inspect
Skill1 starsChanged 3 months agoMITView on GitHub
Probe, describe, compare, and batch-inspect video, audio, and image files using ffprobe. Use when you need metadata (duration, resolution, codecs, size), want to compare two files before/after processing, or need structured probe data to answer questions about a media file without modifying it.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- sanityops-org/sanityops-frameworktheir own version, first seen Nov 4, 2026
- cyrilichti/agent-workflowstheir own version, first seen Oct 17, 2026
- chalk-lab/Mooncake.jltheir own version, first seen Oct 8, 2026
- saleh-alhaddad/itqan-engineeringtheir own version, first seen Sep 29, 2026
- ZeeshanSultan/DocGovtheir own version, first seen Sep 13, 2026
- adezdev/blueprinttheir own version, first seen Aug 11, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- chalk-lab/Mooncake.jl★ 413same name
- Arman-Kudaibergenov/1c-ai-development-kit★ 163same name
- bluzir/claude-code-design★ 102same name
- NakaokaRei/swift-mcp-gui★ 61same name
- howardpen9/cc-inspect★ 17same name
- saleh-alhaddad/itqan-engineering★ 10same name
- HaipingShi/coderail★ 8same name
- cyrilichti/agent-workflows★ 3same name
- sanityops-org/sanityops-framework★ 3same name
- blackwell-systems/agentskills-code-inspector★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- site/AGENTS.mdAGENTS.md
- site/CLAUDE.mdCLAUDE.md
- audioSkill
- captions-complianceSkill
- downloadSkill
- forced-narrative-exactSkill
- imageSkill
- install-media-toolsSkill
- program-masterSkill
- shotsSkill
- speech-captionsSkill
- subtitlesSkill
- timecodeSkill
- video-transformationSkill
- vision-analysisSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Read-only media inspection.
- Very specific: line 41
If your tools showed a filesystem path when loading this SKILL.md, strip SKILL.md and use that folder.
- Very specific: line 42
If you already ran another mediaskills script (for example .../audio/scripts/extract.py), this skill is a sibling of that folder: same …
- Very specific: line 65
Prefer absolute paths for --input / --output when cwd is uncertain.
- Distinctive: line 70
Before running any script, treat these two failures differently:
- Very specific: line 73
Only escalate sandbox permissions if the error is explicitly a permission denial (e.g.
- Very specific: line 103
Check data.a vs data.b for duration drift, resolution change, or size reduction.
- Very specific: line 111
Use data.rows for a table.
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Inspect
Read-only media inspection. Use this skill when you need metadata without changing files.
When to use
- This skill — ffprobe metadata, duration, resolution, batch comparison tables, structured JSON for agent reasoning.
audio/image/video-transformation— when you need to transform media (trim, transcode, resize). Runinspectfirst to confirm codecs and duration before destructive operations.- Raw ffprobe — fine for one-off queries, but these scripts return consistent JSON the agent can parse reliably.
Gotchas
- Container vs stream duration — ffprobe
format.durationis authoritative for most files; individual stream durations can differ when audio/video lengths don't match (bad mux, trailing silence). Preferformat.durationfor edit boundaries. - No video stream — audio-only files return empty resolution;
resolution.pyreportswidth/heightas null, not an error. - Variable frame rate (VFR) —
avg_frame_ratein probe JSON may differ fromr_frame_rate. For frame-accurate edits, inspect both before assuming CFR. - Corrupt or partial files —
moov atom not foundmeans an incomplete MP4 (common with interrupted downloads). Re-download or remux; probing cannot recover metadata. - Image "video" streams — some still formats appear as a single-frame video stream; duration may be
N/Aor0.04seconds.
Running scripts
This skill's scripts live in scripts/ alongside this file. Before running any script, resolve its absolute path from this skill's own directory — do not assume the shell cwd is the skill folder, the repo root, or the workspace. Stay in the workspace (so media paths resolve) and pass the absolute script path to uv run:
uv run <skill_directory>/scripts/describe.py --input "<path-to-media>"<skill_directory> is a placeholder. Never pass those angle brackets to the shell — the command will fail. Replace it with a real absolute directory before invoking uv run.
How to get that directory (do this yourself; do not ask the user first; do not skip the skill):
- If your tools showed a filesystem path when loading this
SKILL.md, stripSKILL.mdand use that folder. - If you already ran another mediaskills script (for example
.../audio/scripts/extract.py), this skill is a sibling of that folder: same parent, directory nameinspect. - Otherwise search standard install locations and confirm the script exists:
NAME=inspect
for d in \
"$HOME/.agents/skills/$NAME" \
"$HOME/.cursor/skills/$NAME" \
"$HOME/.codex/skills/$NAME" \
"$HOME/.claude/skills/$NAME" \
"$PWD/.agents/skills/$NAME" \
"$PWD/.cursor/skills/$NAME" \
"$PWD/skills/$NAME"
do
if [ -f "$d/SKILL.md" ] && [ -e "$d/scripts/describe.py" ]; then
SKILL_DIR=$(cd "$d" && pwd)
break
fi
done
[ -n "$SKILL_DIR" ] || { echo "mediaskills: $NAME not found" >&2; exit 1; }
uv run "$SKILL_DIR/scripts/describe.py" --input "<path-to-media>"Prefer absolute paths for --input / --output when cwd is uncertain.
Missing binaries vs permissions
Before running any script, treat these two failures differently:
- If a required binary (
uv,ffprobe) reportsNo such file or directoryorcommand not found: this is a missing or unreachable binary, not a permissions issue. Escalating sandbox permissions will not fix it. Runcommand -v uvandcommand -v ffprobeto see whether they resolve at all. If not, install or re-link them (install-media-toolsdoctor/install) rather than retrying with wider permissions. - Only escalate sandbox permissions if the error is explicitly a permission denial (e.g.
Operation not permitted,Permission denied).
Recipes
Quick metadata check
uv run <skill_directory>/scripts/describe.py --input /path/to/clip.mp4Example result:
{"ok": true, "op": "inspect.describe", "data": {"format": "mov,mp4,m4a,3gp,3g2,mj2", "duration": "12.500000", "size": "1048576", "video": {"codec": "h264", "width": 1920, "height": 1080}, "audio_codecs": ["aac"]}, "output_paths": []}Full structured probe (for programmatic use)
uv run <skill_directory>/scripts/probe.py --input /path/to/clip.mp4Returns complete ffprobe JSON in data — all streams, tags, bit rates.
Compare before/after a transcode
uv run <skill_directory>/scripts/compare.py --input-a original.mp4 --input-b transcoded.mp4Check data.a vs data.b for duration drift, resolution change, or size reduction.
Batch inventory a folder
uv run <skill_directory>/scripts/batch_probe.py --paths clip1.mp4 clip2.mp4 clip3.wavUse data.rows for a table. Rows with error indicate unreadable paths.
Answer a specific question (agent workflow)
uv run <skill_directory>/scripts/ask.py --input clip.mp4 --question "Does this file have an audio track?"Returns full probe JSON plus your question — the agent reads data.probe.streams and answers.
Troubleshooting
| Error / symptom | Likely cause | Action |
ffprobe not found | Binary missing | Run install-media-tools doctor/install |
Invalid data found when processing input | Not a media file or corrupt | Verify file type with file command |
width/height null | Audio-only or subtitle-only | Use probe.py to list streams |
Duration N/A | Still image or broken header | Try ffprobe -show_format manually |
Available scripts
| Script | Purpose |
scripts/probe.py | Full ffprobe JSON |
scripts/describe.py | Compact human/agent summary |
scripts/duration.py | Duration in seconds |
scripts/resolution.py | Video width × height |
scripts/compare.py | Side-by-side summary of two files |
scripts/batch_probe.py | Table of metadata for many files |
scripts/ask.py | Probe + question for agent reasoning |
Acceptance checks (agent must pass before delivery)
- Contract: exit 0,
ok: true. - Spot-check: duration/streams/codecs answer the user's question; use
compare.pywhen verifying a transform result against its source. - On failure: re-probe or escalate; do not invent metadata.
Do not use for
- Modifying or transcoding media (use
audio,image, orvideo-transformation) - Downloading from URLs (use
download) - Generating captions from speech (use
speech-captions)
Related skills
install-media-tools— install ffprobe/ffmpegaudio,video-transformation,image— processing after inspection
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

