[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77PTSZX27J82ZABPQ3VZRZM":3,"skill-same:01M77PTSZX27J82ZABPQ3VZRZM":108},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M77PTSZX27J82ZABPQ3VZRZM","changelog-video",null,"Turn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when the user provides a changelog\u002Fdigest markdown and wants the weekly video, or says \"changelog video\". Self-contained — fonts, background, lexicon, and scripts ship in this skill.","Reihantt6\u002Fsns-myagent","Reihantt6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219822095?v=4","01M77KK94PV8B7C2D9XWXNS8DJ","Mohamad Reihan tegar prasetya","01M77KK958QFMTHYXGXFV7KZ79",2,"MIT","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Turn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when the user provides a changelog\u002Fdigest markdown and wants the weekly video, or says \\\"changelog video\\\". Self-contained — fonts, background, lexicon, and scripts ship in this skill.\"\n---\n# Changelog → Branded Video\n\nInput: a changelog .md (themes + items, like the weekly HyperFrames digest).\nOutput: a lint-clean, seam-gate-green HyperFrames project in\n`projects\u002Factive\u002Fweekly-changelog-\u003Crange>\u002F`. Render only when asked.\n\n**Load first, non-negotiable:** `motion-doctrine` (+ `cut-the-curve`,\n`oversized-cursor` if a cursor appears, `seam-craft`) and `captions-overlay`.\nThis skill supplies the changelog-specific pipeline; the doctrine supplies the\nmotion law.\n\n## The prime directive: visualize, don't list\n\nEvery theme is illustrated by an **animated mock of the actual UI or a\nfaithful analog** acting out the change in experience — never text bullets.\nRoute every theme\u002Fitem through `references\u002Fvisualization-registry.md` BEFORE\nwriting the script; the registry decides ui-recreate \u002F ui-analog \u002F terminal \u002F\nchecklist. Text checklist is the LAST resort, reserved for genuinely\nnon-visual items (reliability fix lists).\n\n## Pipeline\n\n### 0 · Bootstrap the project from THIS skill's assets — non-negotiable\n\n**Do this before writing any composition HTML. Skipping it always produces a video that looks like a similar project you built before, NOT this skill's brand — that's the single most common way this skill goes off-brand.** The skill's assets, fonts, and scaffold are the skill; the SKILL.md prompt is a router.\n\n```bash\nmkdir -p project\u002Fassets\u002Ffonts\ncp \u003CSKILL_DIR>\u002Fassets\u002Ffonts\u002F*.woff2 project\u002Fassets\u002Ffonts\u002F\ncp \u003CSKILL_DIR>\u002Fassets\u002Fbgm.mp3 project\u002Fbgm.mp3\nffmpeg -y -stream_loop 15 -i \u003CSKILL_DIR>\u002Fassets\u002Fbg-pattern.mp4 -t \u003CTOTAL> \\\n  -vf \"scale=1080:1080,fps=30,eq=saturation=0.72,drawbox=c=black@0.5:t=fill\" \\\n  -an -c:v libx264 -crf 20 -pix_fmt yuv420p project\u002Fassets\u002Fbg-pattern-\u003CTOTAL>s.mp4\ncp \u003CSKILL_DIR>\u002Fexamples\u002Fmaster-skeleton.html project\u002Findex.html\n```\n\nThen **read `references\u002Fbuild-spec.md` end-to-end** (not skimmed) — it defines the brand tokens (TT Norms Pro + ABC Solar Display + TT Norms Mono, cream `#f5f6f4`, rationed green `#5ef17c`, glass cards with green-tinted borders, kicker\u002Fsec-chip pill shape, 32px caption rail at `top: 990`) that every scene inherits from the scaffold.\n\nOnly THEN begin steps 1-6 below. Steps 1-4 (parse, route, script, VO) plan what goes into the scaffold; step 5 fills placeholders (`\u003CRANGE>`, `\u003CTOTAL>`, `\u003CCUT_N>`, `\u003CDUR_N>`, scene bodies) inside the already-copied `project\u002Findex.html` — you do NOT rewrite the scaffold's chrome, fonts, palette, or layout shell.\n\nIf you catch yourself reaching for `cp` on a prior video's `index.html`, or writing your own `@font-face` declarations, or designing a WebGL shader background instead of using the encoded bg-pattern MP4 above: STOP. Delete the current `index.html` and restart at the `cp` of the master-skeleton scaffold. Rebuilding scene content on the right scaffold is cheaper than retrofitting brand into the wrong scaffold.\n\n### 1 · Parse + editorial cut\n\n- Extract: week range, headline stats (releases, commits), themes, items.\n- **Budget: 45-60s total.** Title ≤2s, outro ≤3.5s, 4 themes ≈ 9-12s each.\n- Per theme keep ONE hero visualization + at most 3 spoken items. Everything\n  else exists only as the outro's \"full digest\" pointer. Cutting is the job:\n  a changelog with 30 items still yields ≤14 spoken beats.\n- Order themes by story: marquee feature → product surface → performance →\n  reliability (the digest usually already reads this way).\n\n### 2 · Visualization routing\n\nFor each theme, pick the surface from `references\u002Fvisualization-registry.md`\nand write one line: `theme → surface → the 2-4 sequenced actions the mock\nperforms, each tied to a script phrase`. If no registry surface fits and no\nfaithful analog exists, it's a checklist scene — don't invent fake UI for\nsomething we can't represent honestly.\n\n### 3 · Two-layer script (spoken vs display)\n\nWrite the script as **token lines** per `references\u002Fscript-voice.md`:\nconversational register, every technical term carrying a `spoken` phonetic\nform from `references\u002Flexicon.json` while `display` keeps standard spelling.\nCaptions show `display`; the VO reads `spoken`. Any term not in the lexicon:\nSTOP and ask the user how it's pronounced, then add it to the lexicon.\nSave as `script-tokens.json` in the project.\n\n### 4 · VO — Annie (HeyGen, pinned)\n\n```bash\n# spoken-layer text only; words JSON = ground-truth timestamps of the SPOKEN text\n# Repo-native path: the changelog-video skill runs from the hyperframes repo root,\n# so it uses the tracked hyperframes-media TTS helper directly (no `npx hyperframes\n# skills` install step). If you've copied the skill into another repo, swap in\n# your own path to the media-use \u002F hyperframes-media heygen-tts.mjs.\nnode skills\u002Fhyperframes-media\u002Fscripts\u002Fheygen-tts.mjs .\u002Fvo-spoken.txt \\\n  -o voiceover.mp3 --words vo-words.json \\\n  --voice 330290724a1b470fb63153f34d4c0183   # Annie — lifelike (do not substitute)\n```\n\nRequires `heygen` CLI ≥0.3.0 authenticated (`heygen auth login --oauth`).\nThen align spoken timestamps back to display tokens:\n\n```bash\nnode \u003CSKILL_DIR>\u002Fscripts\u002Falign-captions.mjs \\\n  --tokens script-tokens.json --words vo-words.json --out captions.json\n```\n\n`captions.json` is the caption-rail input (display spelling, spoken timing).\nThe aligner prints `MISMATCH` warnings — resolve every one before building\n(usually a lexicon spelling the TTS renders as multiple words). **The audio\nis the clock**: all beat times come from `vo-words.json`; a VO regen re-opens\nevery seam.\n\n**Word-timings are a hard gate.** Before moving on to step 5, verify\n`vo-words.json` is non-empty and has a `words: [...]` array with `start`\u002F`end`\nper word. If it's empty (0 bytes) or missing the array — a known failure mode\nwhen the TTS provider returns audio but no timestamp payload — DO NOT proceed\nwithout them. Fallback: forced-align the produced audio against the display\nscript using local whisper:\n\n```bash\nuvx --from openai-whisper whisper voiceover.mp3 \\\n  --model base.en --language en --word_timestamps True \\\n  --output_format json --output_dir .\n# then run align-captions.mjs with --words voiceover.json (same shape)\n```\n\nWhisper mishears TTS renderings (\"gee-sap\" → \"gsap\", \"heyjen\" → \"hey Jen\",\netc.) — captions still use the DISPLAY spelling from `script-tokens.json`;\nwhisper only supplies the timestamps. `align-captions.mjs` handles the join.\nThis fallback is the difference between a captioned build and a silently\nuncaptioned one.\n\n### 5 · Build\n\nFollow `references\u002Fbuild-spec.md` exactly: brand tokens + fonts (bundled in\n`\u003CSKILL_DIR>\u002Fassets\u002F`), the animated background encode, scene scaffold,\nchrome, caption rail, one rationed green moment per scene. Then the doctrine\norder: `ledger.json` (all ordinary seams cut-the-curve LEFT) → seam-stamp →\ninternal beats on VO words → seam-gate verify.\n\n**Captions are non-optional.** The master-skeleton ships a caption-rail IIFE\nthat reads a `LINES` array — leaving that array empty is a shipped bug, not a\nstyle choice. Populate it from `captions.json` before proceeding to step 6:\n\n```javascript\n\u002F\u002F paste in place of \"const LINES = \u002F* … *\u002F []\" in the caption-rail IIFE:\nconst LINES = \u002F* contents of captions.json *\u002F [\n  { id: 0, end: 2.74, w: [[\"This\", 0.0], [\"week,\", 0.30], …] },\n  …\n];\n```\n\nIf `align-captions.mjs` was skipped or `LINES` is `[]`, the frame check in\nstep 6 will fail — do not paper over it by removing `#cap-line` from the\nscaffold.\n\n### 6 · Gates (all green before presenting)\n\n1. `bun run --cwd packages\u002Fcli hyperframes check` (or the installed\n   `hyperframes` CLI from the repo-local `skills\u002Fhyperframes-cli\u002F` skill) —\n   0 errors (contrast: dim text ≥ .66 alpha). Do NOT reach for\n   `npx hyperframes@latest`; the tracked repo-local CLI is the source of\n   truth for the composition contract this skill produces against.\n2. `seam-gate.mjs verify` — 0 fail.\n3. Restart the preview server (it caches the bundle), spot-check 3-4 beats\n   via `__player.seek` on the raw comp page.\n4. Do NOT render unless the user asks. After a requested render, verify\n   frames from the MP4 (`ffmpeg -ss \u003Ct> … -frames:v 1`): captions present,\n   background video not black, no tiny\u002Ffrozen frames.\n5. **Caption presence gate — hard fail.** Sample 3-4 frames spread across\n   the VO's spoken window (e.g. `t=3`, `t=15`, `t=30`, `t=42` for a 48s VO)\n   and confirm the caption rail at `top: 990` renders visible text on each.\n   If any frame in a spoken interval is missing captions, the build ships\n   uncaptioned — treat it as a red gate and re-check step 5's `LINES`\n   population. This is exactly what went wrong on the Jul 13-20 v4 build.\n\n## Project layout\n\n```\nprojects\u002Factive\u002Fweekly-changelog-\u003Crange>\u002F\n├── index.html            # single-doc master (scenes as slides, stamped seams)\n├── ledger.json           # vector ledger (seam-stamp input)\n├── script-tokens.json    # two-layer script (source of truth for VO + captions)\n├── vo-spoken.txt         # generated: spoken layer, one line\n├── voiceover.mp3 + vo-words.json + captions.json\n├── bgm.mp3               # copy from \u003CSKILL_DIR>\u002Fassets\u002Fbgm.mp3 (the house track) unless the user supplies one\n└── assets\u002Ffonts\u002F + assets\u002Fbg-pattern-\u003Cdur>s.mp4\n```\n\n## Anti-patterns\n\n| Don't                                                 | Instead                                                                                                                                                                                          |\n| ----------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Bullet-point slides for UI changes                    | Mock the surface acting out the change                                                                                                                                                           |\n| Fake UI for un-representable items                    | Honest checklist scene                                                                                                                                                                           |\n| Plain \"JSON\"\u002F\"CLI\" in the TTS text                    | Lexicon spoken forms; display stays standard                                                                                                                                                     |\n| Phonetic spellings in captions                        | Captions always render the display layer                                                                                                                                                         |\n| Guessing an unknown term's pronunciation              | Ask, then grow the lexicon                                                                                                                                                                       |\n| Speaking every changelog item                         | ≤3 per theme; the digest link carries the rest                                                                                                                                                   |\n| Green accents everywhere                              | One green moment per scene (#5ef17c)                                                                                                                                                             |\n| Starting from a prior video's index.html              | Step 0 — copy `examples\u002Fmaster-skeleton.html` from this skill into `project\u002Findex.html`, always                                                                                                  |\n| Hand-crafted `@font-face` \u002F WebGL shader \u002F custom BGM | Step 0 — copy this skill's `assets\u002F` verbatim; the skill's assets ARE the brand                                                                                                                  |\n| Delivered without CloudFront invalidation             | Run `aws cloudfront create-invalidation` on distribution `E2BSLVSZ7FG3U0` for the exact path after any S3 replace — CDN caches the old file otherwise                                            |\n| Shipping with the `LINES` array empty in the scaffold | Step 4 must produce a populated `captions.json`; step 5 must paste it into the IIFE; step 6 gate 5 must confirm captions on rendered frames. An empty `LINES` = uncaptioned ship = re-do the run |\n| No `vo-words.json` → skip captions and ship anyway    | Fall back to whisper forced alignment on the produced audio; captions are non-optional                                                                                                           |\n","# Changelog → Branded Video\n\nInput: a changelog .md (themes + items, like the weekly HyperFrames digest).\nOutput: a lint-clean, seam-gate-green HyperFrames project in\n`projects\u002Factive\u002Fweekly-changelog-\u003Crange>\u002F`. Render only when asked.\n\n**Load first, non-negotiable:** `motion-doctrine` (+ `cut-the-curve`,\n`oversized-cursor` if a cursor appears, `seam-craft`) and `captions-overlay`.\nThis skill supplies the changelog-specific pipeline; the doctrine supplies the\nmotion law.\n\n## The prime directive: visualize, don't list\n\nEvery theme is illustrated by an **animated mock of the actual UI or a\nfaithful analog** acting out the change in experience — never text bullets.\nRoute every theme\u002Fitem through `references\u002Fvisualization-registry.md` BEFORE\nwriting the script; the registry decides ui-recreate \u002F ui-analog \u002F terminal \u002F\nchecklist. Text checklist is the LAST resort, reserved for genuinely\nnon-visual items (reliability fix lists).\n\n## Pipeline\n\n### 0 · Bootstrap the project from THIS skill's assets — non-negotiable\n\n**Do this before writing any composition HTML. Skipping it always produces a video that looks like a similar project you built before, NOT this skill's brand — that's the single most common way this skill goes off-brand.** The skill's assets, fonts, and scaffold are the skill; the SKILL.md prompt is a router.\n\n```bash\nmkdir -p project\u002Fassets\u002Ffonts\ncp \u003CSKILL_DIR>\u002Fassets\u002Ffonts\u002F*.woff2 project\u002Fassets\u002Ffonts\u002F\ncp \u003CSKILL_DIR>\u002Fassets\u002Fbgm.mp3 project\u002Fbgm.mp3\nffmpeg -y -stream_loop 15 -i \u003CSKILL_DIR>\u002Fassets\u002Fbg-pattern.mp4 -t \u003CTOTAL> \\\n  -vf \"scale=1080:1080,fps=30,eq=saturation=0.72,drawbox=c=black@0.5:t=fill\" \\\n  -an -c:v libx264 -crf 20 -pix_fmt yuv420p project\u002Fassets\u002Fbg-pattern-\u003CTOTAL>s.mp4\ncp \u003CSKILL_DIR>\u002Fexamples\u002Fmaster-skeleton.html project\u002Findex.html\n```\n\nThen **read `references\u002Fbuild-spec.md` end-to-end** (not skimmed) — it defines the brand tokens (TT Norms Pro + ABC Solar Display + TT Norms Mono, cream `#f5f6f4`, rationed green `#5ef17c`, glass cards with green-tinted borders, kicker\u002Fsec-chip pill shape, 32px caption rail at `top: 990`) that every scene inherits from the scaffold.\n\nOnly THEN begin steps 1-6 below. Steps 1-4 (parse, route, script, VO) plan what goes into the scaffold; step 5 fills placeholders (`\u003CRANGE>`, `\u003CTOTAL>`, `\u003CCUT_N>`, `\u003CDUR_N>`, scene bodies) inside the already-copied `project\u002Findex.html` — you do NOT rewrite the scaffold's chrome, fonts, palette, or layout shell.\n\nIf you catch yourself reaching for `cp` on a prior video's `index.html`, or writing your own `@font-face` declarations, or designing a WebGL shader background instead of using the encoded bg-pattern MP4 above: STOP. Delete the current `index.html` and restart at the `cp` of the master-skeleton scaffold. Rebuilding scene content on the right scaffold is cheaper than retrofitting brand into the wrong scaffold.\n\n### 1 · Parse + editorial cut\n\n- Extract: week range, headline stats (releases, commits), themes, items.\n- **Budget: 45-60s total.** Title ≤2s, outro ≤3.5s, 4 themes ≈ 9-12s each.\n- Per theme keep ONE hero visualization + at most 3 spoken items. Everything\n  else exists only as the outro's \"full digest\" pointer. Cutting is the job:\n  a changelog with 30 items still yields ≤14 spoken beats.\n- Order themes by story: marquee feature → product surface → performance →\n  reliability (the digest usually already reads this way).\n\n### 2 · Visualization routing\n\nFor each theme, pick the surface from `references\u002Fvisualization-registry.md`\nand write one line: `theme → surface → the 2-4 sequenced actions the mock\nperforms, each tied to a script phrase`. If no registry surface fits and no\nfaithful analog exists, it's a checklist scene — don't invent fake UI for\nsomething we can't represent honestly.\n\n### 3 · Two-layer script (spoken vs display)\n\nWrite the script as **token lines** per `references\u002Fscript-voice.md`:\nconversational register, every technical term carrying a `spoken` phonetic\nform from `references\u002Flexicon.json` while `display` keeps standard spelling.\nCaptions show `display`; the VO reads `spoken`. Any term not in the lexicon:\nSTOP and ask the user how it's pronounced, then add it to the lexicon.\nSave as `script-tokens.json` in the project.\n\n### 4 · VO — Annie (HeyGen, pinned)\n\n```bash\n# spoken-layer text only; words JSON = ground-truth timestamps of the SPOKEN text\n# Repo-native path: the changelog-video skill runs from the hyperframes repo root,\n# so it uses the tracked hyperframes-media TTS helper directly (no `npx hyperframes\n# skills` install step). If you've copied the skill into another repo, swap in\n# your own path to the media-use \u002F hyperframes-media heygen-tts.mjs.\nnode skills\u002Fhyperframes-media\u002Fscripts\u002Fheygen-tts.mjs .\u002Fvo-spoken.txt \\\n  -o voiceover.mp3 --words vo-words.json \\\n  --voice 330290724a1b470fb63153f34d4c0183   # Annie — lifelike (do not substitute)\n```\n\nRequires `heygen` CLI ≥0.3.0 authenticated (`heygen auth login --oauth`).\nThen align spoken timestamps back to display tokens:\n\n```bash\nnode \u003CSKILL_DIR>\u002Fscripts\u002Falign-captions.mjs \\\n  --tokens script-tokens.json --words vo-words.json --out captions.json\n```\n\n`captions.json` is the caption-rail input (display spelling, spoken timing).\nThe aligner prints `MISMATCH` warnings — resolve every one before building\n(usually a lexicon spelling the TTS renders as multiple words). **The audio\nis the clock**: all beat times come from `vo-words.json`; a VO regen re-opens\nevery seam.\n\n**Word-timings are a hard gate.** Before moving on to step 5, verify\n`vo-words.json` is non-empty and has a `words: [...]` array with `start`\u002F`end`\nper word. If it's empty (0 bytes) or missing the array — a known failure mode\nwhen the TTS provider returns audio but no timestamp payload — DO NOT proceed\nwithout them. Fallback: forced-align the produced audio against the display\nscript using local whisper:\n\n```bash\nuvx --from openai-whisper whisper voiceover.mp3 \\\n  --model base.en --language en --word_timestamps True \\\n  --output_format json --output_dir .\n# then run align-captions.mjs with --words voiceover.json (same shape)\n```\n\nWhisper mishears TTS renderings (\"gee-sap\" → \"gsap\", \"heyjen\" → \"hey Jen\",\netc.) — captions still use the DISPLAY spelling from `script-tokens.json`;\nwhisper only supplies the timestamps. `align-captions.mjs` handles the join.\nThis fallback is the difference between a captioned build and a silently\nuncaptioned one.\n\n### 5 · Build\n\nFollow `references\u002Fbuild-spec.md` exactly: brand tokens + fonts (bundled in\n`\u003CSKILL_DIR>\u002Fassets\u002F`), the animated background encode, scene scaffold,\nchrome, caption rail, one rationed green moment per scene. Then the doctrine\norder: `ledger.json` (all ordinary seams cut-the-curve LEFT) → seam-stamp →\ninternal beats on VO words → seam-gate verify.\n\n**Captions are non-optional.** The master-skeleton ships a caption-rail IIFE\nthat reads a `LINES` array — leaving that array empty is a shipped bug, not a\nstyle choice. Populate it from `captions.json` before proceeding to step 6:\n\n```javascript\n\u002F\u002F paste in place of \"const LINES = \u002F* … *\u002F []\" in the caption-rail IIFE:\nconst LINES = \u002F* contents of captions.json *\u002F [\n  { id: 0, end: 2.74, w: [[\"This\", 0.0], [\"week,\", 0.30], …] },\n  …\n];\n```\n\nIf `align-captions.mjs` was skipped or `LINES` is `[]`, the frame check in\nstep 6 will fail — do not paper over it by removing `#cap-line` from the\nscaffold.\n\n### 6 · Gates (all green before presenting)\n\n1. `bun run --cwd packages\u002Fcli hyperframes check` (or the installed\n   `hyperframes` CLI from the repo-local `skills\u002Fhyperframes-cli\u002F` skill) —\n   0 errors (contrast: dim text ≥ .66 alpha). Do NOT reach for\n   `npx hyperframes@latest`; the tracked repo-local CLI is the source of\n   truth for the composition contract this skill produces against.\n2. `seam-gate.mjs verify` — 0 fail.\n3. Restart the preview server (it caches the bundle), spot-check 3-4 beats\n   via `__player.seek` on the raw comp page.\n4. Do NOT render unless the user asks. After a requested render, verify\n   frames from the MP4 (`ffmpeg -ss \u003Ct> … -frames:v 1`): captions present,\n   background video not black, no tiny\u002Ffrozen frames.\n5. **Caption presence gate — hard fail.** Sample 3-4 frames spread across\n   the VO's spoken window (e.g. `t=3`, `t=15`, `t=30`, `t=42` for a 48s VO)\n   and confirm the caption rail at `top: 990` renders visible text on each.\n   If any frame in a spoken interval is missing captions, the build ships\n   uncaptioned — treat it as a red gate and re-check step 5's `LINES`\n   population. This is exactly what went wrong on the Jul 13-20 v4 build.\n\n## Project layout\n\n```\nprojects\u002Factive\u002Fweekly-changelog-\u003Crange>\u002F\n├── index.html            # single-doc master (scenes as slides, stamped seams)\n├── ledger.json           # vector ledger (seam-stamp input)\n├── script-tokens.json    # two-layer script (source of truth for VO + captions)\n├── vo-spoken.txt         # generated: spoken layer, one line\n├── voiceover.mp3 + vo-words.json + captions.json\n├── bgm.mp3               # copy from \u003CSKILL_DIR>\u002Fassets\u002Fbgm.mp3 (the house track) unless the user supplies one\n└── assets\u002Ffonts\u002F + assets\u002Fbg-pattern-\u003Cdur>s.mp4\n```\n\n## Anti-patterns\n\n| Don't                                                 | Instead                                                                                                                                                                                          |\n| ----------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| Bullet-point slides for UI changes                    | Mock the surface acting out the change                                                                                                                                                           |\n| Fake UI for un-representable items                    | Honest checklist scene                                                                                                                                                                           |\n| Plain \"JSON\"\u002F\"CLI\" in the TTS text                    | Lexicon spoken forms; display stays standard                                                                                                                                                     |\n| Phonetic spellings in captions                        | Captions always render the display layer                                                                                                                                                         |\n| Guessing an unknown term's pronunciation              | Ask, then grow the lexicon                                                                                                                                                                       |\n| Speaking every changelog item                         | ≤3 per theme; the digest link carries the rest                                                                                                                                                   |\n| Green accents everywhere                              | One green moment per scene (#5ef17c)                                                                                                                                                             |\n| Starting from a prior video's index.html              | Step 0 — copy `examples\u002Fmaster-skeleton.html` from this skill into `project\u002Findex.html`, always                                                                                                  |\n| Hand-crafted `@font-face` \u002F WebGL shader \u002F custom BGM | Step 0 — copy this skill's `assets\u002F` verbatim; the skill's assets ARE the brand                                                                                                                  |\n| Delivered without CloudFront invalidation             | Run `aws cloudfront create-invalidation` on distribution `E2BSLVSZ7FG3U0` for the exact path after any S3 replace — CDN caches the old file otherwise                                            |\n| Shipping with the `LINES` array empty in the scaffold | Step 4 must produce a populated `captions.json`; step 5 must paste it into the IIFE; step 6 gate 5 must confirm captions on rendered frames. An empty `LINES` = uncaptioned ship = re-do the run |\n| No `vo-words.json` → skip captions and ship anyway    | Fall back to whisper forced alignment on the produced audio; captions are non-optional                                                                                                           |\n",{"description":7},"main","58843b159d7a4050d6b785a98b908cce505c0b92","agent\u002Fskills\u002Fchangelog-video",0,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent","https:\u002F\u002Fgithub.com\u002FReihantt6","reihsns.web.id","2026-08-19 20:08:18",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Reihantt6\u002Fsns-myagent --skill changelog-video",{"tool":38,"command":39},"bunx","bunx skills add Reihantt6\u002Fsns-myagent --skill changelog-video",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Reihantt6\u002Fsns-myagent --skill changelog-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002FSKILL.md",true,[46,52,56,60,64,68,72,76,82,86,90,94,98,102],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fbg-pattern.mp4","ASSET","资产文件",133,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fassets\u002Fbg-pattern.mp4",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fbgm.mp3",132,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fassets\u002Fbgm.mp3",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"assets\u002Ffonts\u002FABCSolarDisplay-Bold.woff2",105040,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fassets\u002Ffonts\u002FABCSolarDisplay-Bold.woff2",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"assets\u002Ffonts\u002FTT_Norms_Pro_Bold.woff2",101116,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fassets\u002Ffonts\u002FTT_Norms_Pro_Bold.woff2",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"assets\u002Ffonts\u002FTT_Norms_Pro_Medium.woff2",97844,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fassets\u002Ffonts\u002FTT_Norms_Pro_Medium.woff2",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"assets\u002Ffonts\u002Ftt_norms_pro_mono_regular-webfont.woff2",81748,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fassets\u002Ffonts\u002Ftt_norms_pro_mono_regular-webfont.woff2",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"assets\u002Ffonts\u002FTT_Norms_Pro_Normal.woff2",100160,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fassets\u002Ffonts\u002FTT_Norms_Pro_Normal.woff2",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"examples\u002Fmaster-skeleton.html","REFERENCE","参考文档",7022,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fexamples\u002Fmaster-skeleton.html",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"examples\u002Fscript-tokens.json",1201,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fexamples\u002Fscript-tokens.json",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fbuild-spec.md",5429,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Freferences\u002Fbuild-spec.md",{"path":91,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Flexicon.json",1671,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Freferences\u002Flexicon.json",{"path":95,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fscript-voice.md",4877,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Freferences\u002Fscript-voice.md",{"path":99,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fvisualization-registry.md",7348,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Freferences\u002Fvisualization-registry.md",{"path":103,"resourceType":104,"resourceTypeDesc":105,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Falign-captions.mjs","SCRIPT","脚本",4581,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fchangelog-video\u002Fscripts\u002Falign-captions.mjs",[109,116,123,130,137,144],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M77XDCYZ407XYMF2T4P6F7VT","youtube-transcript","Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com\u002Fwatch?v=, youtu.be\u002F, or similar). Supports output with or without timestamps.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-transcript\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M77XD7PBC98J6MXGJJ2TJ8DX","youtube-thumbnail-design","YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A\u002FB testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-thumbnail-design\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":19},"01M77XD2541C8HXJ6RHYZP4NGJ","youtube-short-maker","Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: \"youtube short\", \"make a youtube short\", \"shorts video\", \"short-form video\". NOT for long-form or landscape video.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-short-maker\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":19},"01M77XCXKVSYK7KTZ3PQBVVGFD","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fxcode-project-setup\u002FSKILL.md",[],[],{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":19},"01M77XCR1DV8ZQK2NHWKVY4EWX","x402","Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — \"just use it\" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or \"build it in\" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx402\u002FSKILL.md",[],[],{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":19},"01M77XCMD3R3ZBZQQSW6E0793B","x-twitter-scraper","Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx-twitter-scraper\u002FSKILL.md",[],[]]