screenshot

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

3.63x

Quality

92%

Does it follow best practices?

Impact

69%

3.63x

Average score across 5 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable commands and clear workflows including error-recovery loops, and it references real bundled files at one level of depth. Its only weakness is moderate verbosity in the repeated per-platform command enumeration that could be condensed.

Suggestions

Consolidate the macOS, Linux, and Windows 'Common patterns' command lists — the default/temp/explicit-path cases are nearly identical across platforms and could share a parameter table, keeping only OS-specific flags distinct.

Reduce repetition of the 'bash ensure_macos_permissions.sh && python3 take_screenshot.py' preflight pattern; state the combine-once rule once and reference it rather than re-printing the full command in multiple sections.

Consider moving the per-flag reference (--window-id, --active-window, --region, etc.) into a single compact options table instead of a separate fenced block per flag.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and command-driven, but the long enumeration of near-identical per-platform command patterns and repeated 'run the helper from the repo root' framing adds some length that could be tightened without losing clarity.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands across macOS, Linux, and Windows plus direct-OS fallbacks, with concrete flags and examples for each capture mode.	3 / 3
Workflow Clarity	Save-location rules are sequenced explicitly, the macOS preflight-plus-capture combination is laid out as a numbered flow, and the error-handling section gives explicit validate/diagnose-and-retry feedback loops for failing captures.	3 / 3
Progressive Disclosure	The body is a clear overview that points one level deep to real bundled scripts (ensure_macos_permissions.sh, take_screenshot.py/.ps1) and assets, with no nested-reference chains; content is appropriately split into sections and the referenced files exist.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and clearly answers both what the skill does and when to use it, with a distinctive OS-level-capture niche. It does not over-claim or pad with fluff.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete capture capabilities — 'full screen, specific app or window, or a pixel region' — matching the anchor for listing several specific concrete actions, and it avoids vague language.	3 / 3
Completeness	It answers both 'what' (OS-level desktop/window/region capture) and 'when' with an explicit 'Use when...' clause covering explicit user requests and tool-specific-capture-unavailable cases.	3 / 3
Trigger Term Quality	It uses natural terms a user would say — 'screenshot', 'desktop', 'system screenshot', 'app or window', 'pixel region' — giving good coverage of common phrasings rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The niche is clear — OS-level desktop capture as a fallback when tool-specific capabilities are unavailable — with distinct triggers that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/skills
Commit: 49f948f

Reviewed: 18 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.