browser-extension-builder

You extend the browser to give users superpowers. You understand the unique constraints of extension development - permissions, security, store policies. You build extensions that people install and actually use daily. You know the difference between a toy and a tool.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/browser-extension-builder/SKILL.md

The canonical home for this skill is browser-extension-builder in sickn33/agentic-awesome-skills

Quality

Content

57%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.

The body delivers solid, mostly executable code examples for the core extension building blocks but reads as a flat reference rather than a guided workflow, lacks validation checkpoints, and inlines everything with no progressive disclosure via reference files.

Suggestions

Drop the duplicated opening paragraph and the obvious one-line captions to tighten token efficiency.

Add a short sequenced build-and-verify workflow with a validation checkpoint (e.g. 'Load unpacked in chrome://extensions, inspect service-worker errors, then test on a target page').

Move the full manifest template and storage API reference into a references/ file and link to it from SKILL.md to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Code blocks are lean, but the opening paragraph duplicates the description verbatim including buzzword padding, and several one-line captions ('Code that runs on web pages', 'Persisting extension data') restate what Claude already knows.	3 / 5
Actionability	It provides mostly copy-paste-ready examples (MV3 manifest template, content script with messaging, chrome.storage get/set, async wrappers, UI injection), with minor gaps such as no popup.js example and 'Extension monetization' listed without any concrete guidance.	4 / 5
Workflow Clarity	Content is organized as reference patterns rather than a sequenced build workflow, and there are no validation checkpoints (e.g. load-unpacked test, manifest validation) for an operation where breakage is explicitly called out in the anti-patterns.	3 / 5
Progressive Disclosure	No bundle files exist, so all content is inline; sections are clearly headed, but reference-style material (full manifest template, storage API limits) that could live in separate files is inlined with no external references to offload it.	3 / 5
	Total	13 / 20 Passed

Description

43%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.

The description establishes a clear niche (browser extension development) but is padded with buzzwords, lacks concrete actions, and entirely omits any 'when to use' trigger guidance. It also uses second-person voice throughout, which the rubric penalizes.

Suggestions

Rewrite in third person and replace fluff ('superpowers', 'toy and a tool') with concrete capabilities, e.g. 'Builds Manifest V3 browser extensions: content scripts, service workers, popups, and chrome.storage.'

Add an explicit 'Use when...' trigger clause naming natural terms users say, e.g. 'Use when the user asks to build, debug, or publish a Chrome/Web extension, or mentions manifest.json, content scripts, or service workers.'

Include natural synonyms and file/keyword triggers ('chrome extension', 'web extension', 'MV3', 'Chrome Web Store') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain (browser extensions) but the only actions are generic ('extend the browser', 'build extensions') padded with buzzwords ('superpowers', 'difference between a toy and a tool'), and the second-person voice ('You extend', 'You build') triggers the -1 voice penalty, dropping it from anchor 2 to 1.	1 / 5
Completeness	It has a clear 'what' (build browser extensions under MV3 constraints) but no 'when'/'Use when' clause or explicit trigger guidance, so completeness is capped at 3.	3 / 5
Trigger Term Quality	It includes some relevant natural terms ('browser extension', 'extension development', 'permissions, security, store policies') but misses common variations and synonyms users actually say ('chrome extension', 'web extension', file types).	3 / 5
Distinctiveness Conflict Risk	'Browser extension' is a clear, narrow niche that is unlikely to trigger for unrelated skills, with only minor overlap risk against general frontend skills.	4 / 5
	Total	11 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/browser-extension-builder/SKILL.md
Commit: 57c135b

Reviewed: 1 day 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.