[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ADXE0G2XVPABB79KMT7QMA":3,"skill-same:01M7ADXE0G2XVPABB79KMT7QMA":49},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7ADXE0G2XVPABB79KMT7QMA","shorts-factory",null,"Use when producing short-form vertical or square videos (Shorts, Reels, TikTok) end to end from a topic -- script, narration, alignment, stock b-roll, scene plan, render, and ffmpeg composite with captions. Assembles tts + extensions\u002Fasr + extensions\u002Fstock-footage + animation-direction\u002Fremotion-render into a MoneyPrinterTurbo-equivalent pipeline.","Leostruka\u002Fdevin-bundle","Leostruka","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F81370685?v=4","01M7AD8MAK63VDNAWRDRRRW04N","leandro ostruka","01M7AD8MBS65YDS1KMMV7YPM07",0,"MIT","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fshorts-factory\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: shorts-factory\ndescription: Use when producing short-form vertical or square videos (Shorts, Reels, TikTok) end to end from a topic -- script, narration, alignment, stock b-roll, scene plan, render, and ffmpeg composite with captions. Assembles tts + extensions\u002Fasr + extensions\u002Fstock-footage + animation-direction\u002Fremotion-render into a MoneyPrinterTurbo-equivalent pipeline.\ntriggers: [user, model]\n---\n\n# Shorts Factory\n\nTopic in, captioned short video out. No video editor, no paid TTS\u002FASR.\nReuses bundle pieces; the only new moving part is\n`extensions\u002Fstock-footage\u002Ffetch.py` for b-roll clips.\n\n## Pipeline\n\n```\ntopic -> script -> narration WAVs -> transcript segments\n      -> scene-plan v2 (+ stock clips) -> render -> ffmpeg composite\n```\n\n### 1. Script (agent prompt pattern)\n\nPrompt the agent for a spoken script, one line per caption beat:\n\n- Target 45-90 words for a 30-60s short (160 WPM read time).\n- One sentence per line; each line becomes a narration segment and a\n  caption. No stage directions, no headers.\n- End with a hook or call to action line.\n\n### 2. Narration (tts skill)\n\nOne WAV per script line via `extensions\u002Fvoicebox\u002Fwrapper.py`:\n\n```bash\npython extensions\u002Fvoicebox\u002Fwrapper.py generate \\\n    --text \"\u003Cline>\" --voice \u003Cid> --out narration\u002Fline_01.wav\n```\n\nDefault voicebox backend, or `--backend voicestudio` \u002F\n`VB_BACKEND=voicestudio` for the VoiceStudio app on 127.0.0.1:3900.\n`doctor` first; `status: missing` means tell the user to start the\nbackend. Concatenate WAVs (ffmpeg `concat` demuxer) into `narration.wav`\nrecording each line's cumulative start offset.\n\n### 3. Alignment (extensions\u002Fasr)\n\n```bash\npython extensions\u002Fasr\u002Ftranscribe.py narration.wav --model base\n# -> {\"ok\": true, \"segments\": [{start, end, text}], ...}\n```\n\nSegments anchor captions and scene `sync_range`s. Requires\n`extensions\u002Fasr\u002Fbootstrap.py` to have fetched whisper.cpp + model\n(explicit fetch, never silent). Missing binaries -> `ok:false` + hint.\n\n### 4. B-roll (extensions\u002Fstock-footage)\n\n```bash\npython extensions\u002Fstock-footage\u002Ffetch.py search --query \"\u003Ckw>\" \\\n    --provider pexels --orientation portrait --per-page 10\npython extensions\u002Fstock-footage\u002Ffetch.py download --provider pexels \\\n    --id \u003Cid> --out clips\u002Fclip_01.mp4\n```\n\nKeys from `PEXELS_API_KEY` \u002F `PIXABAY_API_KEY`; absent ->\n`{\"ok\": false, \"status\": \"missing\", \"hint\": ...}` with zero network\ncalls. Download picks the smallest file meeting `--min-width`\n(default 720). Stock clips are optional: skip this stage and let the\nrender stage produce all visuals when no keys are set.\n\n### 5. Scene plan (scene-plan v2)\n\nReuse the scene-plan v2 schema from `skills\u002Fanimation-direction`\n(`craft-bridge` scene_manifest v1 + `motion_spec` + `sync_range`):\n\n```json\n{\"scenes\": [{\"id\": \"s1\", \"sync_range\": [0.0, 3.2],\n  \"visual\": {\"type\": \"kinetic_text\", \"props\": {...}},\n  \"motion_spec\": {\"easing\": \"easeOut\", \"enter\": \"fade\",\n                  \"exit\": \"fade\", \"enter_s\": 0.3, \"exit_s\": 0.3},\n  \"broll\": \"clips\u002Fclip_01.mp4\"}]}\n```\n\nOne scene per transcript segment\u002Fbeat. `broll` is a local downloaded\nclip path; `visual` covers text\u002Fdiagram beats the same way as\nanimation-direction. Validate with\n`extensions\u002Fremotion-render\u002Fplan_check.py` and get plan approval before\nrendering (hard gate, same as animation-direction).\n\n### 6. Render\n\n```bash\npython extensions\u002Fremotion-render\u002Frender.py plan.json --workdir out\u002F\n```\n\nRemotion renders the scene visuals\u002Foverlays. Full 3D scenes route to\n`operate-blender`; pure text+b-roll plans may skip render entirely and\ngo straight to composite.\n\n### 7. Composite (ffmpeg)\n\n```bash\n# 9:16 shorts (1080x1920); use 1920x1080 for 16:9, 1080x1080 for 1:1\nffmpeg -i render.mp4 -i narration.wav \\\n  -vf \"scale=1080:1920:force_original_aspect_ratio=decrease,\\\npad=1080:1920:(ow-iw)\u002F2:(oh-ih)\u002F2,subtitles=captions.srt:force_style='Fontsize=14'\" \\\n  -c:v libx264 -c:a aac -shortest short.mp4\n```\n\nBuild `captions.srt` from ASR segments. Pick aspect per platform:\n9:16 Shorts\u002FReels\u002FTikTok (default), 1:1 feed, 16:9 YouTube.\n\n## Example flow\n\n```bash\nW=extensions\u002Fvoicebox\u002Fwrapper.py\npython $W doctor                                    # backend up?\npython $W generate --text \"Three facts about octopi.\" \\\n    --voice af_heart --out n\u002Fline_01.wav            # per line...\nffmpeg -f concat -safe 0 -i wavlist.txt -c copy narration.wav\npython extensions\u002Fasr\u002Ftranscribe.py narration.wav > transcript.json\npython extensions\u002Fstock-footage\u002Ffetch.py search \\\n    --query \"octopus ocean\" --orientation portrait > hits.json\npython extensions\u002Fstock-footage\u002Ffetch.py download --id 857195 \\\n    --out clips\u002Fc1.mp4\n# agent writes plan.json (scene-plan v2) from transcript + hits\npython extensions\u002Fremotion-render\u002Fplan_check.py plan.json\npython extensions\u002Fremotion-render\u002Frender.py plan.json --workdir out\u002F\nffmpeg -i out\u002Fout.mp4 -i narration.wav -vf \"scale=1080:1920,subtitles=c.srt\" \\\n    -c:v libx264 -c:a aac -shortest short.mp4\n```\n\n## Typed errors per stage\n\n| Stage | Failure | Envelope |\n|---|---|---|\n| tts | backend down | `status:\"missing\"` + start hint |\n| tts | bad voice\u002Fengine | `status:\"error\"`, `error` detail |\n| asr | missing binary\u002Fmodel | `ok:false` + bootstrap hint |\n| asr | fetch\u002Fdecoder failure | `ok:false`, `error:\"fetch_error:*\"` |\n| stock | no API key | `status:\"missing\"` + `hint`, no network |\n| stock | HTTP\u002Ftimeout | `status:\"error\"`, `error:\"http_error:\u003Ccode>\"` |\n| render | plan invalid | `plan_check.py` findings, gate blocks |\n| composite | missing input | ffmpeg nonzero exit; surface stderr |\n\nNever fabricate: no fake audio, no fake transcript, no fake clips.\nEvery stage degrades to a typed error, not a traceback.\n\n## Non-goals\n\n- No auto-publishing or platform upload (YouTube\u002FTikTok APIs).\n- No batch mode, watch folder, or scheduling daemon.\n- No paid TTS\u002FASR\u002Fstock services; no API keys beyond Pexels\u002FPixabay.\n- No long-form video; 3 minutes max is a hard ceiling.\n\n## Boundaries\n\n- Localhost services only (voicebox, VoiceStudio). Keys stay in env,\n  never logged or written to plans.\n- Stock clips carry provider license terms; keep `hits[].url` for\n  attribution.\n- Plan approval gate is mandatory before `render.py` on non-trivial\n  plans, same as animation-direction.\n","# Shorts Factory\n\nTopic in, captioned short video out. No video editor, no paid TTS\u002FASR.\nReuses bundle pieces; the only new moving part is\n`extensions\u002Fstock-footage\u002Ffetch.py` for b-roll clips.\n\n## Pipeline\n\n```\ntopic -> script -> narration WAVs -> transcript segments\n      -> scene-plan v2 (+ stock clips) -> render -> ffmpeg composite\n```\n\n### 1. Script (agent prompt pattern)\n\nPrompt the agent for a spoken script, one line per caption beat:\n\n- Target 45-90 words for a 30-60s short (160 WPM read time).\n- One sentence per line; each line becomes a narration segment and a\n  caption. No stage directions, no headers.\n- End with a hook or call to action line.\n\n### 2. Narration (tts skill)\n\nOne WAV per script line via `extensions\u002Fvoicebox\u002Fwrapper.py`:\n\n```bash\npython extensions\u002Fvoicebox\u002Fwrapper.py generate \\\n    --text \"\u003Cline>\" --voice \u003Cid> --out narration\u002Fline_01.wav\n```\n\nDefault voicebox backend, or `--backend voicestudio` \u002F\n`VB_BACKEND=voicestudio` for the VoiceStudio app on 127.0.0.1:3900.\n`doctor` first; `status: missing` means tell the user to start the\nbackend. Concatenate WAVs (ffmpeg `concat` demuxer) into `narration.wav`\nrecording each line's cumulative start offset.\n\n### 3. Alignment (extensions\u002Fasr)\n\n```bash\npython extensions\u002Fasr\u002Ftranscribe.py narration.wav --model base\n# -> {\"ok\": true, \"segments\": [{start, end, text}], ...}\n```\n\nSegments anchor captions and scene `sync_range`s. Requires\n`extensions\u002Fasr\u002Fbootstrap.py` to have fetched whisper.cpp + model\n(explicit fetch, never silent). Missing binaries -> `ok:false` + hint.\n\n### 4. B-roll (extensions\u002Fstock-footage)\n\n```bash\npython extensions\u002Fstock-footage\u002Ffetch.py search --query \"\u003Ckw>\" \\\n    --provider pexels --orientation portrait --per-page 10\npython extensions\u002Fstock-footage\u002Ffetch.py download --provider pexels \\\n    --id \u003Cid> --out clips\u002Fclip_01.mp4\n```\n\nKeys from `PEXELS_API_KEY` \u002F `PIXABAY_API_KEY`; absent ->\n`{\"ok\": false, \"status\": \"missing\", \"hint\": ...}` with zero network\ncalls. Download picks the smallest file meeting `--min-width`\n(default 720). Stock clips are optional: skip this stage and let the\nrender stage produce all visuals when no keys are set.\n\n### 5. Scene plan (scene-plan v2)\n\nReuse the scene-plan v2 schema from `skills\u002Fanimation-direction`\n(`craft-bridge` scene_manifest v1 + `motion_spec` + `sync_range`):\n\n```json\n{\"scenes\": [{\"id\": \"s1\", \"sync_range\": [0.0, 3.2],\n  \"visual\": {\"type\": \"kinetic_text\", \"props\": {...}},\n  \"motion_spec\": {\"easing\": \"easeOut\", \"enter\": \"fade\",\n                  \"exit\": \"fade\", \"enter_s\": 0.3, \"exit_s\": 0.3},\n  \"broll\": \"clips\u002Fclip_01.mp4\"}]}\n```\n\nOne scene per transcript segment\u002Fbeat. `broll` is a local downloaded\nclip path; `visual` covers text\u002Fdiagram beats the same way as\nanimation-direction. Validate with\n`extensions\u002Fremotion-render\u002Fplan_check.py` and get plan approval before\nrendering (hard gate, same as animation-direction).\n\n### 6. Render\n\n```bash\npython extensions\u002Fremotion-render\u002Frender.py plan.json --workdir out\u002F\n```\n\nRemotion renders the scene visuals\u002Foverlays. Full 3D scenes route to\n`operate-blender`; pure text+b-roll plans may skip render entirely and\ngo straight to composite.\n\n### 7. Composite (ffmpeg)\n\n```bash\n# 9:16 shorts (1080x1920); use 1920x1080 for 16:9, 1080x1080 for 1:1\nffmpeg -i render.mp4 -i narration.wav \\\n  -vf \"scale=1080:1920:force_original_aspect_ratio=decrease,\\\npad=1080:1920:(ow-iw)\u002F2:(oh-ih)\u002F2,subtitles=captions.srt:force_style='Fontsize=14'\" \\\n  -c:v libx264 -c:a aac -shortest short.mp4\n```\n\nBuild `captions.srt` from ASR segments. Pick aspect per platform:\n9:16 Shorts\u002FReels\u002FTikTok (default), 1:1 feed, 16:9 YouTube.\n\n## Example flow\n\n```bash\nW=extensions\u002Fvoicebox\u002Fwrapper.py\npython $W doctor                                    # backend up?\npython $W generate --text \"Three facts about octopi.\" \\\n    --voice af_heart --out n\u002Fline_01.wav            # per line...\nffmpeg -f concat -safe 0 -i wavlist.txt -c copy narration.wav\npython extensions\u002Fasr\u002Ftranscribe.py narration.wav > transcript.json\npython extensions\u002Fstock-footage\u002Ffetch.py search \\\n    --query \"octopus ocean\" --orientation portrait > hits.json\npython extensions\u002Fstock-footage\u002Ffetch.py download --id 857195 \\\n    --out clips\u002Fc1.mp4\n# agent writes plan.json (scene-plan v2) from transcript + hits\npython extensions\u002Fremotion-render\u002Fplan_check.py plan.json\npython extensions\u002Fremotion-render\u002Frender.py plan.json --workdir out\u002F\nffmpeg -i out\u002Fout.mp4 -i narration.wav -vf \"scale=1080:1920,subtitles=c.srt\" \\\n    -c:v libx264 -c:a aac -shortest short.mp4\n```\n\n## Typed errors per stage\n\n| Stage | Failure | Envelope |\n|---|---|---|\n| tts | backend down | `status:\"missing\"` + start hint |\n| tts | bad voice\u002Fengine | `status:\"error\"`, `error` detail |\n| asr | missing binary\u002Fmodel | `ok:false` + bootstrap hint |\n| asr | fetch\u002Fdecoder failure | `ok:false`, `error:\"fetch_error:*\"` |\n| stock | no API key | `status:\"missing\"` + `hint`, no network |\n| stock | HTTP\u002Ftimeout | `status:\"error\"`, `error:\"http_error:\u003Ccode>\"` |\n| render | plan invalid | `plan_check.py` findings, gate blocks |\n| composite | missing input | ffmpeg nonzero exit; surface stderr |\n\nNever fabricate: no fake audio, no fake transcript, no fake clips.\nEvery stage degrades to a typed error, not a traceback.\n\n## Non-goals\n\n- No auto-publishing or platform upload (YouTube\u002FTikTok APIs).\n- No batch mode, watch folder, or scheduling daemon.\n- No paid TTS\u002FASR\u002Fstock services; no API keys beyond Pexels\u002FPixabay.\n- No long-form video; 3 minutes max is a hard ceiling.\n\n## Boundaries\n\n- Localhost services only (voicebox, VoiceStudio). Keys stay in env,\n  never logged or written to plans.\n- Stock clips carry provider license terms; keep `hits[].url` for\n  attribution.\n- Plan approval gate is mandatory before `render.py` on non-trivial\n  plans, same as animation-direction.\n",{"name":5,"triggers":24,"description":7},[25,26],"user","model","main","02b95ddb62959a00b3c31442c2046aca0d19563c","skills\u002Fshorts-factory",1,"https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle","https:\u002F\u002Fleostruka.github.io\u002Fdevin-bundle\u002F","https:\u002F\u002Fgithub.com\u002FLeostruka","2026-11-15 05:19:58",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Leostruka\u002Fdevin-bundle --skill shorts-factory",{"tool":41,"command":42},"bunx","bunx skills add Leostruka\u002Fdevin-bundle --skill shorts-factory",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Leostruka\u002Fdevin-bundle --skill shorts-factory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fshorts-factory\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7E0K3MG2XC4FSRV0MK6SFR1","montador-de-ideias","Use when assembling, expanding, or elevating a raw project idea or initial prompt into an ultra-detailed, first-principles dossier and compiled master prompt with journalistic OSINT market research, Tech Lead and Staff Architect justifications, atomic and modular hardening\u002Foptimization, and high-impact contact surfaces.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fmontador-de-ideias\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7E0J7JJWZ8QMK01RZ3B3C9Z","git-github-adaptive-engineering","Use when any task touches git history, GitHub issues\u002FPRs\u002Freleases\u002FCI, repo governance, or branch and merge decisions. Runs the Fase Zero situational-awareness battery, picks one of five delivery flows via the adaptive decision engine, and enforces commit\u002FPR information-density standards. Orchestrates the gh, git-workflows, github-actions, pr, and debug\u002Ffinish skills.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fgit-github-adaptive-engineering\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7E0GJFRPFEVQQMXEM58EWDM","adaptive-agenda-calendar-routine-engine","Use when planning or executing work across hours, days, weeks, or sprints. Turns the calendar into a strict time-blocked agenda (HH:MM-HH:MM blocks carrying a routine profile, expected inputs, and a handoff output artifact), runs the 5-stage cognitive flow (Radar and Hunt -> Triage plus Steve Jobs conception -> workbench manifest -> >=32-cycle loop -> Close plus Open-Minded Scrum), and unfolds macro calendar milestones into micro agenda blocks through extensions\u002Fgcal\u002Fwrapper.py.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fadaptive-agenda-calendar-routine-engine\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7AE2K9FTY0BVS48N0A9JFKF","demo","Use when demonstrating a skill in a fixture project.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7AE2G3DP38PTV3B1N7MW5TS","duplicate-skill","Use when testing duplicate skill name detection.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Fbeta\u002FSKILL.md",[],[],{"skillNo":86,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AE2DBR8ZHT6T875MJ392GK","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Falpha\u002FSKILL.md",[],[]]