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.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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 well-structured, actionable skill body with concrete manifest starters, specific paths, and built-in safety validation. Adding an explicit validate→fix→retry loop and splitting the manifest templates into a reference file would lift the weakest dimensions.

Suggestions

Add an explicit feedback loop after manifest validation: if JSON/manifest_version checks fail, state that Claude should fix the manifest and re-validate before continuing.

Make the CRX install step concrete by specifying the exact Chrome update-service URL pattern and the extraction command rather than 'extract the ZIP payload safely'.

Consider moving the two full manifest JSON starters into a references/ file and linking to it, so the main body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what extensions or manifests are), with only minor verbosity in the Safety First section that could be tightened, fitting anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	Copy-paste-ready manifest JSON starters and concrete paths like "/a0/usr/browser-extensions/<slug>/" give mostly executable guidance, but the CRX step "extract the ZIP payload safely" is hand-wavy, leaving a minor gap below anchor 5.	4 / 5
Workflow Clarity	Numbered Create (1-7) and Install (1-6) sequences include validation checkpoints (step 5 JSON validation, the Review Checklist), but there is no explicit validate→fix→retry feedback loop for malformed manifests, which keeps it below anchor 5.	4 / 5
Progressive Disclosure	A single self-contained file with well-organized sections (Operating Model, Safety, Create, Install, Review Checklist) and no nested references; at over 50 lines with two inlined manifest examples that could be split, it sits at anchor 4 rather than the simple-skill anchor 5.	4 / 5
	Total	16 / 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, third-person description that answers both what and when with concrete trigger phrases and a clearly distinct niche. Minor gains are possible by adding file-extension triggers and making "safely maintain" more concrete.

Dimension	Reasoning	Score
Specificity	"Create, inspect, install, and safely maintain Chrome extensions" lists four concrete actions, but "safely maintain" is slightly generic compared to fully concrete verbs, leaving minor gaps below the comprehensive anchor 5.	4 / 5
Completeness	It explicitly states what the skill does ("Create, inspect, install, and safely maintain Chrome extensions") and gives a concrete "Use when..." clause enumerating trigger scenarios, matching the anchor-5 example.	5 / 5
Trigger Term Quality	"build a browser extension", "install a Chrome Web Store extension", and "review extension permissions" are natural user phrases with good coverage, but synonyms and file extensions (.crx, manifest.json) are absent, stopping short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Scoping to "Agent Zero's built-in Browser plugin" with specific trigger phrases carves a clear niche with minimal overlap against generic extension or browser skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agent0ai/agent-zero
Path: plugins/_browser/skills/browser-extension-control/SKILL.md
Commit: b22a144

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.