CtrlK
BlogDocsLog inGet started
Tessl Logo

picture-element

Use when reviewing image assets, markup, and CDN or build transforms related to Use <picture> with an <img> fallback. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

61

Quality

73%

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/picture-element/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, actionable overview with a clean one-level-deep reference and concrete check/fix steps. Its weakest point is redundancy: the Explain and Code Review sections restate material Claude already knows or that the description already covers, and a re-validation loop after fixes is only implicit.

Suggestions

Cut or shrink the 'Explain' section: it repeats the intro's 'renders nothing in browsers that don't support <picture> (IE11)' sentence verbatim and re-explains how <source> selection works, which Claude already knows.

Drop or merge the 'Code Review' section, which restates the description's scope; fold its one unique element (confirming fixes in DevTools) into a final verification step after 'Fix'.

Add an explicit re-check loop to 'Fix' — e.g. 'After applying fixes, re-run the Check list on each corrected <picture>' — to close the batch-review workflow's feedback gap.

DimensionReasoningScore

Conciseness

The body is short and mostly efficient, but the 'Explain' section repeats the intro's sentence verbatim ('A <picture> without an <img> fallback renders nothing in browsers that don't support <picture> (IE11)...') and re-explains how <picture> source selection works — a concept Claude already knows. The 'Code Review' section also largely restates the description. Not a 4 because there are two genuinely redundant sections, not just minor trimming.

3 / 5

Actionability

The 'Check' section enumerates six concrete verifications (img as last child, alt, width/height, source ordering, srcset/media, type attributes) and 'Fix' gives exact remediation with concrete markup like 'add <img src="{fallback-url}" alt="{description}" width="{w}" height="{h}">' and 'type="image/avif"'. Not a 5 because the fix markup uses placeholders rather than a copy-paste-ready example, and no inline code snippet is shown (examples live only in the reference).

4 / 5

Workflow Clarity

Clear Check → Fix → Code Review sequence with enumerated steps ('Scan all <picture> elements... Verify: 1)–6)') and a verification checkpoint ('describe how to confirm the fix in DevTools'). Not a 5 because there is no explicit re-check loop after fixes are applied (fix → re-scan), leaving the batch-review workflow's feedback loop implicit.

4 / 5

Progressive Disclosure

The ~45-line body is well organized into Quick Reference / Check / Fix / Explain / Code Review sections and delegates full implementation detail via a single, clearly signaled one-level reference: 'see `references/rule.md`' — a file that exists in the bundle. No nested references and nothing inlined that belongs in a separate file.

5 / 5

Total

16

/

20

Passed

Description

75%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 a solid, trigger-explicit statement with several concrete review actions and natural frontend keywords. Its main weakness is the awkward embedding of the rule title, which slightly blurs both the 'what' and the scope, and it lacks common synonyms like 'srcset' or 'responsive images'.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'reviewing image assets, markup, and CDN or build transforms' and 'Check encoded size, rendered size, loading strategy, and above-the-fold impact' — which name concrete review targets and checks. Not a 5 because the embedded rule title 'related to Use <picture> with an <img> fallback' muddles the action list, and coverage of what the review entails is partially delegated to that phrase.

4 / 5

Completeness

Both parts are present: an explicit trigger clause ('Use when reviewing image assets, markup, and CDN or build transforms...') and a clear what ('Check encoded size, rendered size, loading strategy, and above-the-fold impact together'). Not a 5 because the 'what' is fragmented across two sentences and the awkward 'related to Use <picture> with an <img> fallback' construction makes the scope less explicit than the anchor's crisp statement.

4 / 5

Trigger Term Quality

Good natural keywords a frontend reviewer would say: 'image assets', 'markup', 'CDN or build transforms', 'loading strategy', 'above-the-fold'. Not a 5 because common variations and synonyms are missing — e.g. 'srcset', 'responsive images', 'WebP/AVIF', or file extensions.

4 / 5

Distinctiveness Conflict Risk

The <picture>/<img> fallback niche is distinct with targeted triggers (image markup, CDN transforms, loading strategy), so conflict risk with unrelated skills is low. Not a 5 because 'reviewing image assets' is broad enough to overlap with sibling image-optimization skills in the same category.

4 / 5

Total

16

/

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.