peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

1.92x

Quality

43%

Does it follow best practices?

Impact

77%

1.92x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/peekaboo/SKILL.md

Quality

Discovery

22%

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 too terse and vague to effectively guide skill selection. It names the tool (Peekaboo CLI) and the general domain (macOS UI) but fails to enumerate specific capabilities or provide any trigger guidance for when Claude should select this skill. Without concrete actions and a 'Use when...' clause, this description would be difficult to reliably match against user requests.

Suggestions

Add a 'Use when...' clause with explicit trigger terms like 'Use when the user asks to take screenshots, interact with macOS windows, automate UI clicks, or inspect accessibility elements on macOS.'

List specific concrete actions the skill enables, such as 'Takes screenshots, lists open windows, reads accessibility trees, clicks UI elements, and automates macOS desktop interactions.'

Include natural user keywords like 'screenshot', 'screen capture', 'window list', 'UI testing', 'desktop automation', and 'accessibility inspector' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description says 'Capture and automate macOS UI' which is vague. It doesn't list specific concrete actions like taking screenshots, clicking elements, reading accessibility trees, or other specific capabilities. 'Capture' and 'automate' are broad terms.	1 / 3
Completeness	The description provides a weak 'what' (capture and automate macOS UI) but completely lacks a 'when' clause. There is no 'Use when...' or equivalent trigger guidance, which per the rubric should cap completeness at 2, but the 'what' is also too vague, bringing this to 1.	1 / 3
Trigger Term Quality	It includes 'macOS UI', 'Peekaboo', and 'CLI' which are somewhat relevant keywords. However, it misses natural user terms like 'screenshot', 'screen capture', 'UI automation', 'accessibility', 'click', 'window', or 'desktop automation' that users would actually say.	2 / 3
Distinctiveness Conflict Risk	Mentioning 'Peekaboo CLI' and 'macOS UI' provides some distinctiveness, but 'capture and automate' could overlap with other automation or screenshot tools. The tool name helps but the actions described are too broad to clearly distinguish it.	2 / 3
	Total	6 / 12 Passed

Implementation

64%

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

This is a solid reference-style skill with excellent actionability — the concrete bash examples are its strongest asset. However, it reads more like a comprehensive CLI reference than a focused skill guide, with the exhaustive command listing adding bulk without proportional value. Adding validation/error-handling steps to workflows and splitting the command catalog into a separate reference file would significantly improve it.

Suggestions

Add validation checkpoints and error recovery guidance to multi-step workflows (e.g., 'If `peekaboo see` returns no elements, verify the app is focused and permissions are granted').

Move the exhaustive feature/command catalog (Core/Interaction/System/Vision sections) to a separate REFERENCE.md file and link to it from the SKILL.md overview.

Add a brief troubleshooting section or inline notes for common failure modes (permissions denied, element not found, stale snapshot IDs).

Dimension	Reasoning	Score
Conciseness	The skill is fairly efficient and avoids explaining basic concepts, but the exhaustive feature listing (Core/Interaction/System/Vision sections) is essentially a command catalog that could be trimmed or moved to a reference file. Some of this is useful but borders on verbose for a SKILL.md overview.	2 / 3
Actionability	The skill provides numerous concrete, copy-paste-ready bash commands covering the full range of use cases. The examples are executable, specific, and cover common workflows like see->click->type, window targeting, capture, app management, and keyboard input.	3 / 3
Workflow Clarity	The 'See -> click -> type' example demonstrates a clear multi-step workflow, and the quickstart provides a logical sequence. However, there are no explicit validation checkpoints or error recovery steps — e.g., no guidance on what to do if permissions fail, if an element ID isn't found, or if a click doesn't land correctly.	2 / 3
Progressive Disclosure	The content is reasonably well-organized with clear section headers, but it's monolithic — the extensive command catalog and parameter reference tables could be split into separate reference files. With no bundle files provided, there's no progressive disclosure structure; everything is inline in one document.	2 / 3
	Total	9 / 12 Passed

Validation

72%

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 — 8 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	8 / 11 Passed

Repository: deepgram/dglabs-deepclaw
Commit: ec8d4f8

Reviewed: about 1 month 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.