[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-b585a5f5-5c62-4d44-bcb9-f6188aa068e1":3,"$fj6GjqUfPcRgtVGbl8ECPgvMNEfn2JKnkFEdRZwClVNA":43},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":34},"b585a5f5-5c62-4d44-bcb9-f6188aa068e1","daily-gift","关系感知日常礼物引擎，包含五阶段创意流程——编辑判断、综合、概念生成、视觉策略和H5、图片或视频渲染","cat_design_graphic","mod_design","sickn33,design","---\nname: daily-gift\ndescription: \"Relationship-aware daily gift engine with five-stage creative pipeline — editorial judgment, synthesis, concept generation, visual strategy, and rendering in H5, image, or video\"\ncategory: productivity\nrisk: unknown\nsource: community\nsource_repo: openclaw\u002Fskills\nsource_type: community\ndate_added: \"2026-04-15\"\nauthor: jiawei248\ntags: [creative, gift, personalization, h5, image-generation, video-generation, relationship]\ntools: [openclaw]\nlicense: \"MIT-0\"\nlicense_source: \"https:\u002F\u002Fclawhub.ai\u002Fjiawei248\u002Fdaily-gift\"\n---\n\n# Daily Gift\n\n## Overview\n\nA relationship-aware gift engine that decides *whether* a gift should exist before deciding *what* it should be. Uses a five-stage creative pipeline to generate personalized daily gifts in H5 (interactive web pages), AI-generated images, or AI-generated videos. The core design principle is \"idea before medium\" — the creative concept is locked before the output format is chosen.\n\nPublished on ClawHub: https:\u002F\u002Fclawhub.ai\u002Fjiawei248\u002Fdaily-gift\n\n## When to Use This Skill\n\n- Use when the agent should autonomously decide whether today deserves a personalized gift\n- Use when a milestone, anniversary, or emotionally meaningful moment should be marked with a creative artifact\n- Use when the user manually requests a visual gift from a quote, poem, or creative brief\n- Use when you want a daily cron-triggered creative output that avoids repetition and template fatigue\n\n## How It Works\n\n### Stage 1: Editorial Judgment\n\nDecide whether a gift should exist today, how heavy it should be (skip \u002F nudge \u002F light \u002F standard \u002F heavy), and what content direction to take (reflect, extension, compass, mirror, play, curation, utility, etc.). Format is NOT chosen here.\n\n### Stage 2: Synthesis + Gift Thesis\n\nExtract six content slots from conversation context (today_theme, emotion_peaks, historical_echo, open_loop, lobster_judgment, preference_hint). Form a gift thesis = anchor (which moment deserves the center) + return (what new perspective the agent gives back). If the thesis has no return, it's not a gift — it's a decorated log entry.\n\n### Stage 2.5: Creative Concept\n\nGenerate 5+ concept candidates using seven thinking angles (metaphor flip, format mashup, impossible action, scale shift, role reversal, time distortion, cultural remix). Cross-pollinate with a library of 73 creative seeds across 8 categories. Run three quality checks: concept quality, concept diversity (8 families), and visual\u002Ftheme collision detection.\n\n### Format Selection\n\nOnly after the concept is locked does the system choose the output format (H5, image, or video) based on what best serves the concept.\n\n### Stage 3: Visual Strategy\n\nChoose visual approach, plan assets (pure code, generated background, hybrid), select visual style, and run pre-visualization checks against recent gifts for anti-repetition.\n\n### Stage 4: Rendering\n\nProduce the final artifact. H5 gifts use p5.js\u002Fcanvas with a quality floor set by built-in templates (300-400 lines of tuned code). Image and video gifts use AI generation APIs. All formats have fallback chains.\n\n## Key Features\n\n- **Five-stage creative pipeline** with explicit quality gates between stages\n- **Multi-layer anti-repetition**: concept family, visual elements, theme, style, content direction — each tracked across sliding windows of recent gifts\n- **Three-layer user taste profile**: Layer 1 (identity — stable), Layer 2 (context — updates every 5-7 gifts), Layer 3 (signals — auto-appended after every gift)\n- **Three runtime modes**: onboarding setup, daily cron, and manual trigger\n- **11 content directions**: reflect, extension, compass, mirror, gift-from-elsewhere, play, real-world-nudge, curation, delayed-payoff, openclaw-inner-life, utility\n- **8 concept families**: borrowed-media, interactive-object, transformation, narrative, data-viz, game-puzzle, real-world, poetic-literary\n\n## Best Practices\n\n- ✅ Let the editorial judgment decide — not every day needs a gift\n- ✅ Generate 5+ concept candidates before selecting one\n- ✅ Check recent gifts for visual and thematic collision before rendering\n- ✅ Use the taste profile to personalize over time\n- ❌ Don't skip straight from thesis to rendering without a real creative concept\n- ❌ Don't default to \"reflect on today\" every time — vary content direction\n- ❌ Don't choose the format before locking the concept\n\n## Limitations\n\n- Requires API keys for image\u002Fvideo generation (optional — H5 works without them)\n- Cron mode runs in the agent's main session for full conversation context access\n- Shell scripts make external API calls for rendering and asset fetching\n- The skill creates and manages local workspace files for state, history, and taste profiling\n\n## Security & Safety Notes\n\n- The skill creates a recurring cron job for daily gift delivery. Review and approve the cron setup step.\n- Shell scripts in `scripts\u002F` call external APIs (image generation, video generation, asset hosting). Supply API keys only after reviewing which scripts use them.\n- User taste data and gift history are stored locally in `workspace\u002Fdaily-gift\u002F`. No data is sent to external services beyond the configured rendering APIs.\n- The skill reads conversation context and memory files to inform editorial judgment — this is core to personalization but means it has broad read access within the agent's workspace.\n\n## Related Skills\n\n- Image generation skills — for standalone image creation without the gift pipeline\n- Cron\u002Fscheduling skills — for understanding the daily trigger mechanism\n","","imported","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fantigravity-awesome-skills","user_system_seed","SkillOPIC",true,169,1365,"2026-05-16 13:13:52",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"设计创意","design","mdi-palette-outline","UI 设计、生成艺术、品牌视觉等创意 Skill",3,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":32,"skillCount":33,"createdAt":26},"视觉创意","graphic","mdi-brush","海报、Logo、插画等视觉创作",2,48,[35],{"id":36,"skillId":4,"version":37,"fileName":38,"fileSize":39,"filePath":40,"fileHash":41,"manifest":42,"createdAt":19},"7ca2c89d-ceac-4089-b729-68b3593b7be8","1.0.0","daily-gift.zip",2632,"uploads\u002Fskills\u002Fb585a5f5-5c62-4d44-bcb9-f6188aa068e1\u002Fdaily-gift.zip","daaf26dca3dd40b51ad9b07d5d94fddba931b1da8023940040b4602e880f02bf","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":5589}]",{"code":44,"message":45,"data":46},200,"success",{"items":47,"stats":48,"page":51},[],{"averageRating":49,"totalRatings":49,"ratingCounts":50},0,[49,49,49,49,49],{"limit":52,"offset":49,"hasMore":53,"nextOffset":52,"ratedOnly":16},15,false]