Capture and automate macOS UI with the Peekaboo CLI.
65
Quality
56%
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 ./openclaw/skills/peekaboo/SKILL.mdQuality
Discovery
32%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 brief and lacks critical components for effective skill selection. While it identifies the tool (Peekaboo CLI) and general domain (macOS UI), it fails to list specific capabilities and completely omits trigger guidance. This would make it difficult for Claude to confidently select this skill from a large pool.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks to take screenshots, automate mouse clicks, inspect UI elements, or work with macOS accessibility features'
Expand specific capabilities beyond 'capture and automate' - list concrete actions like 'take screenshots, click UI elements, read window contents, list running applications'
Include natural user terms like 'screenshot', 'screen capture', 'Mac automation', 'click button', 'window inspection' that users would actually say
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (macOS UI) and mentions two actions ('capture' and 'automate'), but lacks specific concrete actions like 'take screenshots', 'click buttons', 'record workflows', or 'inspect elements'. | 2 / 3 |
Completeness | Provides a brief 'what' (capture and automate macOS UI) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'macOS UI' and 'Peekaboo CLI' as keywords, but misses natural user terms like 'screenshot', 'screen capture', 'UI automation', 'click', 'Mac automation', or 'accessibility'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Peekaboo CLI' and 'macOS UI' provides some distinctiveness, but 'automate' is generic and could overlap with other automation skills; lacks specific file types or unique trigger terms. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality CLI reference skill that excels at conciseness and actionability - it's essentially a dense, executable cheatsheet. The main weaknesses are the lack of validation/error-handling guidance for UI automation workflows (which are inherently fragile) and the monolithic structure that could benefit from splitting advanced topics into separate files.
Suggestions
Add validation steps to workflows, e.g., 'After click, use `peekaboo see` to verify the expected UI state before proceeding'
Include error handling guidance: what to do when `click --on B1` fails to find the element or when permissions are denied
Consider splitting detailed examples (capture, scripting with .peekaboo.json) into separate reference files linked from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient - no explanations of what macOS is or how CLIs work. Every section provides direct, actionable information without padding. The feature list is dense but necessary for discoverability. | 3 / 3 |
Actionability | Fully executable bash commands throughout with real flags and arguments. Examples are copy-paste ready with concrete values (paths, coordinates, app names). No pseudocode or vague descriptions. | 3 / 3 |
Workflow Clarity | The 'See -> click -> type' example shows a clear sequence, but lacks explicit validation checkpoints. For UI automation (which can fail silently), there's no guidance on verifying actions succeeded or handling failures. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (Features, Quickstart, Examples), but everything is in one file. References to `--help` and `learn` command exist, but no links to separate detailed docs for complex features like capture engines or scripting. | 2 / 3 |
Total | 10 / 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 | |
8763418
Table of Contents
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.