CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nex-trust-check

Deploy or fork a production-ready Chrome extension for AI text detection and fake review analysis. Use when: Ship a complete AI-text detection extension to the Chrome Web Store; Create a custom content-rewriter extension using a proven MV3 scaffold; Add fake-review detection features to an existing browser tool.

Quality

62%

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 ./skills/nex-trust-check/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

25%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 reads as a product landing page rather than an operational skill: marketing prose, a sales FAQ, and claims of "complete high-fidelity source code" that is explicitly not included in the folder, with dangling references to assets/extension/, analyzer.js, and sites.js. There is no executable code, no sequenced workflow with validation, and no actual developer loop or submission checklist despite both being promised. Almost all instructional value is absent from the shipped bundle.

Suggestions

Ship the actual extension source in assets/extension/ (manifest.json, analyzer.js, sites.js, background worker, side-panel UI) or remove all references to files that are not in the bundle — the current dangling references make the skill's core promise unexecutable.

Replace the marketing sections ("Why use this skill", "What you get") and the purchase-oriented FAQ with a numbered workflow: load unpacked via chrome://extensions, test on a sample review page, verify the side-panel trust score output, then follow a concrete Chrome Web Store submission checklist.

Cut the duplicated promotional footers and restated "When to use" triggers; the ~85-line body can be reduced to a lean overview plus the install/customize/publish steps, cutting token cost by more than half.

DimensionReasoningScore

Conciseness

Multiple padded, non-instructional sections: "Why use this skill" ("bypasses the 'blank page' problem"), a five-question FAQ that restates earlier sections (Q1 repeats "What it does"), purchase-oriented filler ("Buyers receive the current stable version", "after purchase"), and promo links repeated in "What you get" and the footer. This is noticeably verbose with several sections that earn no tokens; it avoids a 1 only because it does not extensively teach concepts Claude already knows.

2 / 5

Actionability

The body's central promise — "I've generated the complete Manifest V3 source in `assets/extension/`" — points at files that do not exist in this bundle (the body itself admits "Scripts, extension source, and templates from the original package are not in this folder"), so the primary task cannot be executed. The only concrete procedure is the prose FAQ instruction to "navigate to chrome://extensions... enable 'Developer mode,' and click 'Load unpacked'"; the rest is descriptive marketing. That is minimal concrete guidance with missing execution steps, not the incomplete-but-present guidance of a 3.

2 / 5

Workflow Clarity

A rough sequence (download source → load unpacked → customize → submit to Web Store) exists but is scattered across marketing prose and FAQ answers rather than presented as steps. There are no validation checkpoints, and the promised "developer loop for rapid iteration and a checklist for Chrome Web Store submission" are mentioned but never actually provided. This matches a rough sequence with many gaps and absent validation.

2 / 5

Progressive Disclosure

The bundle contains no references/, scripts/, or assets/ directories, yet the body directs the reader to `assets/extension/`, `analyzer.js`, and `sites.js` — dangling references to files that are not shipped. Section headers give the document minimal structure (so it is not a monolithic wall), but the core content that clearly belongs in bundle files is simply missing, making the file layout ineffective.

2 / 5

Total

8

/

20

Passed

Description

83%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 description: it states concrete capabilities, includes an explicit multi-scenario "Use when" clause with natural trigger phrases, and occupies a fairly distinct niche. Its only weaknesses are unenumerated runtime capabilities and a trigger ("custom content-rewriter extension") broad enough to overlap with generic MV3 scaffold skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Deploy or fork a production-ready Chrome extension", "Ship a complete AI-text detection extension to the Chrome Web Store", "Create a custom content-rewriter extension using a proven MV3 scaffold", "Add fake-review detection features to an existing browser tool" — but never enumerates the extension's runtime capabilities (heuristic analysis, trust score, side panel), leaving minor gaps in coverage. Not 5 because coverage stops at deploy/customize/extend verbs without the analysis features the skill actually delivers.

4 / 5

Completeness

Clearly answers both: the "what" ("Deploy or fork a production-ready Chrome extension for AI text detection and fake review analysis") and an explicit "Use when:" clause with three concrete trigger scenarios. This mirrors the anchor-5 example structure of a clear capability statement followed by explicit trigger phrases, and uses third-person imperative voice throughout.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "Chrome extension", "AI text detection", "fake review", "Chrome Web Store", "content-rewriter", "browser tool" are phrases users would plausibly say. Missing common synonyms and variations such as "AI-generated text", "GPT-written", "review authenticity", or "Manifest V3", so it falls short of the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The AI-text-detection / fake-review niche is distinct with low conflict risk for those triggers. However, "Create a custom content-rewriter extension using a proven MV3 scaffold" overlaps with generic Chrome extension boilerplate skills, so it is mostly distinct with minor overlap risk rather than a clear exclusive niche.

4 / 5

Total

17

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

NexaiGuy/nex-ai-skills

Path

skills/nex-trust-check/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.