screencast-recorder SKILL.md skillA
screencast-recorder from jbaruch/speaker-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jbaruch/speaker-toolkit/screencast-recorder@git:20260907.e221e3ePins git:20260907.e221e3e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jbaruch/speaker-toolkit
- Path
skills/screencast-recorder/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260907.e221e3e, committed Sep 7, 2026
- First version recorded
- Sep 7, 2026
- Size
- 3,438 bytes
- Repository stars
- 22
- License
- none declared
Verify a recorded screen sequence against its approved storyboard: route and data revision, content framing and label readability, deliberate pans, the pointer landing on what it clicks, clip-to-clip continuity, and whether each visual proof occurs while its phrase is actually spoken. Use when checking a demo or screencast take before shipping it, when a recorded sequence must be proved rather than trusted, or when a clip join must be shown to be invisible. Verification only — this skill does…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Screencast Recorder — Verification Lane
Process steps in order. Do not skip ahead.
This skill verifies a take. It does **not** record one.
Resolve the absolute path of this loaded `SKILL.md`, then set
`speaker_toolkit_root` to the plugin root two directories above the directory
containing this file. Never derive it from the consumer working directory.
Treat `{speaker_toolkit_root}` as absolute in every toolkit-owned command;
sequence, media, and output paths remain consumer-owned.
## Step 1 — Resolve the interpreter
```bash
python3 "{speaker_toolkit_root}/skills/screencast-recorder/scripts/resolve-interpreter.py" <vault_root>
```
Emits `{"ok": true, "python_path": ..., "vault_root": ..., "database": ...}`.
Set `python_path` from that value; it is the interpreter authority for every
command below.
Exit 1 means it could not be resolved — the diagnostic names the cause. Repair
through its owner:
```
Skill(skill: "vault-ingress")
```
Never fall back to whichever `python3` is on `PATH`.
Proceed immediately to Step 2.
## Step 2 — Obtain the sequence description
The recording rig emits one JSON file describing the take: delivery resolution,
…Read the whole file at its exact version.
How to install
mdr add jbaruch/speaker-toolkit/screencast-recorder@sha256:a8e1b868062fd29dThe line at the top of this page pins the label git:20260907.e221e3e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_75o245ay7653n2ai)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, all committed on Sep 7, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260907.e221e3e latest | 2026-09-07 | e221e3e | 3,438 B | A | view · diff |
| git:20260907.970ba65 | 2026-09-07 | 970ba65 | 3,320 B | A | view · diff |
| git:20260907.b53c1f4 | 2026-09-07 | b53c1f4 | 3,355 B | A | view · diff |
| git:20260907.39450aa | 2026-09-07 | 39450aa | 3,414 B | A | view · diff |
| git:20260907.12c4d19 | 2026-09-07 | 12c4d19 | 3,719 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3438 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jbaruch/speaker-toolkit · 22 stars · license none declared · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_75o245ay7653n2ai GET https://markdownregistry.com/api/v1/resolve?ref=jbaruch/speaker-toolkit/screencast-recorder GET https://markdownregistry.com/api/v1/blob/a8e1b868062fd29d35c829c34e41a4a50ec252bc9c955ec9833c5c216d9fc57f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.