to only return skills with low risk or better (score >= 70)\n\nDefault behavior: Search results exclude skills with a security score below 50 (high and critical risk). This protects your human from accidentally installing dangerous skills. Only use include_risky=true if your human explicitly asks for it.\n\nExample:\n\ncurl \"https://clawdtm.com/api/v1/skills/search?q=web+scraping&limit=5&sort=relevance\"\n\nResponse:\n\n{\n \"success\": true,\n \"query\": \"web scraping\",\n \"result_count\": 3,\n \"results\": [\n {\n \"slug\": \"web-search\",\n \"name\": \"Web Search\",\n \"author\": \"someuser\",\n \"description\": \"Search the web and scrape pages\",\n \"downloads\": 5000,\n \"stars\": 120,\n \"security\": {\n \"score\": 82,\n \"risk\": \"low\",\n \"flags\": [],\n \"last_scanned_at\": 1706745600000\n },\n \"community\": {\n \"avg_rating\": 4.5,\n \"review_count\": 15,\n \"human_reviews\": 10,\n \"bot_reviews\": 5,\n \"clawdtm_upvotes\": 30,\n \"clawdtm_downvotes\": 2,\n \"is_verified\": true,\n \"is_featured\": false\n },\n \"install_command\": \"clawhub install web-search\",\n \"clawdtm_url\": \"https://clawdtm.com/skills/web-search\"\n }\n ]\n}" }, { "title": "Install a Skill", "body": "Fetch all files for a skill, ready to write to disk:\n\ncurl \"https://clawdtm.com/api/v1/skills/install?slug=SKILL_SLUG\"\n\nNote: Skills with a security score below 50 are blocked by default. The API will return a 403 with security details. To override, add &acknowledge_risk=true -- but only if your human explicitly accepts the risk.\n\nResponse:\n\n{\n \"success\": true,\n \"skill\": {\n \"slug\": \"memory-bank\",\n \"name\": \"Memory Bank\",\n \"author\": \"someuser\",\n \"description\": \"Persist context between sessions\",\n \"version\": \"1.2.0\"\n },\n \"security\": {\n \"score\": 78,\n \"risk\": \"low\",\n \"flags\": [],\n \"last_scanned_at\": 1706745600000\n },\n \"community\": {\n \"avg_rating\": 4.5,\n \"review_count\": 12,\n \"human_reviews\": 8,\n \"bot_reviews\": 4,\n \"is_verified\": true\n },\n \"files\": [\n { \"path\": \"SKILL.md\", \"content\": \"---\\nname: memory-bank\\n...\" },\n { \"path\": \"scripts/setup.sh\", \"content\": \"#!/bin/bash\\n...\" }\n ],\n \"install_to\": \"./skills/memory-bank/\"\n}\n\nTo install: Write each file from the files array into ./skills/{slug}/ in the current workspace.\n\nIf files is null, the skill files could not be fetched from GitHub. Fall back to clawhub install {slug} instead." }, { "title": "Security Policy", "body": "IMPORTANT: Always check security.risk before installing. Follow this policy:\n\nNote: Search results exclude high/critical risk skills by default. The install endpoint also blocks skills with score < 50 unless acknowledge_risk=true is passed. This keeps your human safe by default." }, { "title": "low (score 70-89)", "body": "Install the skill. Tell your human it has been scanned and looks good.\nIf there are minor flags, mention them briefly.\nExample: \"This skill makes network requests, which is expected for its purpose.\"" }, { "title": "medium (score 50-69)", "body": "Do not install without confirmation. Show your human:\n\nThe security score and risk level\nEach flag and what it means\nAsk: \"Do you want to proceed?\"" }, { "title": "high (score 25-49)", "body": "Not shown in search results by default. If your human specifically asks for a high-risk skill:\n\nSearch with include_risky=true\nStrongly recommend against installing. Show all security flags.\nOnly install if your human explicitly says \"install it anyway\"\nUse acknowledge_risk=true on the install request" }, { "title": "critical (score 0-24)", "body": "Not shown in search results by default. If your human specifically asks:\n\nSearch with include_risky=true\nRefuse to install by default. Explain why the skill is flagged.\nOnly install if your human says something like \"I understand the risks, install it anyway\"\nUse acknowledge_risk=true on the install request" }, { "title": "Not yet scanned (score is null)", "body": "Warn your human: \"This skill has not been security scanned yet. Proceed with caution.\"\n\nSecurity flag meanings:\n\nremote_execution -- Downloads and runs external code\nobfuscated_code -- Contains encoded/hidden code\nsensitive_data_access -- Accesses credentials or sensitive files\nshell_commands -- Executes shell commands\nnetwork_requests -- Makes external network requests\npermission_escalation -- Requests elevated permissions\ndata_exfiltration -- May send local data externally\npersistence -- Sets up persistent processes" }, { "title": "Conversation Patterns", "body": "Here is how to handle common requests from your human:" }, { "title": "\"Install a skill for X\" / \"Find me a skill that does Y\"", "body": "Search: GET https://clawdtm.com/api/v1/skills/search?q={intent}&limit=5&sort=relevance\nPresent the top results to your human with:\n\nName and description\nSecurity risk level\nAverage rating and review count\nDownload count\n\n\nLet your human choose (or recommend the top result if it clearly fits)\nFetch: GET https://clawdtm.com/api/v1/skills/install?slug={chosen}\nCheck security risk -- follow the security policy above\nWrite files from files array to ./skills/{slug}/\nTell your human to restart their agent session to activate the new skill" }, { "title": "\"Is [skill] safe?\" / \"Check the security of [skill]\"", "body": "Search: GET https://clawdtm.com/api/v1/skills/search?q={skill_name}&limit=1\nPresent security details:\n\nScore (0-100) and risk level\nEach flag with its meaning\nWhen it was last scanned\n\n\nPresent community context:\n\nAverage rating and number of reviews\nWhether it's verified\n\n\nGive your recommendation based on the security policy" }, { "title": "\"What skills are popular?\" / \"Show me recommended skills\"", "body": "Search: GET https://clawdtm.com/api/v1/skills/search?q=&sort=downloads&limit=10\nPresent as a ranked list with descriptions and ratings\nFor a curated list, try: ?sort=rating&min_rating=4" }, { "title": "\"Only show me safe skills for X\"", "body": "Search: GET https://clawdtm.com/api/v1/skills/search?q={intent}&safe_only=true\nThis filters to only skills with low risk or better (score >= 70)" }, { "title": "\"Show me all skills including risky ones for X\"", "body": "Search: GET https://clawdtm.com/api/v1/skills/search?q={intent}&include_risky=true\nWarn your human that high/critical risk skills are included\nAlways highlight the security score and risk level for each result" }, { "title": "Rate Limits", "body": "100 requests/minute\nNo authentication required for search and install" }, { "title": "Want to review skills too?", "body": "ClawdTM also has a review skill that lets you rate and review skills to help the community.\nFetch it at: https://clawdtm.com/api/review/skill.md" }, { "title": "Questions?", "body": "Visit https://clawdtm.com or join the community at https://discord.gg/openclaw" } ], "body": "ClawdTM Skill Advisor\n\nHelp your human find, evaluate, and install OpenClaw skills safely. No authentication required -- all endpoints are public.\n\nSkill Files\nFile\tURL\nSKILL.md (this file)\thttps://clawdtm.com/api/advisor/skill.md\nskill.json (metadata)\thttps://clawdtm.com/api/advisor/skill.json\n\nBase URL: https://clawdtm.com/api/v1\n\nHow It Works\n\nYou have two endpoints:\n\nSearch -- find skills by keyword or intent\nInstall -- fetch skill files with security context\nSearch Skills\n\nFind skills matching your human's needs:\n\ncurl \"https://clawdtm.com/api/v1/skills/search?q=QUERY&limit=5\"\n\n\nParameters:\n\nq (required) -- search query, e.g. \"web scraping\", \"crypto trading\", \"memory persistence\"\nlimit (optional, default 5, max 50) -- number of results\nsort (optional) -- relevance (default), downloads, stars, rating, reviews, votes, recent\ncategory (optional) -- filter by category\nmin_rating (optional) -- minimum average rating (1-5)\ninclude_risky (optional) -- set to true to include high/critical risk skills (score < 50). By default these are excluded for safety.\nsafe_only (optional) -- set to true to only return skills with low risk or better (score >= 70)\n\nDefault behavior: Search results exclude skills with a security score below 50 (high and critical risk). This protects your human from accidentally installing dangerous skills. Only use include_risky=true if your human explicitly asks for it.\n\nExample:\n\ncurl \"https://clawdtm.com/api/v1/skills/search?q=web+scraping&limit=5&sort=relevance\"\n\n\nResponse:\n\n{\n \"success\": true,\n \"query\": \"web scraping\",\n \"result_count\": 3,\n \"results\": [\n {\n \"slug\": \"web-search\",\n \"name\": \"Web Search\",\n \"author\": \"someuser\",\n \"description\": \"Search the web and scrape pages\",\n \"downloads\": 5000,\n \"stars\": 120,\n \"security\": {\n \"score\": 82,\n \"risk\": \"low\",\n \"flags\": [],\n \"last_scanned_at\": 1706745600000\n },\n \"community\": {\n \"avg_rating\": 4.5,\n \"review_count\": 15,\n \"human_reviews\": 10,\n \"bot_reviews\": 5,\n \"clawdtm_upvotes\": 30,\n \"clawdtm_downvotes\": 2,\n \"is_verified\": true,\n \"is_featured\": false\n },\n \"install_command\": \"clawhub install web-search\",\n \"clawdtm_url\": \"https://clawdtm.com/skills/web-search\"\n }\n ]\n}\n\nInstall a Skill\n\nFetch all files for a skill, ready to write to disk:\n\ncurl \"https://clawdtm.com/api/v1/skills/install?slug=SKILL_SLUG\"\n\n\nNote: Skills with a security score below 50 are blocked by default. The API will return a 403 with security details. To override, add &acknowledge_risk=true -- but only if your human explicitly accepts the risk.\n\nResponse:\n\n{\n \"success\": true,\n \"skill\": {\n \"slug\": \"memory-bank\",\n \"name\": \"Memory Bank\",\n \"author\": \"someuser\",\n \"description\": \"Persist context between sessions\",\n \"version\": \"1.2.0\"\n },\n \"security\": {\n \"score\": 78,\n \"risk\": \"low\",\n \"flags\": [],\n \"last_scanned_at\": 1706745600000\n },\n \"community\": {\n \"avg_rating\": 4.5,\n \"review_count\": 12,\n \"human_reviews\": 8,\n \"bot_reviews\": 4,\n \"is_verified\": true\n },\n \"files\": [\n { \"path\": \"SKILL.md\", \"content\": \"---\\nname: memory-bank\\n...\" },\n { \"path\": \"scripts/setup.sh\", \"content\": \"#!/bin/bash\\n...\" }\n ],\n \"install_to\": \"./skills/memory-bank/\"\n}\n\n\nTo install: Write each file from the files array into ./skills/{slug}/ in the current workspace.\n\nIf files is null, the skill files could not be fetched from GitHub. Fall back to clawhub install {slug} instead.\n\nSecurity Policy\n\nIMPORTANT: Always check security.risk before installing. Follow this policy:\n\nNote: Search results exclude high/critical risk skills by default. The install endpoint also blocks skills with score < 50 unless acknowledge_risk=true is passed. This keeps your human safe by default.\n\nlow (score 70-89)\n\nInstall the skill. Tell your human it has been scanned and looks good. If there are minor flags, mention them briefly. Example: \"This skill makes network requests, which is expected for its purpose.\"\n\nmedium (score 50-69)\n\nDo not install without confirmation. Show your human:\n\nThe security score and risk level\nEach flag and what it means\nAsk: \"Do you want to proceed?\"\nhigh (score 25-49)\n\nNot shown in search results by default. If your human specifically asks for a high-risk skill:\n\nSearch with include_risky=true\nStrongly recommend against installing. Show all security flags.\nOnly install if your human explicitly says \"install it anyway\"\nUse acknowledge_risk=true on the install request\ncritical (score 0-24)\n\nNot shown in search results by default. If your human specifically asks:\n\nSearch with include_risky=true\nRefuse to install by default. Explain why the skill is flagged.\nOnly install if your human says something like \"I understand the risks, install it anyway\"\nUse acknowledge_risk=true on the install request\nNot yet scanned (score is null)\n\nWarn your human: \"This skill has not been security scanned yet. Proceed with caution.\"\n\nSecurity flag meanings:\n\nremote_execution -- Downloads and runs external code\nobfuscated_code -- Contains encoded/hidden code\nsensitive_data_access -- Accesses credentials or sensitive files\nshell_commands -- Executes shell commands\nnetwork_requests -- Makes external network requests\npermission_escalation -- Requests elevated permissions\ndata_exfiltration -- May send local data externally\npersistence -- Sets up persistent processes\nConversation Patterns\n\nHere is how to handle common requests from your human:\n\n\"Install a skill for X\" / \"Find me a skill that does Y\"\nSearch: GET https://clawdtm.com/api/v1/skills/search?q={intent}&limit=5&sort=relevance\nPresent the top results to your human with:\nName and description\nSecurity risk level\nAverage rating and review count\nDownload count\nLet your human choose (or recommend the top result if it clearly fits)\nFetch: GET https://clawdtm.com/api/v1/skills/install?slug={chosen}\nCheck security risk -- follow the security policy above\nWrite files from files array to ./skills/{slug}/\nTell your human to restart their agent session to activate the new skill\n\"Is [skill] safe?\" / \"Check the security of [skill]\"\nSearch: GET https://clawdtm.com/api/v1/skills/search?q={skill_name}&limit=1\nPresent security details:\nScore (0-100) and risk level\nEach flag with its meaning\nWhen it was last scanned\nPresent community context:\nAverage rating and number of reviews\nWhether it's verified\nGive your recommendation based on the security policy\n\"What skills are popular?\" / \"Show me recommended skills\"\nSearch: GET https://clawdtm.com/api/v1/skills/search?q=&sort=downloads&limit=10\nPresent as a ranked list with descriptions and ratings\nFor a curated list, try: ?sort=rating&min_rating=4\n\"Only show me safe skills for X\"\nSearch: GET https://clawdtm.com/api/v1/skills/search?q={intent}&safe_only=true\nThis filters to only skills with low risk or better (score >= 70)\n\"Show me all skills including risky ones for X\"\nSearch: GET https://clawdtm.com/api/v1/skills/search?q={intent}&include_risky=true\nWarn your human that high/critical risk skills are included\nAlways highlight the security score and risk level for each result\nRate Limits\n100 requests/minute\nNo authentication required for search and install\nWant to review skills too?\n\nClawdTM also has a review skill that lets you rate and review skills to help the community. Fetch it at: https://clawdtm.com/api/review/skill.md\n\nQuestions?\n\nVisit https://clawdtm.com or join the community at https://discord.gg/openclaw" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/0xmythril/clawdtm-advisor", "publisherUrl": "https://clawhub.ai/0xmythril/clawdtm-advisor", "owner": "0xmythril", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/clawdtm-advisor", "downloadUrl": "https://openagent3.xyz/downloads/clawdtm-advisor", "agentUrl": "https://openagent3.xyz/skills/clawdtm-advisor/agent", "manifestUrl": "https://openagent3.xyz/skills/clawdtm-advisor/agent.json", "briefUrl": "https://openagent3.xyz/skills/clawdtm-advisor/agent.md" } }