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 a broad domain (macOS UI capture/automation) but fails to enumerate specific capabilities or provide any trigger guidance for when this skill should be selected. Users searching for screenshot, UI testing, or accessibility-related tasks may not match to this skill.

Suggestions

Add a 'Use when...' clause with explicit trigger conditions, e.g., 'Use when the user needs to take screenshots, interact with macOS UI elements, automate clicks, or inspect accessibility trees on macOS.'

List specific concrete actions the skill enables, such as 'take screenshots, click UI elements, read accessibility data, automate GUI workflows, inspect window hierarchies.'

Include natural user terms like 'screenshot', 'screen capture', 'UI testing', 'GUI automation', 'accessibility tree', 'window inspection' 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	It partially addresses 'what' (capture and automate macOS UI) but is vague about it, and completely lacks a 'when' clause. There's no 'Use when...' guidance or explicit trigger conditions, which per the rubric should cap completeness at 2, and the weak 'what' brings it to 1.	1 / 3
Trigger Term Quality	Includes 'macOS UI', 'Peekaboo', and 'CLI' which are somewhat relevant keywords. However, it's missing natural user terms like 'screenshot', 'screen capture', 'click button', 'UI automation', 'accessibility', or 'GUI testing' that users would actually say.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Peekaboo CLI' and 'macOS UI' provides some distinctiveness, but 'automate macOS UI' could overlap with other automation or macOS-related skills. The tool name 'Peekaboo' helps differentiate it somewhat.	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, actionable skill with excellent concrete examples covering the breadth of Peekaboo's CLI capabilities. Its main weaknesses are the lack of validation/error-recovery steps in workflows and the monolithic structure that packs a full command catalog plus extensive examples into a single file. Trimming the feature list and splitting detailed examples into a separate reference would improve both conciseness and progressive disclosure.

Suggestions

Add validation checkpoints and error recovery guidance to workflows (e.g., 'If `peekaboo see` returns no annotated elements, check permissions with `peekaboo permissions` and verify the target app/window is visible').

Move the exhaustive command catalog (Core/Interaction/System/Vision) to a separate REFERENCE.md and keep only the most essential commands in SKILL.md.

Split the extensive examples section into an EXAMPLES.md file, keeping only the quickstart and the 'see -> click -> type' flow inline as the primary workflow demonstration.

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 redundancy exists between the feature list and the examples.	2 / 3
Actionability	The skill provides numerous concrete, copy-paste-ready bash commands covering a wide range of use cases. The examples are executable with real flags and arguments, and the common parameters sections give specific flag names and values.	3 / 3
Workflow Clarity	The 'See -> click -> type' flow demonstrates a clear multi-step sequence, and the quickstart provides a logical progression. However, there are no explicit validation checkpoints or error recovery steps — e.g., no guidance on what to do if permissions fail, if `see` returns no elements, or if a click misses its target.	2 / 3
Progressive Disclosure	The content is reasonably well-structured with clear section headers, but it's a monolithic file with no references to external files. The extensive command catalog and numerous examples could benefit from being split into a reference file and an examples file, with the SKILL.md serving as a concise overview.	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 8 hours 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.