microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/cat-agent-skills --skill clipchamp-videogit clone --depth 1 https://github.com/microsoft/cat-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/cat-agent-skills/clipchamp-video)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/clipchamp-video"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/clipchamp-video/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/clipchamp-video"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/clipchamp-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 101 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00156 | $0.10684 |
| Opus 5 | $0.00078 | $0.05342 |
| Sonnet 5 | $0.00031 | $0.02137 |
| Haiku 4.5 | $0.00016 | $0.01068 |
Grade A, and why
clipchamp-video scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Filter by command line (`*edge-tenant*`) so you only touch your own window, and invoke it from Node with `child_process.execSync('powershell -NoProfile -ExecutionPolicy Bypass -File maximize.ps1')`. How it starts
The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clipchamp Narrated Demo Video Skill
Produce a polished, narrated demo video: real screen-flow footage of a live app/agent under an AI voiceover. This captures hard-won lessons — read it fully before starting.
STEP 0 — ASK THE USER: which assembly method? (do this FIRST, before recording)
The recording step is identical for both. The assembly + narration step has two paths — ask the user to pick before you start, e.g. via m_ask_user:
"How should I assemble the video — (A) Headless (ffmpeg + Ava neural TTS) — faster (~2–3 min), scripted, precise, produces a finished MP4; or (B) Clipchamp web UI — slower (~15–25 min of browser clicks) but gives you an editable Clipchamp project to hand-tweak later (transitions, captions, music)?"
Guidance to offer with the question:
- Default / recommended: (A) Headless — faster, deterministic, exact narration timing, no session-drop/upload-hook risk. Best when the deliverable is just the finished MP4.
- Choose (B) Clipchamp only if the user wants an editable project living in their Clipchamp account, or plans manual edits (transitions, captions, background music, hand re-timing).
- (B) requires the
playwright-browser_*MCP tools. If those tools are not available in the session (they can be disabled/dropped), (B) is impossible — tell the user and either have them re-enable the Browser Control tools / start a new chat, or fall back to (A).
Record the flow the same way either path (§1), then follow §2 + §2b (headless) or §3 (Clipchamp) based on their choice.
STEP 0b — ASK: page-only capture, or "your actions + the chat" (dual capture)?
If the user says anything like "record your actions and the chat at the same time", "show what you're doing while it runs", "a making-of", or "I want to see both" — they want the Scout/assistant conversation visible alongside the app, not just the app. That is a different capture mode and you must pick it BEFORE recording:
- Page-only (default, §1). Playwright
recordVideocaptures the page's internal buffer. Clean, no browser chrome, immune to other windows / screen switches. It physically cannot capture the Scout window —recordVideoonly ever sees the one page. - Dual capture (§1b). OS-level desktop capture with ffmpeg
gdigrabwhile Scout and the automated browser sit side by side. One capture, so the two halves are perfectly in sync for free.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- metadata.json 603 B
- README.md 5.1 KB
- scripts/arrange.ps1 2.1 KB runs code
- scripts/clone.ps1 1.7 KB runs code
- scripts/common.js 5.5 KB runs code
- scripts/diag.js 1.5 KB runs code
- scripts/dual-capture.js 2.8 KB runs code
- scripts/findagent.js 2.4 KB runs code
- scripts/maximize.ps1 1.4 KB runs code
- scripts/prep.ps1 1.3 KB runs code
- scripts/recorder.js 5.8 KB runs code
- scripts/require-playwright.js 958 B runs code
- scripts/verify.js 3.5 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 338 lines · 156 tokens per session scan A 68d54f71317c
clipchamp-video is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed today), licensed MIT. It adds 156 tokens to every session and 10,684 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.