CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-automation

Local OpenWork Electron browser automation with CDP. Use when driving a local Electron dev app, browser_list, browser_snapshot, browser_eval, composer automation, or local UI smoke tests.

70

Quality

85%

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

82%Weight 40%Scale 1-5

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

A tight, highly actionable skill body with concrete commands and a copy-paste-ready automation snippet, clear sequencing, and good organization. Main improvement would be adding an explicit verify-and-retry feedback loop and optionally extracting the longer JS snippet into a script file.

Suggestions

Add an explicit error-recovery feedback loop to the Browser Tool Flow (e.g., 'if the Run task button is disabled or the response is not confirmed, re-check the editor state and retry') to raise workflow_clarity.

Consider moving the ~22-line 'Send A Session' browser_eval snippet into a scripts/ file referenced from the body, which would tighten conciseness and improve progressive_disclosure for the longer inline code.

Trim the 'What I Do' summary or fold it into the 'Browser Tool Flow' to remove the minor redundancy and push conciseness toward 5.

DimensionReasoningScore

Conciseness

Lean and assumes competence (no explanations of CDP/Electron basics), with concrete env vars, URLs, and commands; minor redundancy between the 'What I Do' summary and the 'Browser Tool Flow' section keeps it just below 5.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: 'pnpm dev' launch commands, 'nohup' background launch, 'lsof -nP -iTCP:9823' readiness check, and a complete 'browser_eval' JS snippet with specific selectors covering the common case.

5 / 5

Workflow Clarity

The 'Browser Tool Flow' is a clear 6-step sequence with a confirm/verify step (step 6) and a readiness checkpoint ('lsof'), and the operation is not destructive/batch so no cap applies; falls short of 5 because there is no explicit error-recovery feedback loop.

4 / 5

Progressive Disclosure

Well-organized into clear sections (What I Do, Local Dev Setup, Background Launch, Browser Tool Flow, Send A Session, Notes) with no nested references and no external bundle files needed; the inline ~22-line JS snippet is somewhat substantial for a single file, keeping it at 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both what the skill does and when to use it, with concrete trigger phrases and low conflict risk. Minor room to improve by converting tool-name triggers into more natural user phrasing.

DimensionReasoningScore

Specificity

Names the domain ('Local OpenWork Electron browser automation with CDP') and lists several concrete actions/tools ('browser_list, browser_snapshot, browser_eval, composer automation, or local UI smoke tests'); falls short of 5 because the actions are tool names rather than fully elaborated capabilities.

4 / 5

Completeness

Clearly answers 'what' ('Local OpenWork Electron browser automation with CDP') and explicitly answers 'when' via a concrete 'Use when driving a local Electron dev app, browser_list, browser_snapshot, browser_eval, composer automation, or local UI smoke tests' clause.

5 / 5

Trigger Term Quality

Good natural coverage for the niche ('browser automation', 'CDP', 'Electron dev app', 'composer automation', 'UI smoke tests') with a few natural synonyms missing; the tool-name terms (browser_list, etc.) are less like phrases a user would naturally say, keeping it at 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

Highly specific niche (OpenWork Electron app, CDP, composer automation) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

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
different-ai/openwork
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.