[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EB7QR80YYPPHPXWZMSR5YJ":3,"skill-same:01M7EB7QR80YYPPHPXWZMSR5YJ":87},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7EB7QR80YYPPHPXWZMSR5YJ","clipify",null,"Find the funniest moments in a video, cut them as standalone clips, optionally reformat 16:9 → 9:16 (face-pan or split-screen), and burn opus-style word-by-word captions. Use when the user mentions \"clipify,\" \"cut clips from this video,\" \"make shorts from this,\" \"find funny moments,\" \"reframe to 9:16,\" \"vertical clips,\" or pastes a video file path and wants social-ready cuts.","fozagtx\u002FBuildOS-workflow","fozagtx","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160292135?v=4","01M7EAS4W39D2X3WNCCVVZ7CVZ","fawuzan","01M7EAS4WP1G4JD4KG87P6PTK6",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: clipify\ndescription: Find the funniest moments in a video, cut them as standalone clips, optionally reformat 16:9 → 9:16 (face-pan or split-screen), and burn opus-style word-by-word captions. Use when the user mentions \"clipify,\" \"cut clips from this video,\" \"make shorts from this,\" \"find funny moments,\" \"reframe to 9:16,\" \"vertical clips,\" or pastes a video file path and wants social-ready cuts.\n---\n\n# Clipify\n\nFind the funniest moments in a video, cut them as standalone clips, optionally reformat 16:9 → 9:16 (face-pan or split-screen), and burn opus-style word-by-word captions.\n\n## Inputs\n\n- A video file path (the user will provide it; otherwise ask)\n- Optional: requested format (9:16, 16:9, 1:1) — if not given, ask after candidates are picked\n- Optional: subtitle style preference — if not given, ask before captioning\n\n## Tooling (use only the fastest path)\n\n- **Whisper:** `whisper --model tiny.en --word_timestamps True --output_format json` (≈10× faster than `small.en`; quality fine for English). For non-English: `--model base` (drop `--language`).\n- **ffmpeg:** add `-hwaccel videotoolbox` for decode and `-preset ultrafast` for renders. Use `-c:v libx264 -crf 20` for the final master.\n- **Numpy** for audio alignment (FFT cross-correlation). No scipy\u002Fcv2 needed.\n- **Scripts:** `\u003Cskill-dir>\u002Fscripts\u002F` (where `\u003Cskill-dir>` is the directory containing this SKILL.md — typically `~\u002F.Codex\u002Fskills\u002Fclipify\u002F`)\n  - `analyze.py` — speaker timeline from two ROI motion files\n  - `build_pan.py` — ffmpeg crop x-expression with hard cuts\n  - `build_ass.py` — opus-style ASS captions from whisper JSON\n  - `audio_align.py` — find offset of a sub-clip in a longer source\n\nWorking dir: `\u002Ftmp\u002Fclipify\u002F` (mkdir at start, leave artifacts for debugging).\n\n---\n\n## Workflow\n\n### Step 1 — Find the funniest parts\n\n```bash\nmkdir -p \u002Ftmp\u002Fclipify\nffmpeg -y -hwaccel videotoolbox -i \"$VIDEO\" -vn -ac 1 -ar 16000 \u002Ftmp\u002Fclipify\u002Faudio.wav\nwhisper \u002Ftmp\u002Fclipify\u002Faudio.wav --model tiny.en --word_timestamps True --output_format json --output_dir \u002Ftmp\u002Fclipify --language en\n```\n\nRead the resulting JSON (or `.txt`) and pick 3–5 candidate clips. Funny signals to scan for:\n\n- **Punchlines and reactions:** words like \"what\", \"wait\", \"no way\", laughter, \"haha\", swearing\n- **Reversal moments:** setup question → unexpected answer\n- **Awkward pauses:** Whisper segment with long gap, or filler (\"uh\", \"um\")\n- **Self-roast \u002F quotable one-liners:** short declarative sentences that stand alone\n- **Audio peaks:** detect via `ffmpeg -af volumedetect` or look for rapid back-and-forth (alternating short Whisper segments)\n\nFor each candidate, propose: `[start, end, why-it's-funny, suggested title]`. Aim for 10–25s clips. Show the list and let the user confirm\u002Fpick.\n\n### Step 2 — Trim each chosen clip\n\n```bash\nffmpeg -y -ss \"$START\" -t \"$DURATION\" -i \"$VIDEO\" -c copy \u002Ftmp\u002Fclipify\u002Fclip_$N.mp4\n```\n\n(Use `-c copy` for instant trim. Re-encode only if cuts must be frame-accurate.)\n\n### Step 3 — Decide the output format\n\nAsk the user (skip if they already specified): \"9:16 (TikTok \u002F Reels), 16:9 (YouTube), or 1:1 (Insta feed)?\"\n\n### Step 4 — If 16:9 → 9:16: pan-between-faces vs split-screen\n\nDetect source aspect with `ffprobe`. If source is 16:9 and target is 9:16, ask:\n\n> \"Two options: **(a) hard-cut pan** that follows whoever is speaking (single face on screen at a time), or **(b) split-screen** stack with both faces visible. Which do you want?\"\n\nSkip the question if there's only one face (single-talker clip). For single-talker, just center-crop.\n\n#### Step 4a — Pan-between-faces (recommended for fast-cut talking-head dialogue)\n\n1. **Locate the two face ROIs.** Sample one frame: `ffmpeg -ss \u003Cmiddle> -i \u003Cclip> -frames:v 1 \u002Ftmp\u002Fclipify\u002Fprobe.jpg`. Read it. Eyeball each face's mouth+chin area as `x,y,w,h` in the source's pixel space. (No cv2 needed — camera is static within a clip; one frame is enough.) Verify by drawing boxes:\n\n   ```bash\n   ffmpeg -i probe.jpg -vf \"drawbox=x=$LX:y=$LY:w=$LW:h=$LH:color=cyan@0.9:t=4,drawbox=x=$RX:y=$RY:w=$RW:h=$RH:color=magenta@0.9:t=4\" verify.jpg\n   ```\n\n   Iterate **at most twice**. Boxes should cover mouth + chin and avoid hands\u002Fmics. Don't over-tune — frame differencing is forgiving.\n\n2. **Extract per-frame motion energy in each ROI:**\n\n   ```bash\n   ffmpeg -y -i clip.mp4 -filter_complex \"\n   [0:v]split=2[a][b];\n   [a]crop=$LW:$LH:$LX:$LY,format=gray,tblend=all_mode=difference,signalstats,metadata=mode=print:key=lavfi.signalstats.YAVG:file=\u002Ftmp\u002Fclipify\u002FL.txt[la];\n   [b]crop=$RW:$RH:$RX:$RY,format=gray,tblend=all_mode=difference,signalstats,metadata=mode=print:key=lavfi.signalstats.YAVG:file=\u002Ftmp\u002Fclipify\u002FR.txt[ra]\n   \" -map \"[la]\" -f null - -map \"[ra]\" -f null -\n   ```\n\n3. **Build speaker timeline** (min dwell 1.0s — short interjections merge into the prior speaker):\n\n   ```bash\n   python3 \u003Cskill-dir>\u002Fscripts\u002Fanalyze.py \u002Ftmp\u002Fclipify\u002FL.txt \u002Ftmp\u002Fclipify\u002FR.txt 1.0 > \u002Ftmp\u002Fclipify\u002Fsegments.json\n   ```\n\n4. **Pick pan x-coordinates** for a 9:16 vertical strip from the source. With source W=1920 and target W=1080, crop strip width = 608.\n   - LEFT_X = `face_left_center_x - 304` (clamp ≥ 0)\n   - RIGHT_X = `face_right_center_x - 304` (clamp ≤ source_W - 608)\n\n5. **Generate the hard-cut x expression and render:**\n\n   ```bash\n   EXPR=$(python3 \u003Cskill-dir>\u002Fscripts\u002Fbuild_pan.py \u002Ftmp\u002Fclipify\u002Fsegments.json $LEFT_X $RIGHT_X)\n   ffmpeg -y -hwaccel videotoolbox -i clip.mp4 -filter_complex \\\n     \"[0:v]crop=608:1080:x='$EXPR':y=0,scale=1080:1920:flags=lanczos[v]\" \\\n     -map \"[v]\" -map 0:a -c:v libx264 -preset fast -crf 20 -pix_fmt yuv420p \\\n     -c:a aac -b:a 192k \u002Ftmp\u002Fclipify\u002Fclip_panned.mp4\n   ```\n\n   Source 1920×1080 assumed; for 4K source either downscale first or double all coordinates.\n\n#### Step 4b — Split-screen (both faces always visible)\n\nTwo stacked tiles, 1080×960 each. The active speaker's tile is on top — overlay flips at speaker changes.\n\n```\n[0:v]split=2[a0][a1];\n[a0]crop=Wcrop:Hcrop:LX_tile:LY_tile,scale=1080:960,split=2[lt0][lt1];\n[a1]crop=Wcrop:Hcrop:RX_tile:RY_tile,scale=1080:960,split=2[rt0][rt1];\n[lt0][rt0]vstack[layoutL];\n[rt1][lt1]vstack[layoutR];\n[layoutL][layoutR]overlay=0:0:enable='\u003CRIGHT_SPEAKER_ENABLE>'[v]\n```\n\nBuild `\u003CRIGHT_SPEAKER_ENABLE>` from `segments.json` as `between(t,a,b)+between(t,a,b)+...` over the right-speaker segments. Tile crops should target ~720×640 around each face (1.125:1 to match 1080×960).\n\n### Step 5 — Add subtitles\n\nAsk once (only if user hasn't already specified a style):\n\n> \"Three subtitle styles: **opus** (big bold white, yellow active-word highlight), **karaoke** (4-word chunks, green highlight), **minimal** (clean Helvetica, no highlight). Or paste an example you like.\"\n\nIf they paste a reference image\u002Fexample: match the font, size, weight, color, position, and animation as closely as possible — write a custom ASS by hand or extend `build_ass.py`.\n\nElse use the preset:\n\n```bash\n# Re-run whisper on the trimmed clip for accurate timestamps relative to clip start\nwhisper \u002Ftmp\u002Fclipify\u002Fclip_panned.mp4 --model tiny.en --word_timestamps True --output_format json --output_dir \u002Ftmp\u002Fclipify --language en\npython3 \u003Cskill-dir>\u002Fscripts\u002Fbuild_ass.py \u002Ftmp\u002Fclipify\u002Fclip_panned.json \u002Ftmp\u002Fclipify\u002Fcaptions.ass opus\n```\n\nBurn captions:\n\n```bash\nffmpeg -y -i \u002Ftmp\u002Fclipify\u002Fclip_panned.mp4 -vf \"subtitles=\u002Ftmp\u002Fclipify\u002Fcaptions.ass\" \\\n  -c:v libx264 -preset fast -crf 20 -c:a copy \"$OUTPUT.mp4\"\n```\n\n### Step 6 — Deliver\n\n- Save each output to `\u003Csource_dir>\u002Fclipify_out\u002F` (mkdir if missing)\n- Print one line per clip: name, duration, what was funny, output path\n- Open the first output with `open \u003Cpath>` so the user can check it\n- Offer to iterate (different style, different ROI, swap to split-screen, retime captions)\n\n---\n\n## Pitfalls (lessons from prior runs — don't repeat)\n\n- **Don't over-tune ROIs.** Two iterations max. Motion-diff is forgiving — wider ROIs covering mouth+chin work fine even if not perfectly mouth-centered.\n- **Watch out for scene cuts inside a clip.** Run `ffmpeg -filter:v \"select='gt(scene,0.3)',showinfo\" -f null -` to count cuts. If a 16:9→9:16 clip has many cuts, the fixed face ROIs only work for the dominant scene; warn the user, and offer to either pick a single-take clip or accept off-center framing during cuts.\n- **Source resolution matters.** If source is 4K, either downscale to 1920×1080 first (faster, fine for 9:16 output) or multiply all ROI\u002Fpan coordinates by 2.\n- **Burned-in subtitles in source.** Some \"raw\" clips still have subtitles. If so, find the no-subs master via audio cross-correlation (`audio_align.py`) and trim from there.\n- **Don't run whisper on the full feature-length source if a short clip suffices.** Whisper the trimmed clip after Step 2; only whisper the full source in Step 1 if you need a transcript to find funny moments.\n- **State the plan in one line, then act.** Don't narrate every iteration.\n","# Clipify\n\nFind the funniest moments in a video, cut them as standalone clips, optionally reformat 16:9 → 9:16 (face-pan or split-screen), and burn opus-style word-by-word captions.\n\n## Inputs\n\n- A video file path (the user will provide it; otherwise ask)\n- Optional: requested format (9:16, 16:9, 1:1) — if not given, ask after candidates are picked\n- Optional: subtitle style preference — if not given, ask before captioning\n\n## Tooling (use only the fastest path)\n\n- **Whisper:** `whisper --model tiny.en --word_timestamps True --output_format json` (≈10× faster than `small.en`; quality fine for English). For non-English: `--model base` (drop `--language`).\n- **ffmpeg:** add `-hwaccel videotoolbox` for decode and `-preset ultrafast` for renders. Use `-c:v libx264 -crf 20` for the final master.\n- **Numpy** for audio alignment (FFT cross-correlation). No scipy\u002Fcv2 needed.\n- **Scripts:** `\u003Cskill-dir>\u002Fscripts\u002F` (where `\u003Cskill-dir>` is the directory containing this SKILL.md — typically `~\u002F.Codex\u002Fskills\u002Fclipify\u002F`)\n  - `analyze.py` — speaker timeline from two ROI motion files\n  - `build_pan.py` — ffmpeg crop x-expression with hard cuts\n  - `build_ass.py` — opus-style ASS captions from whisper JSON\n  - `audio_align.py` — find offset of a sub-clip in a longer source\n\nWorking dir: `\u002Ftmp\u002Fclipify\u002F` (mkdir at start, leave artifacts for debugging).\n\n---\n\n## Workflow\n\n### Step 1 — Find the funniest parts\n\n```bash\nmkdir -p \u002Ftmp\u002Fclipify\nffmpeg -y -hwaccel videotoolbox -i \"$VIDEO\" -vn -ac 1 -ar 16000 \u002Ftmp\u002Fclipify\u002Faudio.wav\nwhisper \u002Ftmp\u002Fclipify\u002Faudio.wav --model tiny.en --word_timestamps True --output_format json --output_dir \u002Ftmp\u002Fclipify --language en\n```\n\nRead the resulting JSON (or `.txt`) and pick 3–5 candidate clips. Funny signals to scan for:\n\n- **Punchlines and reactions:** words like \"what\", \"wait\", \"no way\", laughter, \"haha\", swearing\n- **Reversal moments:** setup question → unexpected answer\n- **Awkward pauses:** Whisper segment with long gap, or filler (\"uh\", \"um\")\n- **Self-roast \u002F quotable one-liners:** short declarative sentences that stand alone\n- **Audio peaks:** detect via `ffmpeg -af volumedetect` or look for rapid back-and-forth (alternating short Whisper segments)\n\nFor each candidate, propose: `[start, end, why-it's-funny, suggested title]`. Aim for 10–25s clips. Show the list and let the user confirm\u002Fpick.\n\n### Step 2 — Trim each chosen clip\n\n```bash\nffmpeg -y -ss \"$START\" -t \"$DURATION\" -i \"$VIDEO\" -c copy \u002Ftmp\u002Fclipify\u002Fclip_$N.mp4\n```\n\n(Use `-c copy` for instant trim. Re-encode only if cuts must be frame-accurate.)\n\n### Step 3 — Decide the output format\n\nAsk the user (skip if they already specified): \"9:16 (TikTok \u002F Reels), 16:9 (YouTube), or 1:1 (Insta feed)?\"\n\n### Step 4 — If 16:9 → 9:16: pan-between-faces vs split-screen\n\nDetect source aspect with `ffprobe`. If source is 16:9 and target is 9:16, ask:\n\n> \"Two options: **(a) hard-cut pan** that follows whoever is speaking (single face on screen at a time), or **(b) split-screen** stack with both faces visible. Which do you want?\"\n\nSkip the question if there's only one face (single-talker clip). For single-talker, just center-crop.\n\n#### Step 4a — Pan-between-faces (recommended for fast-cut talking-head dialogue)\n\n1. **Locate the two face ROIs.** Sample one frame: `ffmpeg -ss \u003Cmiddle> -i \u003Cclip> -frames:v 1 \u002Ftmp\u002Fclipify\u002Fprobe.jpg`. Read it. Eyeball each face's mouth+chin area as `x,y,w,h` in the source's pixel space. (No cv2 needed — camera is static within a clip; one frame is enough.) Verify by drawing boxes:\n\n   ```bash\n   ffmpeg -i probe.jpg -vf \"drawbox=x=$LX:y=$LY:w=$LW:h=$LH:color=cyan@0.9:t=4,drawbox=x=$RX:y=$RY:w=$RW:h=$RH:color=magenta@0.9:t=4\" verify.jpg\n   ```\n\n   Iterate **at most twice**. Boxes should cover mouth + chin and avoid hands\u002Fmics. Don't over-tune — frame differencing is forgiving.\n\n2. **Extract per-frame motion energy in each ROI:**\n\n   ```bash\n   ffmpeg -y -i clip.mp4 -filter_complex \"\n   [0:v]split=2[a][b];\n   [a]crop=$LW:$LH:$LX:$LY,format=gray,tblend=all_mode=difference,signalstats,metadata=mode=print:key=lavfi.signalstats.YAVG:file=\u002Ftmp\u002Fclipify\u002FL.txt[la];\n   [b]crop=$RW:$RH:$RX:$RY,format=gray,tblend=all_mode=difference,signalstats,metadata=mode=print:key=lavfi.signalstats.YAVG:file=\u002Ftmp\u002Fclipify\u002FR.txt[ra]\n   \" -map \"[la]\" -f null - -map \"[ra]\" -f null -\n   ```\n\n3. **Build speaker timeline** (min dwell 1.0s — short interjections merge into the prior speaker):\n\n   ```bash\n   python3 \u003Cskill-dir>\u002Fscripts\u002Fanalyze.py \u002Ftmp\u002Fclipify\u002FL.txt \u002Ftmp\u002Fclipify\u002FR.txt 1.0 > \u002Ftmp\u002Fclipify\u002Fsegments.json\n   ```\n\n4. **Pick pan x-coordinates** for a 9:16 vertical strip from the source. With source W=1920 and target W=1080, crop strip width = 608.\n   - LEFT_X = `face_left_center_x - 304` (clamp ≥ 0)\n   - RIGHT_X = `face_right_center_x - 304` (clamp ≤ source_W - 608)\n\n5. **Generate the hard-cut x expression and render:**\n\n   ```bash\n   EXPR=$(python3 \u003Cskill-dir>\u002Fscripts\u002Fbuild_pan.py \u002Ftmp\u002Fclipify\u002Fsegments.json $LEFT_X $RIGHT_X)\n   ffmpeg -y -hwaccel videotoolbox -i clip.mp4 -filter_complex \\\n     \"[0:v]crop=608:1080:x='$EXPR':y=0,scale=1080:1920:flags=lanczos[v]\" \\\n     -map \"[v]\" -map 0:a -c:v libx264 -preset fast -crf 20 -pix_fmt yuv420p \\\n     -c:a aac -b:a 192k \u002Ftmp\u002Fclipify\u002Fclip_panned.mp4\n   ```\n\n   Source 1920×1080 assumed; for 4K source either downscale first or double all coordinates.\n\n#### Step 4b — Split-screen (both faces always visible)\n\nTwo stacked tiles, 1080×960 each. The active speaker's tile is on top — overlay flips at speaker changes.\n\n```\n[0:v]split=2[a0][a1];\n[a0]crop=Wcrop:Hcrop:LX_tile:LY_tile,scale=1080:960,split=2[lt0][lt1];\n[a1]crop=Wcrop:Hcrop:RX_tile:RY_tile,scale=1080:960,split=2[rt0][rt1];\n[lt0][rt0]vstack[layoutL];\n[rt1][lt1]vstack[layoutR];\n[layoutL][layoutR]overlay=0:0:enable='\u003CRIGHT_SPEAKER_ENABLE>'[v]\n```\n\nBuild `\u003CRIGHT_SPEAKER_ENABLE>` from `segments.json` as `between(t,a,b)+between(t,a,b)+...` over the right-speaker segments. Tile crops should target ~720×640 around each face (1.125:1 to match 1080×960).\n\n### Step 5 — Add subtitles\n\nAsk once (only if user hasn't already specified a style):\n\n> \"Three subtitle styles: **opus** (big bold white, yellow active-word highlight), **karaoke** (4-word chunks, green highlight), **minimal** (clean Helvetica, no highlight). Or paste an example you like.\"\n\nIf they paste a reference image\u002Fexample: match the font, size, weight, color, position, and animation as closely as possible — write a custom ASS by hand or extend `build_ass.py`.\n\nElse use the preset:\n\n```bash\n# Re-run whisper on the trimmed clip for accurate timestamps relative to clip start\nwhisper \u002Ftmp\u002Fclipify\u002Fclip_panned.mp4 --model tiny.en --word_timestamps True --output_format json --output_dir \u002Ftmp\u002Fclipify --language en\npython3 \u003Cskill-dir>\u002Fscripts\u002Fbuild_ass.py \u002Ftmp\u002Fclipify\u002Fclip_panned.json \u002Ftmp\u002Fclipify\u002Fcaptions.ass opus\n```\n\nBurn captions:\n\n```bash\nffmpeg -y -i \u002Ftmp\u002Fclipify\u002Fclip_panned.mp4 -vf \"subtitles=\u002Ftmp\u002Fclipify\u002Fcaptions.ass\" \\\n  -c:v libx264 -preset fast -crf 20 -c:a copy \"$OUTPUT.mp4\"\n```\n\n### Step 6 — Deliver\n\n- Save each output to `\u003Csource_dir>\u002Fclipify_out\u002F` (mkdir if missing)\n- Print one line per clip: name, duration, what was funny, output path\n- Open the first output with `open \u003Cpath>` so the user can check it\n- Offer to iterate (different style, different ROI, swap to split-screen, retime captions)\n\n---\n\n## Pitfalls (lessons from prior runs — don't repeat)\n\n- **Don't over-tune ROIs.** Two iterations max. Motion-diff is forgiving — wider ROIs covering mouth+chin work fine even if not perfectly mouth-centered.\n- **Watch out for scene cuts inside a clip.** Run `ffmpeg -filter:v \"select='gt(scene,0.3)',showinfo\" -f null -` to count cuts. If a 16:9→9:16 clip has many cuts, the fixed face ROIs only work for the dominant scene; warn the user, and offer to either pick a single-take clip or accept off-center framing during cuts.\n- **Source resolution matters.** If source is 4K, either downscale to 1920×1080 first (faster, fine for 9:16 output) or multiply all ROI\u002Fpan coordinates by 2.\n- **Burned-in subtitles in source.** Some \"raw\" clips still have subtitles. If so, find the no-subs master via audio cross-correlation (`audio_align.py`) and trim from there.\n- **Don't run whisper on the full feature-length source if a short clip suffices.** Whisper the trimmed clip after Step 2; only whisper the full source in Step 1 if you need a transcript to find funny moments.\n- **State the plan in one line, then act.** Don't narrate every iteration.\n",{"name":5,"description":7},"master","8c91ae30409640de28e218b3e9c7fe01c01d257b","skills\u002Fclipify","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow","https:\u002F\u002Fgithub.com\u002Ffozagtx","hi.fawuzanpima@gmail.com","Forward deployed","2026-10-08 00:13:28",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add fozagtx\u002FBuildOS-workflow --skill clipify",{"tool":39,"command":40},"bunx","bunx skills add fozagtx\u002FBuildOS-workflow --skill clipify",{"tool":42,"command":43},"pnpm","pnpm dlx skills add fozagtx\u002FBuildOS-workflow --skill clipify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002FSKILL.md",true,[47,53,59,63,69,75,79,83],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},".gitignore","OTHER","其他",67,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002F.gitignore",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"assets\u002Fpreview.png","ASSET","资产文件",280420,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002Fassets\u002Fpreview.png",{"path":60,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":16},"LICENSE","许可证",1075,{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"README.md","REFERENCE","参考文档",3292,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002FREADME.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fanalyze.py","SCRIPT","脚本",2236,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002Fscripts\u002Fanalyze.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Faudio_align.py",951,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002Fscripts\u002Faudio_align.py",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fbuild_ass.py",2699,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002Fscripts\u002Fbuild_ass.py",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Fbuild_pan.py",524,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fclipify\u002Fscripts\u002Fbuild_pan.py",[88,95,102,109,116,125],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":20},"01M7EE49XAN8GE213J691P3RZ9","xitter","Interact with X\u002FTwitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fxitter\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":20},"01M7EE3TMR3CR7HR7HTCAKPTTR","writing-plans","Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":20},"01M7EE3AJ6V2VBVAX1WTV7M447","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\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwhisper\u002FSKILL.md",[],[],{"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":20},"01M7EE36AAP5THSCQAHH6JCWVV","weights-and-biases","Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fweights-and-biases\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":120,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":20},"01M7EE30R3S4EAK1FWJEBG7MW9","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":20},"01M7EE2X3PJ0ZJR0JJNF2M4NS5","web-pentest","Authorized web pentest: recon, proof-based exploits, report.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fweb-pentest\u002FSKILL.md",[],[]]