CtrlK
BlogDocsLog inGet started
Tessl Logo

peekaboo

macOS screenshots, UI inspect, clicks, typing, app/window automation.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The body is concise, highly actionable, and well-structured with explicit verification checkpoints in the workflow and clean section organization appropriate for a single-domain skill.

DimensionReasoningScore

Conciseness

The body is lean and operational — binary resolution, app host, safety, commands, and a workflow — with no explanation of concepts Claude already knows (TCC, bridges, screen recording); every token earns its place, matching the 'lean and efficient' anchor.

3 / 3

Actionability

Provides a full executable bash block resolving PB plus concrete copy-paste-ready commands (e.g., 'image --mode screen --screen-index 0 --path /tmp/screen.png --json --no-remote', 'click --coords 100,100 --json') and specific flags, matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

An 8-step numbered workflow includes explicit validation checkpoints (verify the GUI bridge, run 'permissions status --json' and report missing grants, verify output files with 'sips'), and the Safety section guards destructive clicks/typing, matching the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

A single-domain skill with no external bundle files and well-organized sections (Binary, Mac app host, Safety, Common Commands, Workflow) that defers deep reference to 'tools --json' and 'learn' rather than inlining a full command reference; per the simple-skills note this clear, appropriately scoped organization warrants the top anchor.

3 / 3

Total

12

/

12

Passed

Description

67%

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 and well-scoped to macOS GUI automation but is missing an explicit 'Use when...' trigger clause and leans on a slightly unnatural phrase ('UI inspect') rather than broader natural terms.

Suggestions

Add a 'Use when ...' clause naming natural trigger situations (e.g., 'Use when the user needs to take macOS screenshots, inspect or click UI elements, type into apps, or automate windows on a Mac').

Replace or supplement 'UI inspect' with more natural phrasing users would actually say, such as 'inspect UI elements' or 'read on-screen elements'.

Broaden trigger terms to include common variations like 'screenshot', 'screen capture', 'GUI automation', and 'mouse/keyboard automation'.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions — 'macOS screenshots, UI inspect, clicks, typing, app/window automation' — matching the 'lists multiple specific concrete actions' anchor; not level 2 since it goes beyond naming a domain plus a few actions.

3 / 3

Completeness

Clearly states what the skill does but lacks any 'Use when...' trigger clause; per the judging guidelines a missing explicit when-guidance caps completeness at 2 even though the what is well specified.

2 / 3

Trigger Term Quality

Includes some natural user terms ('screenshots', 'clicks', 'typing') but 'UI inspect' is jargony phrasing and common variations like 'screenshot', 'screen capture', 'automate' are missing, matching the 'some relevant keywords but missing common variations' anchor rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

Scoped specifically to 'macOS' GUI automation, a clear niche with distinct triggers unlikely to fire for non-macOS or non-GUI skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
steipete/agent-scripts
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.