CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

compression

Use when auditing slow page loads, heavy assets, or rendering delays related to Enable text-based compression. Verify the actual bottleneck in DevTools, Lighthouse, or field data before recommending changes.

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/compression/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.

A well-structured, token-efficient overview with excellent progressive disclosure to a real, one-level-deep reference file. The main weakness is actionability: the Fix section stays at the hint level while all executable configuration lives in the reference, and a couple of known-concept sentences could be trimmed.

Suggestions

Inline one minimal executable fix (e.g. a 3-line nginx gzip block or the Node `compression` middleware snippet) in the Fix section so the body is actionable without opening the reference.

Trim the intro paragraph's explanation of why compression helps (known to Claude) and drop the redundant Quick Reference bullet that repeats it.

Move the verify-first checkpoint from the description into the body's Check section (e.g. 'Confirm compression is the actual bottleneck via DevTools/Lighthouse before recommending changes') to close the workflow-clarity gap.

DimensionReasoningScore

Conciseness

The body is efficient with clear sections, but the intro sentence "Compressed assets download faster, reducing the time to first paint and improving the overall perceived performance" explains a concept Claude already knows and partially duplicates the Quick Reference bullet "Significantly reduces data transfer size and load times" — anchor 4 (efficient, minor over-explanation to trim), not anchor 3 since padding is limited to a couple of sentences.

4 / 5

Actionability

The Check section is concrete ("served with `Content-Encoding: gzip` or `br` headers"), but the Fix section is a high-level hint ("Enable Gzip or Brotli compression in your web server (Nginx, Apache) or CDN settings") with no inline commands or config — the executable nginx/express steps exist only in references/rule.md — matching anchor 3 (some concrete guidance but incomplete in the body).

3 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review ordering gives an unambiguous verify-first sequence for a simple, non-destructive skill, with the Check section acting as the checkpoint before changes are recommended — anchor 4 rather than 5 because the body omits a confirm-the-bottleneck loop (it lives only in the description).

4 / 5

Progressive Disclosure

The body is a clear ~35-line overview organized into labeled sections, with one well-signaled one-level-deep reference ("For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`") that exists and matches its description — matching anchor 5 exactly.

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 has a clear, explicit trigger clause and a sensible verify-first what, but it describes only the auditing step and leaves the skill's actual remediation unnamed. Trigger keywords are good but miss the most obvious synonyms (compression, gzip, brotli, page speed).

Suggestions

State the skill's core action alongside the audit step, e.g. 'Enable Gzip or Brotli compression in Nginx, Apache, or CDN configuration' so the 'what' is comprehensive.

Add missing natural trigger terms such as 'compression', 'gzip', 'brotli', 'minify', or 'page speed' so users searching those words match this skill.

Reword 'related to Enable text-based compression' (an imperative rule title embedded in prose) into a natural noun phrase like 'text-based compression' to sharpen distinctiveness against sibling performance skills.

DimensionReasoningScore

Specificity

The description names the domain ("Enable text-based compression") and one concrete action ("Verify the actual bottleneck in DevTools, Lighthouse, or field data"), but the remediation work the skill actually performs is never stated, matching anchor 3 (1-2 concrete actions, not comprehensive) rather than anchor 4's 'several specific actions'.

3 / 5

Completeness

Both parts are present: an explicit "Use when auditing slow page loads..." trigger and a what ("Verify the actual bottleneck... before recommending changes"). It falls short of anchor 5 because the 'what' covers only the audit step and never states the skill's core action (enabling/configuring compression).

4 / 5

Trigger Term Quality

"slow page loads, heavy assets, or rendering delays" are natural phrases users would say, giving good keyword coverage, but common variations like "compression", "gzip", "brotli", and "page speed" are missing — anchor 4, not anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The symptom triggers ("slow page loads, heavy assets, or rendering delays") are broad and would also match image-optimization or lazy-loading skills; the scope qualifier "related to Enable text-based compression" narrows it but is awkwardly phrased — anchor 3 (somewhat specific but overlap risk remains).

3 / 5

Total

14

/

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/compression/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.