メニュー
Extract, normalize, mix, and process audio tracks - audio manipulation and analysis
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
SkillsBench contribution workflow. Use when: (1) Creating benchmark tasks, (2) Understanding repo structure, (3) Preparing PRs for task submission.
SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. Use when the user wants to create a new SkillsBench task, scaffold a task from an existing workflow (notebook, Excel workbook, document, dataset), convert a prompt or a benchmark item into a SkillsBench task, write skills for a task, or prepare a SkillsBench PR. Pairs with `task-review` (run that as a self-check before submitting).
SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks against the track-specific rubric, benchmarks the task across oracle plus Claude and Codex (with and without skills), audits trajectories for cheating and skill invocation, and produces a `pr-N-task-timestamp-run.txt` review report alongside a `prN.zip` bundle of trajectories. Use when reviewing a SkillsBench task PR (by number, branch, or local task path), when the user asks to review a task, run benchmarks on a PR, audit a submission, classify a task as research or multimodal track, or prepare a comment to post on a SkillsBench PR.
Methodology for clause-by-clause review of a contract against a structured deviation policy ("playbook"). Covers how to walk a playbook, locate the matching provision in the contract, apply rule types (max-value, must-be-present, must-be-absent, acceptable-set, must-have-feature), classify the result (ok / risk / reject), choose the prescribed action, and ground each finding in a verbatim excerpt. Use whenever reviewing any contract — NDA, MSA, vendor DD questionnaire, lease, DPA — against a structured rules-based playbook.
Reference for the standard clauses found in commercial non-disclosure agreements (mutual and one-way) — what each clause does, the surface forms it appears in, and how to recognise it in unfamiliar drafting. Use when reviewing, comparing, or extracting provisions from any confidentiality / NDA / mutual NDA / standstill-and-confidentiality agreement.
Read Microsoft Excel (.xlsx) files robustly with `openpyxl` (or `pandas`). Covers multi-sheet workbooks, header rows, empty cells, merged cells, comma-separated list cells, and converting a sheet to a list-of-dicts the rest of your code can consume. Use when a task input or reference document is an `.xlsx` file rather than JSON/CSV.
| name | ffmpeg-audio-processing |
| description | Extract, normalize, mix, and process audio tracks - audio manipulation and analysis |
Extract, normalize, mix, and process audio tracks from video files.
# Extract as MP3
ffmpeg -i video.mp4 -vn -acodec libmp3lame -q:a 2 audio.mp3
# Extract as AAC (copy, no re-encode)
ffmpeg -i video.mp4 -vn -c:a copy audio.aac
# Extract as WAV (uncompressed)
ffmpeg -i video.mp4 -vn -acodec pcm_s16le audio.wav
# Extract specific audio stream
ffmpeg -i video.mp4 -map 0:a:1 -c:a copy audio2.aac
# Normalize loudness (ITU-R BS.1770-4)
ffmpeg -i input.mp4 -af "loudnorm=I=-23:TP=-1.5:LRA=11" output.mp4
# Simple normalization
ffmpeg -i input.mp4 -af "volume=2.0" output.mp4
# Peak normalization
ffmpeg -i input.mp4 -af "volumedetect" -f null -
# Then use the detected peak to normalize
ffmpeg -i input.mp4 -af "volume=0.5" output.mp4
# Increase volume by 6dB
ffmpeg -i input.mp4 -af "volume=6dB" output.mp4
# Decrease volume by 3dB
ffmpeg -i input.mp4 -af "volume=-3dB" output.mp4
# Set absolute volume
ffmpeg -i input.mp4 -af "volume=0.5" output.mp4
# Extract left channel
ffmpeg -i stereo.mp3 -map_channel 0.0.0 left.mp3
# Extract right channel
ffmpeg -i stereo.mp3 -map_channel 0.0.1 right.mp3
# Convert stereo to mono
ffmpeg -i stereo.mp3 -ac 1 mono.mp3
# Convert mono to stereo
ffmpeg -i mono.mp3 -ac 2 stereo.mp3
# Replace audio track
ffmpeg -i video.mp4 -i audio.mp3 -c:v copy -map 0:v:0 -map 1:a:0 output.mp4
# Mix two audio tracks
ffmpeg -i video.mp4 -i audio2.mp3 \
-filter_complex "[0:a][1:a]amix=inputs=2:duration=first" \
-c:v copy output.mp4
# Mix with volume control
ffmpeg -i video.mp4 -i bgm.mp3 \
-filter_complex "[0:a]volume=1.0[voice];[1:a]volume=0.3[music];[voice][music]amix=inputs=2:duration=first" \
-c:v copy output.mp4
# Delay audio by 0.5 seconds
ffmpeg -i video.mp4 -itsoffset 0.5 -i video.mp4 \
-map 0:v -map 1:a -c copy output.mp4
# Using adelay filter (milliseconds)
ffmpeg -i input.mp4 -af "adelay=500|500" output.mp4
# Resample to 48kHz
ffmpeg -i input.mp4 -af "aresample=48000" output.mp4
# Resample audio only
ffmpeg -i input.mp4 -vn -af "aresample=48000" -ar 48000 audio.wav
# High-pass filter (remove low frequencies)
ffmpeg -i input.mp4 -af "highpass=f=200" output.mp4
# Low-pass filter (remove high frequencies)
ffmpeg -i input.mp4 -af "lowpass=f=3000" output.mp4
# Band-pass filter
ffmpeg -i input.mp4 -af "bandpass=f=1000:width_type=h:w=500" output.mp4
# Fade in/out
ffmpeg -i input.mp4 -af "afade=t=in:st=0:d=2,afade=t=out:st=8:d=2" output.mp4
# Detect volume levels
ffmpeg -i input.mp4 -af "volumedetect" -f null -
# Measure loudness (LUFS)
ffmpeg -i input.mp4 -af "ebur128=peak=true" -f null -
# Get audio statistics
ffprobe -v error -select_streams a:0 \
-show_entries stream=sample_rate,channels,bit_rate \
-of json input.mp4
# Concatenate audio files
ffmpeg -i "concat:audio1.mp3|audio2.mp3|audio3.mp3" -c copy output.mp3
# Using file list
# file 'audio1.mp3'
# file 'audio2.mp3'
ffmpeg -f concat -safe 0 -i list.txt -c copy output.mp3
-vn to disable video when extracting audio-map to select specific streams-af for audio filters-ac for channel count-ar for sample rate