CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nex-page-watch

Deploy a production-ready Manifest V3 Chrome extension for visual webpage monitoring and change alerts. Use when: Deploy a fully functional Manifest V3 extension with no build steps required; Implement visual diffing logic using offscreen documents for performance; Fork a proven 'action-on-click' extension architecture for custom tools.

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-page-watch/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 brochure rather than agent guidance: it is repetitive, promotional, contains no executable instructions, and its key reference (assets/extension/) is missing from the bundle. Claude reading this SKILL.md would learn almost nothing about how to actually build or customize the extension.

Suggestions

Remove the redundant FAQ section and the duplicated 'When to use' list — each restates facts already covered elsewhere in the file — and drop the promotional links (nex-ai.be, slopsome.com, paid catalog) that consume tokens without aiding execution.

Add an actionable build workflow: a minimal manifest.json example, the background-alarms and offscreen-diff wiring skeleton in executable code, and concrete steps for testing via chrome://extensions 'Load unpacked', so the agent has something it can actually run and extend.

Resolve the broken core reference: either include the promised assets/extension/ source files in the bundle or replace the 'You receive the complete assets/extension/ source directory' claim with self-contained instructions for generating the extension from scratch.

DimensionReasoningScore

Conciseness

The same facts are repeated three times — the no-build vanilla stack appears in 'Supported architecture', 'When to use', and FAQ #2; offscreen-API performance appears in 'What it does', the features list, and FAQ #5; 'When to use' restates the frontmatter verbatim — plus promotional padding ('Built by Nex AI. More skills... at nex-ai.be and slopsome.com'). This is noticeably verbose with several padded sections (anchor 2); it is not anchor 1 because it does not explain concepts Claude already knows.

2 / 5

Actionability

The body contains no code and no commands for the agent — it names files ('manifest.json', 'background.js', 'diff.js') and one end-user install step ('Open chrome://extensions, enable Developer Mode, and Load unpacked') but otherwise describes what the skill delivers rather than instructing how to do it. Minimal concrete guidance with missing execution steps matches anchor 2; not anchor 1 because a few concrete details (file names, install sequence) are present.

2 / 5

Workflow Clarity

There is no development workflow at all — the only sequence is a rough three-beat install instruction buried in the 'Example' section, with many gaps (nothing on creating the manifest, writing the diff engine, wiring alarms, or testing) and no validation checkpoints. This fits anchor 2's 'rough sequence present but many gaps'; it falls short of anchor 3 because no real step list for the actual task exists.

2 / 5

Progressive Disclosure

The body's central promise — 'You receive the complete assets/extension/ source directory' — references a directory that does not exist, and the body itself concedes 'Scripts, extension source, and templates from the original package are not in this folder'. With the core reference broken/absent and ~20 lines of redundant FAQ inlined, this matches anchor 2; it is not anchor 3 because the references are not merely unclear — they point to nothing.

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 in third-person imperative voice and includes an explicit, multi-clause 'Use when:' trigger section. The main weaknesses are missing natural trigger synonyms ('page monitor', 'price changes') and one overly broad fork-the-architecture trigger that raises overlap risk with general extension-building skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Deploy a production-ready Manifest V3 Chrome extension for visual webpage monitoring and change alerts', 'Implement visual diffing logic using offscreen documents', 'Fork a proven action-on-click extension architecture' — with only minor coverage gaps (e.g., notification and background-scheduling actions are not named). It exceeds the 1-2 concrete actions of anchor 3 but is not the comprehensive coverage of anchor 5.

4 / 5

Completeness

Explicitly answers both parts: the 'what' ('Deploy a production-ready Manifest V3 Chrome extension for visual webpage monitoring and change alerts') and the 'when' via a concrete 'Use when:' clause with three specific trigger scenarios. The 'when' is already explicit and specific, so this fits anchor 5 rather than anchor 4's 'could be more explicit'.

5 / 5

Trigger Term Quality

Includes natural terms a user would say such as 'Chrome extension', 'webpage monitoring', and 'change alerts', giving good keyword coverage. Falls short of anchor 5 because common variations and synonyms are missing (e.g., 'page monitor', 'website change', 'price tracker', 'notify me when a page changes').

4 / 5

Distinctiveness Conflict Risk

The page-monitoring/change-alerts niche is clear and distinct, but the trigger 'Fork a proven action-on-click extension architecture for custom tools' is broad enough to overlap with generic Chrome-extension development skills. Mostly distinct with minor overlap risk matches anchor 4; it lacks the minimal-conflict profile of anchor 5.

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-page-watch/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.