CtrlK
BlogDocsLog inGet started
Tessl Logo

cdn

Use when auditing slow page loads, heavy assets, or rendering delays related to Use a content delivery network. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

50

Quality

55%

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/cdn/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

40%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 has a sensible section structure and a well-signaled pointer to a real references/rule.md containing the executable detail, but the body itself is padding-heavy (the CDN concept is explained three times) and its Check/Fix/Explain/Code Review steps are one-line abstractions with no commands, code, or validation steps. Most of the actual instructional value lives entirely in the reference file.

Suggestions

Replace the vague Check step with concrete verification, e.g. "Open DevTools Network panel and confirm asset Host/`Cache-Control` headers; assets should return `X-Cache: HIT` from an edge domain, and Lighthouse's 'Serve static assets with an efficient cache policy' audit should pass."

Replace the vague Fix step with the executable config from references/rule.md (the Next.js images/headers example) or a minimal generic CDN setup snippet, plus a re-verify step after configuration.

Delete the redundant Explain section and the duplicate Quick Reference bullet — the intro paragraph already states the concept, and Claude knows what a CDN is; the saved tokens can carry the concrete check/fix steps instead.

DimensionReasoningScore

Conciseness

The body is short, but the same concept is stated three times — the intro ("A CDN serves static assets from geographically distributed servers—users download from the nearest location..."), Quick Reference bullet 1 ("CDNs serve content from edge servers closest to users"), and the Explain section ("Explain how CDNs reduce latency by serving content from geographically distributed servers."), which restates a concept Claude already knows. It is mostly efficient with removable padding, above anchor 2 but not the lean anchor 5.

3 / 5

Actionability

The Check ("Check if static assets are served from a CDN and if the CDN is properly configured"), Fix ("Configure a CDN to serve static assets with proper caching headers and geographic distribution"), and Code Review sections are all abstract directions with no commands, code, or concrete steps — only a named list of providers ("Cloudflare, Vercel, AWS CloudFront, Fastly") and a pointer to references/rule.md. It is above anchor 1 (it does name concrete providers and what to inspect) but sits well below the executable-code anchors.

2 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections give a rough sequence, but each step is a single vague sentence with no detail on how to perform it, no measurement commands (despite the description promising DevTools/Lighthouse verification), and no validation checkpoint such as confirming cache headers after configuring. This matches anchor 2's 'rough sequence present but many gaps; steps poorly defined' rather than anchor 3's listed-steps-with-implicit-checkpoints.

2 / 5

Progressive Disclosure

The body acts as a short overview with a clearly signaled one-level-deep reference — "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — and that file exists with the promised content (Next.js config example, caching headers). It misses anchor 5 because the body duplicates rule.md's intro text and Quick Reference claims instead of cleanly splitting overview vs. detail.

4 / 5

Total

11

/

20

Passed

Description

71%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 has a strong, explicit trigger structure with concrete verification actions and named tooling, but the auto-templated insertion "related to Use a content delivery network" reads awkwardly and weakens both the what-clause and the description's distinctiveness from other performance rules. Natural trigger terms are good but omit the most obvious keyword ("CDN").

Suggestions

Rewrite the what-clause so the rule name reads naturally, e.g. "Use when auditing slow page loads, heavy assets, or rendering delays that may be caused by missing or misconfigured CDN delivery of static assets."

Include the keyword "CDN" / "content delivery network" as an explicit trigger term so users and Claude can match the skill by its actual subject.

Narrow the trigger to CDN-specific symptoms (e.g. "slow global load times", "assets served from origin") to reduce conflict with sibling performance skills like image optimization or lazy loading.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "auditing slow page loads, heavy assets, or rendering delays", "Verify the actual bottleneck in DevTools, Lighthouse, or field data", "before recommending changes" — with named tools. It falls short of a 5 because "recommending changes" is generic and coverage of what the audit covers beyond verification is thin.

4 / 5

Completeness

Both parts are present: an explicit "Use when auditing slow page loads, heavy assets, or rendering delays..." trigger clause, and a what ("Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes"). It does not match anchor 5 because the what is garbled by the templated phrase "related to Use a content delivery network", which obscures the actual capability (CDN audit/configuration guidance).

4 / 5

Trigger Term Quality

Natural user phrases like "slow page loads", "heavy assets", "rendering delays", "DevTools", and "Lighthouse" are present and would be said by users with this problem. A few natural terms are missing ("CDN" itself never appears as a keyword, nor "latency", "slow site", "network waterfall"), so it does not reach anchor 5; it is clearly above the 'some relevant keywords' anchor 3.

4 / 5

Distinctiveness Conflict Risk

The trigger terms ("slow page loads", "heavy assets", "rendering delays") are generic performance complaints that would equally match sibling performance skills (image optimization, lazy loading, bundling), and the only CDN-specific tie is the awkwardly inserted rule title. It is more specific than anchor 2's broad overlap but does not achieve anchor 4's 'minor overlap risk with closely related skills'.

3 / 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
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.