capture-screen SKILL.md skillA
capture-screen from dimitar-radenkov/pointframe is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add dimitar-radenkov/pointframe/capture-screen@git:20261005.bc01c9aPins git:20261005.bc01c9a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dimitar-radenkov/pointframe
- Path
plugin/pointframe/skills/capture-screen/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261005.bc01c9a, committed Oct 5, 2026
- Size
- 1,697 bytes
- Repository stars
- 15
- License
- MIT
Look at the user's Windows screen with Pointframe. Use when the user asks you to look at, check, read or compare something on their screen, a monitor or an app window, or to read on-screen text such as an error dialog.
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
# Capture and look at the screen The Pointframe MCP tools let you see the Windows desktop. They only observe; they never click or type. 1. Call `list_displays` to get the monitors, or `list_windows` to get visible windows with their handles, titles and process names. 2. To look at a whole monitor or part of one, call `capture_monitor` with a monitor name exactly as `list_displays` returned it. To look at one app, call `capture_window` with its handle from `list_windows`. The image comes back inline so you can see it. 3. To read text instead of describing pixels, call `read_text_from_window` or `read_text_from_monitor`. They use Windows OCR and are cheaper than an image when the text is all you need. 4. To find an earlier screenshot, call `search_captures` with a word from its filename or its on-screen text, then `get_capture` with the ID. Tips: - Capture the specific window instead of the whole monitor when you can; the image is smaller and shows only what matters. - Pass `includeImage: false` when you only need the saved file path and metadata. - A screenshot can contain private information. Capture only what the task needs, and tell the user what you captured. …
Read the whole file at its exact version.
How to install
mdr add dimitar-radenkov/pointframe/capture-screen@sha256:8b9c0d2f719a43f5The line at the top of this page pins the label git:20261005.bc01c9a, 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_k63otyskxrpugrq6)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 5, 2026.
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 (1697 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
dimitar-radenkov/pointframe · 15 stars · license MIT · pushed 2026-10-26 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_k63otyskxrpugrq6 GET https://markdownregistry.com/api/v1/resolve?ref=dimitar-radenkov/pointframe/capture-screen GET https://markdownregistry.com/api/v1/blob/8b9c0d2f719a43f5238e0862ea25aa805b3b87c6c9ae727115f395eb235d741d
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.
More from dimitar-radenkov/pointframe
Every file in dimitar-radenkov/pointframe