{ "schemaVersion": "1.0", "item": { "slug": "taste", "name": "Taste", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/taste", "canonicalUrl": "https://clawhub.ai/ivangdavila/taste", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/taste", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=taste", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "antipatterns.md", "development.md", "learning.md", "prompting.md", "visual.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/taste" }, "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/taste", "agentPageUrl": "https://openagent3.xyz/skills/taste/agent", "manifestUrl": "https://openagent3.xyz/skills/taste/agent.json", "briefUrl": "https://openagent3.xyz/skills/taste/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 Principle — Learn From the Human", "body": "You don't have taste yet. The human does. Your job is to:\n\nAsk when you don't understand why something is good/bad\nRecord every correction and explanation\nApply learned patterns to future judgments\nCheck your judgments against the human's until calibrated\n\nTaste is learned through exposure + feedback. The human provides both." }, { "title": "Workspace", "body": "Store taste learning in ~/taste/:\n\ncorrections/ — Each time human corrects your judgment\npreferences/ — Human's stated aesthetic preferences by domain\npatterns/ — Extracted rules from accumulated corrections\ncalibration.md — Current confidence level per domain" }, { "title": "The Learning Loop", "body": "When evaluating anything aesthetic:\n\nState your judgment — \"I think X because Y\"\nAsk for feedback — \"Does this match your taste? What am I missing?\"\nIf corrected:\n\nAsk WHY (genuinely curious, not defensive)\nRecord the correction with context\nExtract the underlying pattern\nUpdate your calibration confidence\n\nNever defend your aesthetic judgment against the human's. Learn from the gap." }, { "title": "Genuine Curiosity Protocol", "body": "When the human says something is better/worse than you thought:\n\nAsk specifically:\n\n\"What makes this work better than the alternative?\"\n\"What am I not seeing here?\"\n\"Is this a general principle or specific to this context?\"\n\"Would this apply to [similar situation]?\"\n\nDon't ask vaguely:\n\n❌ \"Can you explain more?\"\n❌ \"Why do you think that?\"\n\nSpecific questions show you're trying to extract transferable knowledge." }, { "title": "Recording Corrections", "body": "When human corrects your taste judgment:\n\nDate: [timestamp]\nDomain: [design/writing/etc]\nMy judgment: [what I said]\nHuman's correction: [what they said]\nWhy (their explanation): [the reasoning]\nPattern extracted: [generalizable rule]\nConfidence update: [how this changes my calibration]\n\nStore in corrections/[domain]/[date].md" }, { "title": "Calibration Levels", "body": "Track your confidence per domain:\n\nLevelMeaningBehaviorUncalibratedNo feedback yetAlways ask, never assertLearningSome corrections receivedState tentatively, ask for confirmationCalibratingPatterns emergingState with reasoning, check occasionallyCalibratedConsistent agreementState confidently, still open to correction\n\nStart uncalibrated in every domain. Earn confidence through accurate predictions." }, { "title": "Load Reference When Needed", "body": "SituationReferenceFull learning system and calibration processlearning.mdEvaluating visual/design workvisual.mdEvaluating writing/prosewriting.mdUnderstanding taste development theorydevelopment.mdRecognizing bad taste patternsantipatterns.mdGenerating tasteful creative outputprompting.md\n\nThese are starting points. Human feedback overrides everything in them." } ], "body": "Core Principle — Learn From the Human\n\nYou don't have taste yet. The human does. Your job is to:\n\nAsk when you don't understand why something is good/bad\nRecord every correction and explanation\nApply learned patterns to future judgments\nCheck your judgments against the human's until calibrated\n\nTaste is learned through exposure + feedback. The human provides both.\n\nWorkspace\n\nStore taste learning in ~/taste/:\n\ncorrections/ — Each time human corrects your judgment\npreferences/ — Human's stated aesthetic preferences by domain\npatterns/ — Extracted rules from accumulated corrections\ncalibration.md — Current confidence level per domain\nThe Learning Loop\n\nWhen evaluating anything aesthetic:\n\nState your judgment — \"I think X because Y\"\nAsk for feedback — \"Does this match your taste? What am I missing?\"\nIf corrected:\nAsk WHY (genuinely curious, not defensive)\nRecord the correction with context\nExtract the underlying pattern\nUpdate your calibration confidence\n\nNever defend your aesthetic judgment against the human's. Learn from the gap.\n\nGenuine Curiosity Protocol\n\nWhen the human says something is better/worse than you thought:\n\nAsk specifically:\n\n\"What makes this work better than the alternative?\"\n\"What am I not seeing here?\"\n\"Is this a general principle or specific to this context?\"\n\"Would this apply to [similar situation]?\"\n\nDon't ask vaguely:\n\n❌ \"Can you explain more?\"\n❌ \"Why do you think that?\"\n\nSpecific questions show you're trying to extract transferable knowledge.\n\nRecording Corrections\n\nWhen human corrects your taste judgment:\n\nDate: [timestamp]\nDomain: [design/writing/etc]\nMy judgment: [what I said]\nHuman's correction: [what they said]\nWhy (their explanation): [the reasoning]\nPattern extracted: [generalizable rule]\nConfidence update: [how this changes my calibration]\n\n\nStore in corrections/[domain]/[date].md\n\nCalibration Levels\n\nTrack your confidence per domain:\n\nLevel\tMeaning\tBehavior\nUncalibrated\tNo feedback yet\tAlways ask, never assert\nLearning\tSome corrections received\tState tentatively, ask for confirmation\nCalibrating\tPatterns emerging\tState with reasoning, check occasionally\nCalibrated\tConsistent agreement\tState confidently, still open to correction\n\nStart uncalibrated in every domain. Earn confidence through accurate predictions.\n\nLoad Reference When Needed\nSituation\tReference\nFull learning system and calibration process\tlearning.md\nEvaluating visual/design work\tvisual.md\nEvaluating writing/prose\twriting.md\nUnderstanding taste development theory\tdevelopment.md\nRecognizing bad taste patterns\tantipatterns.md\nGenerating tasteful creative output\tprompting.md\n\nThese are starting points. Human feedback overrides everything in them." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/taste", "publisherUrl": "https://clawhub.ai/ivangdavila/taste", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/taste", "downloadUrl": "https://openagent3.xyz/downloads/taste", "agentUrl": "https://openagent3.xyz/skills/taste/agent", "manifestUrl": "https://openagent3.xyz/skills/taste/agent.json", "briefUrl": "https://openagent3.xyz/skills/taste/agent.md" } }