CtrlK
BlogDocsLog inGet started
Tessl Logo

web-browser

Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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 clean, executable tool-collection skill: command-first sections, a concrete quick-start flow, and real bundle files backing every reference. Main improvements would be trimming the dense start section and adding a top-level script index plus light validation cues.

Suggestions

Tighten the start section's headless/headed and profile paragraph into a short bullet list to trim tokens.

Add a brief top-level overview or table enumerating all available scripts so the full toolset is discoverable at a glance.

Insert light validation cues in the quick-start flow (e.g., confirm navigation succeeded before emulating or screenshotting).

DimensionReasoningScore

Conciseness

Lean, command-first body with no re-explained concepts, but the dense start-section paragraph on headless/headed and profile behavior plus a few trimmable asides ('best to use single quotes') keep it just shy of fully lean.

4 / 5

Actionability

Every section is copy-paste-ready executable commands with flags and real env overrides (BROWSER_BIN, BROWSER_DEBUG_PORT), covering the common cases for each tool.

5 / 5

Workflow Clarity

A clear 6-step 'Quick Mobile Debug Flow' sequence is provided; operations are non-destructive so the validation cap does not apply, but no explicit validate/verify checkpoints are given after navigation or evaluation.

4 / 5

Progressive Disclosure

Well-organized per-script sections with all referenced scripts resolving to real bundle files at one level; minor gap is the absence of a top-level overview signpost enumerating the full script set.

4 / 5

Total

17

/

20

Passed

Description

92%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 names concrete actions, includes a natural 'Use when' trigger, and carves out a distinct niche with low conflict risk. Only minor gap is missing common web-automation/scraping synonyms.

DimensionReasoningScore

Specificity

Names the domain (web pages/Chrome/CDP) and lists six concrete actions — 'navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers 'what' (the CDP action list) and 'when' ('Use when an agent needs a real browser') with a concrete trigger phrase, matching the anchor for clearly answering both.

5 / 5

Trigger Term Quality

Strong natural-term coverage ('web pages', 'Chrome', 'navigate', 'fill forms', 'screenshots', 'Use when an agent needs a real browser') with a natural trigger clause, but broader automation/scraping synonyms users commonly say are not surfaced.

4 / 5

Distinctiveness Conflict Risk

Clear niche — real browser automation via CDP — with distinct triggers ('real browser', 'headless Chrome', 'console/network debugging') and minimal overlap with HTTP-fetch or scraping skills.

5 / 5

Total

19

/

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
mitsuhiko/agent-stuff
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.