CtrlK
BlogDocsLog inGet started
Tessl Logo

browser-extension-control

Create, inspect, install, and safely maintain Chrome extensions for Agent Zero's built-in Browser plugin. Use when the user asks to build a browser extension, modify an existing extension, install a Chrome Web Store extension, or review extension permissions.

75

Quality

92%

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

85%

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

A tight, actionable instruction skill: complete manifest examples, concrete filesystem paths, sequenced workflows with validation gates, and a review checklist. The only slack is minor redundancy with the frontmatter and a few safety sentences that could be trimmed.

Suggestions

Drop or shorten the opening 'Use this skill when...' sentence since the frontmatter description already states the trigger; lead instead with the Operating Model.

Tighten the Safety First intro paragraph to the essential risk statement and let the bullet list carry the guidance.

Add an explicit validate-then-fix-retry loop after 'Validate JSON syntax' (e.g. 'if it fails, fix and re-validate before proceeding') to make the error-recovery feedback loop concrete.

DimensionReasoningScore

Conciseness

Mostly lean and it assumes Chrome/manifest competence, but the opening 'Use this skill when...' line restates the frontmatter trigger and the Safety First intro paragraph could be tightened, so not every token earns its place.

2 / 3

Actionability

Provides concrete paths ('/a0/usr/browser-extensions/<slug>/manifest.json'), two complete copy-paste manifest JSON examples, and explicit Chrome Web Store URL shapes — fully executable guidance.

3 / 3

Workflow Clarity

Create and Install flows are clearly numbered with explicit checkpoints (validate JSON syntax, inspect manifest, enable only after the user accepts risk) plus a Review Checklist, matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

Single, well-organized file with clearly labeled sections and no nested references; no content here needs splitting into separate bundle files, so the structure navigates cleanly.

3 / 3

Total

11

/

12

Passed

Description

100%

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 well-crafted description: third-person voice, concrete capabilities, an explicit Use-when trigger with natural phrasing, and a tightly scoped niche. It hits the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists four concrete actions — 'Create, inspect, install, and safely maintain Chrome extensions' — matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.

3 / 3

Completeness

Explicitly answers both what ('Create, inspect, install, and safely maintain...') and when ('Use when the user asks to build...'), satisfying the 3 anchor and avoiding the cap for a missing 'Use when' clause.

3 / 3

Trigger Term Quality

'build a browser extension, modify an existing extension, install a Chrome Web Store extension, or review extension permissions' are natural phrases a user would say, with good variation; not jargon-only like the 1 anchor.

3 / 3

Distinctiveness Conflict Risk

Scoped to 'Chrome extensions for Agent Zero's built-in Browser plugin' — a clear niche with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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
agent0ai/agent-zero
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.