← All skills
video-use
62 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a media skill usually calls an AI service over the internet.
By ma08/botfiles (GitHub) · media · 29 stars · scanned at commit 0009976
Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.
Works with any agent that supports SKILL.md skills.
What this skill can do
Changes files outside its own folder
The author does not mention this.
Found in 6 places.
Show 3 more
Downloads and installs other software
The author does not mention this.
Found in 20 places.
Show 17 more
- codex/skills/video-use/SKILL.md, line 64
- Python deps installed (`uv sync` or `pip install -e .` inside the repo). - codex/skills/video-use/SKILL.md, line 67
- First-use animation setup happens inside the slot directory, never at the video-use repo root. HyperFrames can be invoked with `npx --yes hyperframes ...`; Re - codex/skills/video-use/SKILL.md, line 210
For HyperFrames slots, scaffold the slot inside `edit/animations/slot_<id>/` with `npx --yes hyperframes init . --example blank --non-interactive --skip-skills` - codex/skills/video-use/SKILL.md, line 212
For Remotion slots, keep the Remotion project isolated inside the same slot directory, scaffold with `npx create-video@latest` or install Remotion locally there - codex/skills/video-use/install.md, line 26
- Do everything yourself. Only ask the user for things you cannot generate — the ElevenLabs API key, and confirmation before `brew install`. - codex/skills/video-use/install.md, line 46
command -v uv >/dev/null && uv sync || pip install -e . - codex/skills/video-use/install.md, line 57
command -v ffmpeg >/dev/null || brew install ffmpeg - codex/skills/video-use/install.md, line 58
command -v yt-dlp >/dev/null || brew install yt-dlp # optional - codex/skills/video-use/install.md, line 151
- If `pyproject.toml` changed deps, re-run `uv sync` / `pip install -e .` after pulling. - codex/skills/video-use/install.md, line 160
- HyperFrames, Remotion, and Manim are optional animation engines. Don't install or prefer one globally during setup; pick the engine per animation slot in `SKI - codex/skills/video-use/skills/manim-video/README.md, line 19
Python 3.10+, Manim CE (`pip install manim`), LaTeX, ffmpeg. - codex/skills/video-use/skills/manim-video/SKILL.md, line 27
Run `scripts/setup.sh` to verify all dependencies. Requires: Python 3.10+, Manim Community Edition v0.20+ (`pip install manim`), LaTeX (`texlive-full` on Linux, - codex/skills/video-use/skills/manim-video/references/rendering.md, line 141
pip install "manim-voiceover[elevenlabs]" - codex/skills/video-use/skills/manim-video/references/rendering.md, line 143
pip install "manim-voiceover[gtts]" # Google TTS (free, lower quality) - codex/skills/video-use/skills/manim-video/references/rendering.md, line 144
pip install "manim-voiceover[azure]" # Azure Cognitive Services - codex/skills/video-use/skills/manim-video/scripts/setup.sh, line 9
python3 -c "import manim" 2>/dev/null && ok "Manim $(manim --version 2>&1 | head -1)" || { fail "Manim not installed: pip install manim"; errors=$((errors+1)); - codex/skills/video-use/skills/manim-video/scripts/setup.sh, line 10
command -v pdflatex &>/dev/null && ok "LaTeX (pdflatex)" || { fail "LaTeX not found (macOS: brew install --cask mactex-no-gui)"; errors=$((errors+1)); }
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README.
Found in 18 places.
Show 15 more
- codex/skills/video-use/helpers/render.py, line 64
subprocess.run(cmd, check=True) - codex/skills/video-use/helpers/render.py, line 123
out = subprocess.run( - codex/skills/video-use/helpers/render.py, line 130
except subprocess.CalledProcessError: - codex/skills/video-use/helpers/render.py, line 194
subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE) - codex/skills/video-use/helpers/render.py, line 265
subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE) - codex/skills/video-use/helpers/render.py, line 395
proc = subprocess.run(cmd, capture_output=True, text=True) - codex/skills/video-use/helpers/render.py, line 440
subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE) - codex/skills/video-use/helpers/render.py, line 472
subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE) - codex/skills/video-use/helpers/render.py, line 552
subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE) - codex/skills/video-use/helpers/timeline_view.py, line 60
subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) - codex/skills/video-use/helpers/timeline_view.py, line 85
r = subprocess.run(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) - codex/skills/video-use/helpers/transcribe.py, line 55
subprocess.run(cmd, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL) - codex/skills/video-use/skills/manim-video/SKILL.md, line 169
manim -ql script.py Scene1_Introduction Scene2_CoreConcept # draft - codex/skills/video-use/skills/manim-video/SKILL.md, line 176
cat > concat.txt << 'EOF' - codex/skills/video-use/skills/manim-video/SKILL.md, line 186
manim -ql --format=png -s script.py Scene2_CoreConcept # preview still
Can call paid AI services billed to you
This is disclosed by the author in the skill's SKILL.md or README. Expected for a media skill.
Found in 2 places.
Connects to the internet
The author does not mention this. Expected for a media skill.
Found in 2 places.
Safer alternatives
Low-risk skills in the same category (media) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'video-use' ] || [ -L ~/.agents/skills/'video-use' ]; then echo 'A skill folder named video-use already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ma08/botfiles' "$d" && git -C "$d" checkout --quiet '00099765c7700fd71f0257fa7274c2e4a0248fc1' -- 'codex/skills/video-use' && mkdir -p ~/.agents/skills && cp -R "$d"/'codex/skills/video-use' ~/.agents/skills/'video-use' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'video-use' ~/.claude/skills/'video-use' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for ma08/botfiles shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/ma08/botfiles/)
Score history
| Date | Version | Score |
|---|
| 2026-11-12 | 0009976 | 62 |