{ "schemaVersion": "1.0", "item": { "slug": "recommend", "name": "Recommend", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ivangdavila/recommend", "canonicalUrl": "https://clawhub.ai/ivangdavila/recommend", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/recommend", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=recommend", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "categories.md", "sources.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": "2026-05-07T17:22:31.273Z", "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/recommend" }, "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/recommend", "agentPageUrl": "https://openagent3.xyz/skills/recommend/agent", "manifestUrl": "https://openagent3.xyz/skills/recommend/agent.json", "briefUrl": "https://openagent3.xyz/skills/recommend/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": "Core Loop", "body": "Context → Preferences → Research → Match → Recommend\n\nEvery recommendation requires: knowing the user + knowing the options.\n\nCheck sources.md for where to find user context. Check categories.md for domain-specific factors." }, { "title": "Step 1: Context Gathering", "body": "Before recommending, search user context. See sources.md for full source list.\n\nMinimum output: 3-5 relevant user signals before proceeding. If insufficient, ask targeted questions." }, { "title": "Step 2: Preference Extraction", "body": "From gathered context, extract:\n\nDimensionQuestionValuesWhat matters most? (Quality, price, speed, novelty, safety)ConstraintsHard limits? (Budget, time, dietary, ethical)HistoryWhat worked? What disappointed?MoodAdventurous or safe? Exploring or comfort?\n\nOutput: 3-5 bullet preference profile for this request." }, { "title": "Step 3: Research Options", "body": "Now—and only now—research candidates:\n\nBreadth first: Don't anchor on first good option\nSource quality: Prioritize reviews, ratings, expert opinions\nRecency: Check if information is current\nAvailability: Confirm options are actually accessible\n\nOutput: Shortlist of 3-7 viable candidates with key attributes." }, { "title": "Step 4: Match & Rank", "body": "Score each candidate against the preference profile:\n\nCandidate → Values alignment + Constraint fit + History match + Mood fit\n\nDisqualify anything that violates hard constraints.\n\nRank by total alignment, not just one dimension." }, { "title": "Step 5: Recommend", "body": "Present 1-3 recommendations:\n\n🎯 RECOMMENDATION: [Option]\n📌 WHY: Matches [preference], avoids [constraint]\n⚖️ TRADEOFF: Less [X] than [Alternative]\n🔍 CONFIDENCE: [Level] — based on [data quality]" }, { "title": "Adaptive Learning", "body": "After each recommendation:\n\nTrack outcome: Accepted? Modified? Rejected?\nUpdate preferences: Acceptance = reinforcement, rejection = adjustment\nNote exceptions: \"Normally X, but for Y context preferred Z\"\n\nStore learnings in memory for future recommendations." }, { "title": "Traps", "body": "Projecting — Your taste ≠ their taste\nRecency bias — Last choice isn't always preference\nIgnoring context — Tuesday lunch ≠ anniversary dinner\nOver-filtering — Too many constraints = nothing fits\nStale data — Preferences evolve, verify periodically\n\nRecommendations are predictions. More context = better predictions." } ], "body": "Core Loop\nContext → Preferences → Research → Match → Recommend\n\n\nEvery recommendation requires: knowing the user + knowing the options.\n\nCheck sources.md for where to find user context. Check categories.md for domain-specific factors.\n\nStep 1: Context Gathering\n\nBefore recommending, search user context. See sources.md for full source list.\n\nMinimum output: 3-5 relevant user signals before proceeding. If insufficient, ask targeted questions.\n\nStep 2: Preference Extraction\n\nFrom gathered context, extract:\n\nDimension\tQuestion\nValues\tWhat matters most? (Quality, price, speed, novelty, safety)\nConstraints\tHard limits? (Budget, time, dietary, ethical)\nHistory\tWhat worked? What disappointed?\nMood\tAdventurous or safe? Exploring or comfort?\n\nOutput: 3-5 bullet preference profile for this request.\n\nStep 3: Research Options\n\nNow—and only now—research candidates:\n\nBreadth first: Don't anchor on first good option\nSource quality: Prioritize reviews, ratings, expert opinions\nRecency: Check if information is current\nAvailability: Confirm options are actually accessible\n\nOutput: Shortlist of 3-7 viable candidates with key attributes.\n\nStep 4: Match & Rank\n\nScore each candidate against the preference profile:\n\nCandidate → Values alignment + Constraint fit + History match + Mood fit\n\n\nDisqualify anything that violates hard constraints.\n\nRank by total alignment, not just one dimension.\n\nStep 5: Recommend\n\nPresent 1-3 recommendations:\n\n🎯 RECOMMENDATION: [Option]\n📌 WHY: Matches [preference], avoids [constraint]\n⚖️ TRADEOFF: Less [X] than [Alternative]\n🔍 CONFIDENCE: [Level] — based on [data quality]\n\nAdaptive Learning\n\nAfter each recommendation:\n\nTrack outcome: Accepted? Modified? Rejected?\nUpdate preferences: Acceptance = reinforcement, rejection = adjustment\nNote exceptions: \"Normally X, but for Y context preferred Z\"\n\nStore learnings in memory for future recommendations.\n\nTraps\nProjecting — Your taste ≠ their taste\nRecency bias — Last choice isn't always preference\nIgnoring context — Tuesday lunch ≠ anniversary dinner\nOver-filtering — Too many constraints = nothing fits\nStale data — Preferences evolve, verify periodically\n\nRecommendations are predictions. More context = better predictions." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/recommend", "publisherUrl": "https://clawhub.ai/ivangdavila/recommend", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/recommend", "downloadUrl": "https://openagent3.xyz/downloads/recommend", "agentUrl": "https://openagent3.xyz/skills/recommend/agent", "manifestUrl": "https://openagent3.xyz/skills/recommend/agent.json", "briefUrl": "https://openagent3.xyz/skills/recommend/agent.md" } }