peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
56
43%
Does it follow best practices?
Impact
77%
1.92xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/peekaboo/SKILL.mdQuality
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 a specific tool (Peekaboo CLI) and platform (macOS) which helps with distinctiveness, but fails to enumerate concrete capabilities and completely lacks a 'Use when...' clause to indicate trigger conditions.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user needs to take screenshots, inspect UI elements, or automate macOS desktop interactions.'
List specific concrete actions the skill enables, such as 'take screenshots, inspect accessibility tree elements, click buttons, read on-screen text, automate GUI workflows.'
Include natural trigger terms users would say, like 'screenshot', 'screen capture', 'UI testing', 'desktop automation', 'accessibility inspector', 'GUI interaction'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'Capture and automate macOS UI' which is vague. It names two broad actions ('capture' and 'automate') but doesn't specify concrete capabilities like taking screenshots, clicking elements, reading screen content, or interacting with specific UI components. | 1 / 3 |
Completeness | The 'what' is only vaguely described ('capture and automate macOS UI'), and there is no 'when' clause at all — no 'Use when...' or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it down to 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'macOS UI', 'Peekaboo CLI', and 'capture'/'automate', but misses natural user terms like 'screenshot', 'screen capture', 'UI automation', 'click', 'accessibility', or 'desktop automation' that users would actually say. | 2 / 3 |
Distinctiveness Conflict Risk | Mentioning 'Peekaboo CLI' and 'macOS UI' provides some distinctiveness since it names a specific tool and platform, but 'capture and automate' is broad enough to overlap with other automation or screenshot-related skills. | 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 skill with excellent actionability through numerous concrete, executable examples covering a wide range of Peekaboo CLI capabilities. Its main weaknesses are the verbose inline feature catalog that could be externalized for better token efficiency, and the lack of explicit validation/error-recovery steps in workflows for what is inherently fragile UI automation.
Suggestions
Move the exhaustive feature/command catalog to a separate REFERENCE.md file and keep only the most essential commands inline, linking to the full list.
Add validation checkpoints and error recovery guidance to the workflow examples (e.g., 'If `peekaboo see` shows no matching elements, try broadening the query or checking permissions').
Include a brief troubleshooting section or error-handling pattern for common failures like missing permissions, stale snapshot IDs, or elements not found.
| 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 referenced externally rather than inline. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | Excellent concrete, copy-paste-ready bash examples covering the most common workflows. Commands include specific flags, arguments, and realistic values. The quickstart and examples sections are fully executable. | 3 / 3 |
Workflow Clarity | The 'See -> click -> type' flow is well-sequenced and represents the most reliable pattern. However, there are no explicit validation checkpoints or error recovery steps (e.g., what to do if permissions fail, if an element ID isn't found, or if a click misses). For UI automation which can be fragile, feedback loops would be valuable. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections (Features, Quickstart, Parameters, Examples), but the full feature catalog is inlined rather than referenced externally. The skill mentions `peekaboo <cmd> --help` and `peekaboo learn` for deeper info, but doesn't use linked reference files for the extensive command listings. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%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
- qsimeon/openclaw-engaging
- Commit
4467e04
- Reviewed
Table of Contents
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.