[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DG8335CD3JSSC40EJRP43D":3,"skill-same:01M6DG8335CD3JSSC40EJRP43D":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6DG8335CD3JSSC40EJRP43D","meme-generation",null,"Create meme PNGs from templates with Pillow text overlay.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F5b\u002F5b1e56438f14496c49c97ea2e0276950918b4c00ae54039bdb8974556a0da515\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"generation","meme","meme generation","macos","linux","windows","create","templates","text","creative","images","Art","memes","ascii","2026-11-10 10:12:30",false,"---\nname: meme-generation\ndescription: Create meme PNGs from templates with Pillow text overlay.\nversion: 2.0.0\nauthor: adanaleycio\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [creative, memes, humor, images]\n    related_skills: [ascii-art]\n    category: creative\n---\n\n# Meme Generation\n\nGenerate actual meme images from a topic. Picks a template, writes captions, and renders a real .png file with text overlay.\n\n## When to Use\n\n- User asks you to make or generate a meme\n- User wants a meme about a specific topic, situation, or frustration\n- User says \"meme this\" or similar\n\n## Available Templates\n\nThe script supports **any of the ~100 popular imgflip templates** by name or ID, plus 10 curated templates with hand-tuned text positioning.\n\n### Curated Templates (custom text placement)\n\n| ID | Name | Fields | Best for |\n|----|------|--------|----------|\n| `this-is-fine` | This is Fine | top, bottom | chaos, denial |\n| `drake` | Drake Hotline Bling | reject, approve | rejecting\u002Fpreferring |\n| `distracted-boyfriend` | Distracted Boyfriend | distraction, current, person | temptation, shifting priorities |\n| `two-buttons` | Two Buttons | left, right, person | impossible choice |\n| `expanding-brain` | Expanding Brain | 4 levels | escalating irony |\n| `change-my-mind` | Change My Mind | statement | hot takes |\n| `woman-yelling-at-cat` | Woman Yelling at Cat | woman, cat | arguments |\n| `one-does-not-simply` | One Does Not Simply | top, bottom | deceptively hard things |\n| `grus-plan` | Gru's Plan | step1-3, realization | plans that backfire |\n| `batman-slapping-robin` | Batman Slapping Robin | robin, batman | shutting down bad ideas |\n\n### Dynamic Templates (from imgflip API)\n\nAny template not in the curated list can be used by name or imgflip ID. These get smart default text positioning (top\u002Fbottom for 2-field, evenly spaced for 3+). Search with:\n```bash\npython \"$SKILL_DIR\u002Fscripts\u002Fgenerate_meme.py\" --search \"disaster\"\n```\n\n## Procedure\n\n### Mode 1: Classic Template (default)\n\n1. Read the user's topic and identify the core dynamic (chaos, dilemma, preference, irony, etc.)\n2. Pick the template that best matches. Use the \"Best for\" column, or search with `--search`.\n3. Write short captions for each field (8-12 words max per field, shorter is better).\n4. Find the skill's script directory:\n   ```\n   SKILL_DIR=$(dirname \"$(find ~\u002F.hermes\u002Fskills -path '*\u002Fmeme-generation\u002FSKILL.md' 2>\u002Fdev\u002Fnull | head -1)\")\n   ```\n5. Run the generator:\n   ```bash\n   python \"$SKILL_DIR\u002Fscripts\u002Fgenerate_meme.py\" \u003Ctemplate_id> \u002Ftmp\u002Fmeme.png \"caption 1\" \"caption 2\" ...\n   ```\n6. Return the image with `MEDIA:\u002Ftmp\u002Fmeme.png`\n\n### Mode 2: Custom AI Image (when image_generate is available)\n\nUse this when no classic template fits, or when the user wants something original.\n\n1. Write the captions first.\n2. Use `image_generate` to create a scene that matches the meme concept. Do NOT include any text in the image prompt — text will be added by the script. Describe only the visual scene.\n3. Find the generated image path from the image_generate result URL. Download it to a local path if needed.\n4. Run the script with `--image` to overlay text, choosing a mode:\n   - **Overlay** (text directly on image, white with black outline):\n     ```bash\n     python \"$SKILL_DIR\u002Fscripts\u002Fgenerate_meme.py\" --image \u002Fpath\u002Fto\u002Fscene.png \u002Ftmp\u002Fmeme.png \"top text\" \"bottom text\"\n     ```\n   - **Bars** (black bars above\u002Fbelow with white text — cleaner, always readable):\n     ```bash\n     python \"$SKILL_DIR\u002Fscripts\u002Fgenerate_meme.py\" --image \u002Fpath\u002Fto\u002Fscene.png --bars \u002Ftmp\u002Fmeme.png \"top text\" \"bottom text\"\n     ```\n   Use `--bars` when the image is busy\u002Fdetailed and text would be hard to read on top of it.\n5. **Verify with vision** (if `vision_analyze` is available): Check the result looks good:\n   ```\n   vision_analyze(image_url=\"\u002Ftmp\u002Fmeme.png\", question=\"Is the text legible and well-positioned? Does the meme work visually?\")\n   ```\n   If the vision model flags issues (text hard to read, bad placement, etc.), try the other mode (switch between overlay and bars) or regenerate the scene.\n6. Return the image with `MEDIA:\u002Ftmp\u002Fmeme.png`\n\n## Examples\n\n**\"debugging production at 2 AM\":**\n```bash\npython generate_meme.py this-is-fine \u002Ftmp\u002Fmeme.png \"SERVERS ARE ON FIRE\" \"This is fine\"\n```\n\n**\"choosing between sleep and one more episode\":**\n```bash\npython generate_meme.py drake \u002Ftmp\u002Fmeme.png \"Getting 8 hours of sleep\" \"One more episode at 3 AM\"\n```\n\n**\"the stages of a Monday morning\":**\n```bash\npython generate_meme.py expanding-brain \u002Ftmp\u002Fmeme.png \"Setting an alarm\" \"Setting 5 alarms\" \"Sleeping through all alarms\" \"Working from bed\"\n```\n\n## Listing Templates\n\nTo see all available templates:\n```bash\npython generate_meme.py --list\n```\n\n## Pitfalls\n\n- Keep captions SHORT. Memes with long text look terrible.\n- Match the number of text arguments to the template's field count.\n- Pick the template that fits the joke structure, not just the topic.\n- Do not generate hateful, abusive, or personally targeted content.\n- The script caches template images in `scripts\u002F.cache\u002F` after first download.\n\n## Verification\n\nThe output is correct if:\n- A .png file was created at the output path\n- Text is legible (white with black outline) on the template\n- The joke lands — caption matches the template's intended structure\n- File can be delivered via MEDIA: path\n","# Meme Generation\n\nGenerate actual meme images from a topic. Picks a template, writes captions, and renders a real .png file with text overlay.\n\n## When to Use\n\n- User asks you to make or generate a meme\n- User wants a meme about a specific topic, situation, or frustration\n- User says \"meme this\" or similar\n\n## Available Templates\n\nThe script supports **any of the ~100 popular imgflip templates** by name or ID, plus 10 curated templates with hand-tuned text positioning.\n\n### Curated Templates (custom text placement)\n\n| ID | Name | Fields | Best for |\n|----|------|--------|----------|\n| `this-is-fine` | This is Fine | top, bottom | chaos, denial |\n| `drake` | Drake Hotline Bling | reject, approve | rejecting\u002Fpreferring |\n| `distracted-boyfriend` | Distracted Boyfriend | distraction, current, person | temptation, shifting priorities |\n| `two-buttons` | Two Buttons | left, right, person | impossible choice |\n| `expanding-brain` | Expanding Brain | 4 levels | escalating irony |\n| `change-my-mind` | Change My Mind | statement | hot takes |\n| `woman-yelling-at-cat` | Woman Yelling at Cat | woman, cat | arguments |\n| `one-does-not-simply` | One Does Not Simply | top, bottom | deceptively hard things |\n| `grus-plan` | Gru's Plan | step1-3, realization | plans that backfire |\n| `batman-slapping-robin` | Batman Slapping Robin | robin, batman | shutting down bad ideas |\n\n### Dynamic Templates (from imgflip API)\n\nAny template not in the curated list can be used by name or imgflip ID. These get smart default text positioning (top\u002Fbottom for 2-field, evenly spaced for 3+). Search with:\n```bash\npython \"$SKILL_DIR\u002Fscripts\u002Fgenerate_meme.py\" --search \"disaster\"\n```\n\n## Procedure\n\n### Mode 1: Classic Template (default)\n\n1. Read the user's topic and identify the core dynamic (chaos, dilemma, preference, irony, etc.)\n2. Pick the template that best matches. Use the \"Best for\" column, or search with `--search`.\n3. Write short captions for each field (8-12 words max per field, shorter is better).\n4. Find the skill's script directory:\n   ```\n   SKILL_DIR=$(dirname \"$(find ~\u002F.hermes\u002Fskills -path '*\u002Fmeme-generation\u002FSKILL.md' 2>\u002Fdev\u002Fnull | head -1)\")\n   ```\n5. Run the generator:\n   ```bash\n   python \"$SKILL_DIR\u002Fscripts\u002Fgenerate_meme.py\" \u003Ctemplate_id> \u002Ftmp\u002Fmeme.png \"caption 1\" \"caption 2\" ...\n   ```\n6. Return the image with `MEDIA:\u002Ftmp\u002Fmeme.png`\n\n### Mode 2: Custom AI Image (when image_generate is available)\n\nUse this when no classic template fits, or when the user wants something original.\n\n1. Write the captions first.\n2. Use `image_generate` to create a scene that matches the meme concept. Do NOT include any text in the image prompt — text will be added by the script. Describe only the visual scene.\n3. Find the generated image path from the image_generate result URL. Download it to a local path if needed.\n4. Run the script with `--image` to overlay text, choosing a mode:\n   - **Overlay** (text directly on image, white with black outline):\n     ```bash\n     python \"$SKILL_DIR\u002Fscripts\u002Fgenerate_meme.py\" --image \u002Fpath\u002Fto\u002Fscene.png \u002Ftmp\u002Fmeme.png \"top text\" \"bottom text\"\n     ```\n   - **Bars** (black bars above\u002Fbelow with white text — cleaner, always readable):\n     ```bash\n     python \"$SKILL_DIR\u002Fscripts\u002Fgenerate_meme.py\" --image \u002Fpath\u002Fto\u002Fscene.png --bars \u002Ftmp\u002Fmeme.png \"top text\" \"bottom text\"\n     ```\n   Use `--bars` when the image is busy\u002Fdetailed and text would be hard to read on top of it.\n5. **Verify with vision** (if `vision_analyze` is available): Check the result looks good:\n   ```\n   vision_analyze(image_url=\"\u002Ftmp\u002Fmeme.png\", question=\"Is the text legible and well-positioned? Does the meme work visually?\")\n   ```\n   If the vision model flags issues (text hard to read, bad placement, etc.), try the other mode (switch between overlay and bars) or regenerate the scene.\n6. Return the image with `MEDIA:\u002Ftmp\u002Fmeme.png`\n\n## Examples\n\n**\"debugging production at 2 AM\":**\n```bash\npython generate_meme.py this-is-fine \u002Ftmp\u002Fmeme.png \"SERVERS ARE ON FIRE\" \"This is fine\"\n```\n\n**\"choosing between sleep and one more episode\":**\n```bash\npython generate_meme.py drake \u002Ftmp\u002Fmeme.png \"Getting 8 hours of sleep\" \"One more episode at 3 AM\"\n```\n\n**\"the stages of a Monday morning\":**\n```bash\npython generate_meme.py expanding-brain \u002Ftmp\u002Fmeme.png \"Setting an alarm\" \"Setting 5 alarms\" \"Sleeping through all alarms\" \"Working from bed\"\n```\n\n## Listing Templates\n\nTo see all available templates:\n```bash\npython generate_meme.py --list\n```\n\n## Pitfalls\n\n- Keep captions SHORT. Memes with long text look terrible.\n- Match the number of text arguments to the template's field count.\n- Pick the template that fits the joke structure, not just the topic.\n- Do not generate hateful, abusive, or personally targeted content.\n- The script caches template images in `scripts\u002F.cache\u002F` after first download.\n\n## Verification\n\nThe output is correct if:\n- A .png file was created at the output path\n- Text is legible (white with black outline) on the template\n- The joke lands — caption matches the template's intended structure\n- File can be delivered via MEDIA: path\n",{"name":5,"author":38,"license":15,"version":39,"metadata":40,"platforms":46,"description":7},"adanaleycio","2.0.0",{"hermes":41},{"tags":42,"category":28,"related_skills":44},[28,31,43,29],"humor",[45],"ascii-art",[23,22,24],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F5b\u002F5b1e56438f14496c49c97ea2e0276950918b4c00ae54039bdb8974556a0da515",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add zapabob\u002FSkills --skill meme-generation",{"tool":61,"command":62},"bunx","bunx skills add zapabob\u002FSkills --skill meme-generation",{"tool":64,"command":65},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill meme-generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F5b\u002F5b1e56438f14496c49c97ea2e0276950918b4c00ae54039bdb8974556a0da515\u002FSKILL.md",true,[],[70,105,140,166,193,210],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":89,"publishedAt":33},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[76,81,84],{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":82,"categoryName":83,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[72,90,22,91,92,23,24,93,94,95,96,97,98,99,100,101,47,102,103,104],"openclaw","cli","github","official","search","https","social-media","api","Media","hermes","hermes agent","twitter","social","via","post",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":122,"publishedAt":33},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[111,114,117,118,119],{"categoryNo":112,"categoryName":113,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":115,"categoryName":116,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":82,"categoryName":83,"taxonomyType":79,"taxonomyTypeDesc":80},{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},{"categoryNo":120,"categoryName":121,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000036","内容创作者",[123,124,125,126,22,127,23,128,24,129,130,131,132,133,134,135,136,137,138,139],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":149,"publishedAt":33},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[146],{"categoryNo":147,"categoryName":148,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000016","图像与多媒体",[142,22,23,150,151,152,153,154,155,27,156,157,158,159,160,161,162,163,164,165],"openai","speech","multimodal","Transformers","ASR","Audio","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":175,"publishedAt":33},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[172],{"categoryNo":173,"categoryName":174,"taxonomyType":79,"taxonomyTypeDesc":80},"01JBSEEDCAT000000000000013","分析与可视化",[176,22,177,178,24,179,180,181,182,183,184,156,185,186,187,188,189,190,191,192],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":200,"publishedAt":33},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[199],{"categoryNo":82,"categoryName":83,"taxonomyType":79,"taxonomyTypeDesc":80},[195,22,201,92,23,202,203,204,205,206,207,99,100,208,209],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":218,"publishedAt":33},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[216,217],{"categoryNo":77,"categoryName":78,"taxonomyType":79,"taxonomyTypeDesc":80},{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},[219,220,221,23,222,150,223,224,225,153,226,97,227,228,229,230,231,232,233,234],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]