CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

blocked-links

Use when reviewing HTML source and JavaScript for links or resource URLs pointing to domains listed in common adblocker filter lists.

Quality

74%

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/blocked-links/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured overview with excellent progressive disclosure to a real, one-level reference, and the Check/Fix guidance is concrete and testable. Its main weakness is filler: the Explain and Code Review sections add boilerplate rather than skill-specific value.

Suggestions

Cut or merge the 'Explain' section — it re-describes reference content as meta-instruction and adds no unique guidance.

Replace the generic 'Code Review' boilerplate with rule-specific review points (e.g., which headers/anchor patterns to inspect for tracking redirects).

Pull the uBlock Origin DevTools verification steps from references/rule.md into a one-line inline checklist in the Check section to make the validation loop self-contained.

DimensionReasoningScore

Conciseness

The Quick Reference, Check, and Fix sections are dense and useful, but the 'Explain' section restates content already in references/rule.md as meta-instruction, and the 'Code Review' section is generic boilerplate ('Review server config, headers, forms, and integration points related to Blocked Tracking Links') that could apply to any rule — matching 'Mostly efficient but includes some unnecessary explanation or could be tightened'. Not a 4 because the boilerplate sections are noticeable rather than minor, and not a 2 because the body avoids explaining concepts Claude already knows and stays compact.

3 / 5

Actionability

The Check section is concretely executable ('Identify external script sources, image src URLs, iframe src URLs, and anchor href values... (googletagmanager.com, hotjar.com, facebook.net, doubleclick.net, etc.). Test whether these resources load successfully with uBlock Origin enabled.'), and Fix gives specific remedies (self-host, reverse proxy, direct destination URLs with UTM parameters), with copy-paste code properly deferred to references/rule.md — matching 'Mostly executable guidance; concrete code or commands with minor gaps'. Not a 5 because the body itself contains no executable example, relying on the reference for code.

4 / 5

Workflow Clarity

The Check → Fix sequence is clear and Check embeds an explicit validation step ('Test whether these resources load successfully with uBlock Origin enabled'), expanded by the Verification section in references/rule.md (DevTools Network tab, filter by 'Blocked'), matching 'Clear sequence with most checkpoints present; minor validation gaps'. Not a 5 because the sections are unordered headings rather than an explicit sequence, and the body's own validation guidance is a single sentence deferred to the reference; not a 3 because validation is present and named, not implicit.

4 / 5

Progressive Disclosure

The ~45-line body is a genuine overview (summary bullets, check/fix guidance) with one clearly signaled, one-level-deep reference — 'For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`' — and the file exists in the bundle with exactly that content, matching 'Clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation'. The anti-drift check against anchor 4 shows only trivial summary overlap between body and reference, not misplaced content.

5 / 5

Total

16

/

20

Passed

Description

66%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 is explicit, honest, and highly distinct with a proper 'Use when' trigger, but it under-sells the skill: only one action (reviewing) is stated and the most natural user vocabulary (tracking, blocked, analytics) is missing, which weakens both specificity and trigger recall.

Suggestions

Add the natural synonyms users actually say — e.g., 'tracking domains', 'blocked links/scripts', 'analytics blocked by adblockers' — to improve trigger recall.

State 1-2 more concrete actions beyond reviewing (e.g., 'identify affected URLs and fix them by self-hosting or direct-linking') to raise specificity.

Keep the third-person 'Use when...' structure; it is already correct.

DimensionReasoningScore

Specificity

The description names the domain ("reviewing HTML source and JavaScript for links or resource URLs") and one concrete action — reviewing — but offers no further actions (e.g., detect, flag, fix, self-host), matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It is not a 4 because it does not list several specific actions, and not a 2 because the reviewed artifacts and matching criteria are concrete, not generic.

3 / 5

Completeness

An explicit 'Use when...' clause supplies the trigger ("Use when reviewing HTML source and JavaScript for links or resource URLs pointing to domains listed in common adblocker filter lists"), and the what (reviewing for such links/URLs) is embedded in the same clause — both present, matching 'Has both what and when; when could be more explicit or specific'. It is not a 5 because the what is only the review action itself and lacks concrete companion actions, and not a 3 because the when clause is explicit, not merely implied.

4 / 5

Trigger Term Quality

Relevant keywords are present ("adblocker filter lists", "links", "resource URLs", "domains", "HTML", "JavaScript"), but the most natural user phrasages for this task — "tracking domains", "blocked links", "analytics scripts blocked" — are absent, matching 'Some relevant keywords but missing common variations or synonyms'. It misses a 4 because those missing synonyms are central to how users would describe the need, not peripheral.

3 / 5

Distinctiveness Conflict Risk

The niche is precise — HTML/JavaScript links and resource URLs matching adblocker filter-list domains — which no other plausible skill description would claim, matching 'Clear niche with distinct triggers; minimal conflict risk'. The anti-drift check against anchor 4 finds no meaningful overlap with a broader class of similar skills.

5 / 5

Total

15

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/blocked-links/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.