Show HN: A video editor where the LLM never watches the video

A developer known as ranahaani released 'i-hate-editing', an open-source AI video editor skill for Claude Code, Cursor, and Codex that edits talking-head footage without the LLM ever watching the video, relying instead on audio transcription via whisper.cpp and local scripts. The tool automates take selection, silence removal, captioning, screen capture, and sound effects, and is installed via 'npx skills add ranahaani/i-hate-editing'.

Drop in raw talking-head takes. Get back something you can publish. I named it after a note to myself: never hand back work that still needs fixing by hand. Same recording on both phones. Left is what came off the camera; right is what came back. Instagram reel this footage shipped as https://www.instagram.com/reel/Db3VN1Boyej/ . The skill picks the take, decides the repo and the docs page were worth capturing, where to zoom, which line gets the highlighter, what goes on each card, and where every sound lands. You say "punchier." It owns the numbers. - Cuts from silence and word onsets, not from scrubbing the timeline - Re-transcribes a short window around every seam so repeated words and mid-clause cuts get caught before you see a preview - Writes captions that still read on a phone, with a proofread gate before they ship - Captures real pages as tall stills, then scrolls, zooms, and highlights the line you said no mocked screenshots - Places free-licensed SFX by intent and aligns peaks so a short window is actually audible - Hands back a package: master, platform crops, ranked thumbnails, post lines - Remembers corrections in taste.md so the tenth video is better than the first - Runs transcription on your machine with whisper.cpp . No cloud STT key. Built for talking-head reels and YouTube explainers. npx skills add ranahaani/i-hate-editing That registers the skill with your agent. You still need the local tools ffmpeg , whisper-cpp , Playwright Chromium . Details in install.md /ranahaani/i-hate-editing/blob/main/install.md . Works in Claude Code, Cursor, Codex, and anything else with a shell: Set up https://github.com/ranahaani/i-hate-editing for me. Read install.md first: clone the repo to a stable path, symlink it into this agent's skills directory, install ffmpeg + whisper.cpp, create the Python venv with playwright + pillow, and optionally run scripts/sfx library.py install. Then read SKILL.md for daily usage. After install, don't start editing — tell me it's ready and wait for me to drop footage into a folder. git clone https://github.com/ranahaani/i-hate-editing ~/Developer/i-hate-editing ln -sfn ~/Developer/i-hate-editing ~/.claude/skills/i-hate-editing Claude Code ln -sfn ~/Developer/i-hate-editing ~/.cursor/skills/i-hate-editing Cursor ln -sfn ~/Developer/i-hate-editing ~/.codex/skills/i-hate-editing Codex cd ~/Developer/i-hate-editing uv venv .venv && uv pip install --python .venv playwright pillow .venv/bin/playwright install chromium brew install ffmpeg whisper-cpp macOS; use your package manager on Linux cd /path/to/your/footage claude or your agent of choice edit these into a reel It scans the machine, asks five questions, picks a Whisper model for your language and hardware, and starts. More in install.md /ranahaani/i-hate-editing/blob/main/install.md . The model does not watch the video. Audio is the clock. Scripts do the mechanical work; the agent only makes taste calls. %%{init: { "theme": "base", "themeVariables": { "fontFamily": "ui-sans-serif, system-ui, sans-serif", "fontSize": "14px", "primaryTextColor": " 0f172a", "lineColor": " 94a3b8", "clusterBkg": " ffffff00", "clusterBorder": " e2e8f0", "edgeLabelBackground": " ffffff", "tertiaryColor": " f8fafc" }, "flowchart": { "curve": "basis", "padding": 16, "nodeSpacing": 32, "rankSpacing": 40, "htmlLabels": true } }}%% flowchart TB RAW "🎬 raw takes" :::src PROF "🎛️ profile.yml" :::cfg subgraph A "🎧 1 · LISTEN" direction LR SCAN "🔍 scan" :::listen ASR "🗣️ whisper.cpp" :::listen PACK "📄 pack" :::listen SIL "🔇 silences" :::listen TAKES "takes.md" :::artBlue GAPS "gaps.json" :::artBlue SCAN -- ASR -- PACK -- TAKES SCAN -- SIL -- GAPS end subgraph B "✂️ 2 · CUT · HARD GATE" direction LR EDL "edl.json" :::artAmber RND "🎞️ render" :::cut VER{"🛡️ verify<br/ seam re-ASR"}:::gate GRD "🎨 grade" :::cut CUTV "cut.mp4" :::artAmber EDL -- RND -- CUTV -- VER VER -- "❌ fail" -- EDL VER -- "✅ pass" -- GRD end subgraph C "✨ 3 · ENRICH" direction LR CAP "💬 captions" :::enrich PRF "🌐 proof" :::enrich SFX "🔊 sfx + music" :::enrich CMP "🧩 compose" :::enrich MASTER "master.mp4" :::artPink CAP -- CMP PRF -- CMP SFX -- CMP CMP -- MASTER end subgraph D "🚀 4 · SHIP" direction LR DEL "📦 deliver" :::ship PKG "studio/out" :::artGreen REV "👀 review" :::ship DEL -- PKG -- REV end RAW -- SCAN PROF -.- SCAN PROF -.- CAP TAKES -- EDL GAPS -- EDL GRD -- CAP GRD -- PRF GRD -- SFX MASTER -- DEL classDef src fill: 0f172a,stroke: facc15,stroke-width:3px,color: fef08a classDef cfg fill: fef3c7,stroke: f59e0b,stroke-width:2px,color: 92400e classDef listen fill: dbeafe,stroke: 2563eb,stroke-width:2px,color: 1e3a8a classDef cut fill: ffedd5,stroke: ea580c,stroke-width:2px,color: 9a3412 classDef enrich fill: f3e8ff,stroke: 9333ea,stroke-width:2px,color: 581c87 classDef ship fill: dcfce7,stroke: 16a34a,stroke-width:2px,color: 14532d classDef gate fill: fee2e2,stroke: dc2626,stroke-width:3px,color: 7f1d1d classDef artBlue fill: eff6ff,stroke: 3b82f6,stroke-width:2px,color: 1d4ed8 classDef artAmber fill: fffbeb,stroke: d97706,stroke-width:2px,color: b45309 classDef artPink fill: fdf4ff,stroke: c026d3,stroke-width:2px,color: 86198f classDef artGreen fill: f0fdf4,stroke: 22c55e,stroke-width:2px,color: 15803d style A fill: eff6ff,stroke: 3b82f6,stroke-width:2px,color: 1e40af style B fill: fff7ed,stroke: f97316,stroke-width:2px,color: c2410c style C fill: faf5ff,stroke: a855f7,stroke-width:2px,color: 7e22ce style D fill: f0fdf4,stroke: 22c55e,stroke-width:2px,color: 15803d linkStyle 8 stroke: dc2626,stroke-width:2.5px linkStyle 9 stroke: 16a34a,stroke-width:2.5px verify blocks the cut. review is when you look at the package. If you change the cut after captions and sound are built, those timestamps are wrong. Start that layer over. footage/ ├── take-01.mp4 your sources stay put └── studio/ everything the skill writes ├── profile.yml ├── taste.md ├── transcripts/ ├── edl.json ├── composition/ └── out/ what you publish from Two things matter. The rest is plumbing. Joins love to leave a word sitting there twice. Cuts land mid-clause and flip what you meant. A whole-file transcript papers over both. So after the cut renders, verify re-transcribes short windows on each seam. Repeats are mechanical. Broken clauses get flagged for a human call. And when you correct something, it sticks. "Captions feel early" goes into taste.md and shows up on the next job. You should not have to teach the same lesson twice. You also should not be asked which font, which transition, or what decibel level. Say punchier , slower , less music . The studio owns the numbers. Name a repo, an article, a number. The skill opens the real page in a vertical viewport, grabs one tall still, then scrolls, zooms, and draws a highlighter across the line you said. A screen recording locks scroll speed forever. A still plus motion in the composition can re-time with the cut and sit on the same timeline as your face, captions, and sound. Targets are text, not CSS selectors. If the line is not on the page, it says so instead of grabbing something nearby. Each rule exists because a render failed once and we paid for it. | File | Covers | |---|---| | HARD-RULES.md /ranahaani/i-hate-editing/blob/main/HARD-RULES.md | Silent failures. Non-negotiable. | | rules/cutting.md /ranahaani/i-hate-editing/blob/main/rules/cutting.md | Take selection, seams, what to remove | | rules/hooks.md /ranahaani/i-hate-editing/blob/main/rules/hooks.md | Openings, headline, retention | | rules/captions.md /ranahaani/i-hate-editing/blob/main/rules/captions.md | Timing, chunking, style | | rules/sound.md /ranahaani/i-hate-editing/blob/main/rules/sound.md | Placement, levels, audibility | | rules/motion.md /ranahaani/i-hate-editing/blob/main/rules/motion.md | Zooms, pacing, easing | | rules/framing.md /ranahaani/i-hate-editing/blob/main/rules/framing.md | Crops, splits, composition | | rules/proof.md /ranahaani/i-hate-editing/blob/main/rules/proof.md | Screenshots, B-roll, zoom, highlight | Agent instructions: SKILL.md /ranahaani/i-hate-editing/blob/main/SKILL.md . Threat model: SECURITY.md /ranahaani/i-hate-editing/blob/main/SECURITY.md . | Tool | Why | Required | |---|---|---| | ffmpeg / ffprobe | Media | Yes | | whisper.cpp | Local transcription | Yes | | node 22+ | HyperFrames | Yes | | playwright + pillow | Proof capture, thumbnails | For proof / deliver | | yt-dlp | Reference footage | Optional | - Talking-head short-form and explainers. Not travel montages or multi-cam. - You bring the music bed. The skill ducks it; it does not license tracks. - Proof capture needs Chromium. Skip it if face + captions is enough. - First Whisper download is roughly 0.5–3 GB, depending on language and hardware. Best PR is a rule: what failed, what it cost, what you will never do again. Add it under rules/ /ranahaani/i-hate-editing/blob/main/rules or in HARD-RULES.md /ranahaani/i-hate-editing/blob/main/HARD-RULES.md . uv venv .venv && uv pip install --python .venv pytest .venv/bin/pytest -q Footage stays on your machine. Scripts can still hit the network for proof pages, Mixkit SFX, and a pinned HyperFrames package. See SECURITY.md /ranahaani/i-hate-editing/blob/main/SECURITY.md . Copyright on yt-dlp downloads and music beds is on you. Brand marks from Simple Icons / Lucide are for editorial use; check trademark rules before ads. review.py binds localhost by default. Only pass --lan on a network you trust. No auth on that server. Composition and rendering by HyperFrames https://github.com/heygen-com/hyperframes version pinned in scripts/compose.py . MIT. Vulnerabilities: SECURITY.md /ranahaani/i-hate-editing/blob/main/SECURITY.md .