agentleFS
Sign inStart free
kiku-jwkiku-jw/codex-skills/screenshot/SKILL.md

screenshot

Skill0 starsChanged 4 months agoMITView on GitHub

Capture desktop or system screenshots with the bundled OS helpers when the user explicitly asks for a screenshot or when tool-specific capture cannot reach the target. Supports full screen, app/window, active window, and region capture.

50 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use obsidian-vault, slides and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • simo97Skill

    obsidian-vault

    Also in 4 projects that use this

  • JetBrainsSkill

    slides

    Create and edit presentation slide decks (`.pptx`) with PptxGenJS and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.

    Also in 5 projects that use this

  • simo97Skill

    edit-article

    The user will invoke this skill to help them edit an article.

    Also in 3 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 3 projects that use this

  • LesaniSkill

    writing-shape

    Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

    Also in 3 projects that use this

  • GoogleSkill

    setup-matt-pocock-skills

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 46 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use when: a tool-specific screenshot path already solves the task more directly and faithfully.

    line 10
  2. Distinctive:

    Use the bundled helpers to capture desktop, app, window, or region screenshots predictably across platforms without re-deriving OS-specific …

    line 14
  3. Distinctive:

    If the capture is for Codex inspection, view the saved temp image(s) in order and only manipulate them if needed.

    line 19
  4. Distinctive:

    Prefer tool-specific capture first when it is clearly better for the target.

    line 22
  5. Distinctive:

    Do not guess app names, window ids, or captured content.

    line 23
  6. Distinctive:

    If OS permissions or dependencies block capture, say that directly.

    line 25
  7. Distinctive:

    If relevant, the next inspection step, such as opening/viewing the image or retrying after permission setup.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 46 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Screenshot Capture

Metadata

  • Trigger when: the user wants an OS-level screenshot or a better-integrated tool cannot capture the target surface.
  • Do not use when: a tool-specific screenshot path already solves the task more directly and faithfully.

Skill Purpose

Use the bundled helpers to capture desktop, app, window, or region screenshots predictably across platforms without re-deriving OS-specific commands every time.

Instructions

  1. Choose the save-location rule first: user path if provided, OS default if the user just wants a screenshot, or temp storage when Codex needs the image for its own inspection. On macOS, run ~/.codex/skills/screenshot/scripts/ensure_macos_permissions.sh before app/window capture when possible.
  2. Use the exact helper that matches the OS: ~/.codex/skills/screenshot/scripts/take_screenshot.py for macOS/Linux and ~/.codex/skills/screenshot/scripts/take_screenshot.ps1 for Windows. Prefer helper flags such as --mode temp, --app, --window-name, --active-window, --window-id, or --region instead of improvising raw OS commands. Fall back to native commands only if the helper path is unavailable.
  3. If the capture is for Codex inspection, view the saved temp image(s) in order and only manipulate them if needed. If permissions or prerequisites fail, report the missing piece clearly and stop instead of pretending a capture exists.

Non-Negotiable Acceptance Criteria

  • Prefer tool-specific capture first when it is clearly better for the target.
  • Do not guess app names, window ids, or captured content.
  • Each generated image path must be reported explicitly, especially when multiple windows or displays are captured.
  • If OS permissions or dependencies block capture, say that directly.

Output

  • The saved screenshot path or paths.
  • The capture mode used: full screen, app/window, active window, or region.
  • If relevant, the next inspection step, such as opening/viewing the image or retrying after permission setup.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free