CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

61%

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

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

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 is a solid, executable reference of MV3 patterns with good templates and genuinely useful non-obvious details (storage limits, MV3 worker termination), but it reads as a pattern catalog rather than a guided workflow, lacks any validation or testing steps, and buries everything in one file with no progressive disclosure. Persona preamble and filler sections cost tokens without instructing anything.

Suggestions

Add a build/test workflow with validation checkpoints, e.g. 'Load unpacked at chrome://extensions -> verify the popup opens and content script injects -> check chrome://extensions errors console', and error-recovery guidance for common MV3 pitfalls.

Split copyable scaffolding (manifest.json template, popup/, content/, background/ starter files) into a references/ or templates/ bundle so SKILL.md stays a lean overview with clearly signaled one-level-deep references.

Cut the persona preamble that repeats the description and the filler 'When to Use' line ('This skill is applicable to execute the workflow or actions described in the overview.'), and trim basic chrome.storage usage Claude already knows in favor of the non-obvious details like storage limits.

DimensionReasoningScore

Conciseness

Mostly lean code templates, but it pads with a persona preamble that repeats the description verbatim, explains basics Claude already knows (chrome.storage.local.get/set), and ends with the filler line 'This skill is applicable to execute the workflow or actions described in the overview.'

3 / 5

Actionability

Provides concrete, copy-paste-ready guidance throughout - a complete MV3 manifest template, project structure, working content-script and storage code - matching the 'mostly executable with minor gaps' anchor; gaps include no sender-side chrome.runtime.sendMessage example and a stub click handler.

4 / 5

Workflow Clarity

Content is organized as a pattern reference with implicit ordering (structure -> manifest -> content scripts -> storage) rather than a sequenced workflow, and validation checkpoints are entirely absent (no 'load unpacked at chrome://extensions and verify' or debugging step), matching the 'sequence present but checkpoints missing' anchor.

3 / 5

Progressive Disclosure

Everything is inlined in a single ~245-line file with no bundle files or external references; templates that would naturally be separate files (manifest.json, popup/options scaffolding) are inline, though section headers keep it navigable - matching the 'some structure but content that should be separate is inline' anchor.

3 / 5

Total

13

/

20

Passed

Description

48%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 names a clear niche (browser extension development) but is written in second person, contains fluff ('give users superpowers', 'the difference between a toy and a tool'), and provides no 'use when' trigger guidance or natural terms users would say like 'Chrome extension' or 'add-on'. It communicates the domain adequately but would not reliably trigger for users needing this skill.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when building Chrome or Firefox extensions, writing a Manifest V3 manifest, or publishing to the Chrome Web Store.'

Rewrite in third person and replace fluff ('give users superpowers', 'toy vs tool') with concrete actions like 'Builds Manifest V3 extensions with content scripts, service workers, and chrome.storage, and publishes them to the Chrome Web Store.'

Include natural trigger terms and synonyms users actually say: 'Chrome extension', 'Firefox add-on', 'Manifest V3', 'content script', 'Web Store'.

DimensionReasoningScore

Specificity

Actions are generic ('You extend the browser', 'You build extensions'), comparable to the anchor-2 example 'Processes PDF files', and the rubric's mandated 1-point penalty for second-person voice ('You extend... You build...') applies, landing it at 2 rather than 3.

2 / 5

Completeness

The 'what' is stated (building browser extensions under permissions/security/store constraints) but there is no 'Use when...' clause or any trigger guidance, so the rubric's cap of 3 for missing 'when' guidance applies.

3 / 5

Trigger Term Quality

Contains relevant keywords ('extension', 'browser', 'permissions', 'store') but misses common user phrasings and synonyms like 'Chrome extension', 'Firefox', 'add-on', 'plugin', or 'Manifest V3', matching the anchor for some relevant keywords with missing variations.

3 / 5

Distinctiveness Conflict Risk

The browser-extension domain is a clear niche with minor overlap risk against general frontend/web-development skills, matching the 'mostly distinct' anchor; it falls short of 5 because it lacks the distinct trigger phrases that would fully separate it.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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/skills/browser-extension-builder/SKILL.md

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.