CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

figure-figcaption

Use when reviewing image assets, markup, and CDN or build transforms related to Use <figure> and <figcaption> for image captions. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

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/figure-figcaption/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 presents a well-structured Check/Fix/Explain workflow with concrete numbered steps and a clean one-level pointer to references/rule.md, which genuinely holds the deeper material. Its main weaknesses are the verbatim duplication of the reference's rationale paragraph, an Explain section re-teaching HTML semantics Claude already knows, and the absence of a post-fix validation step.

Suggestions

Drop the duplicated opening paragraph — it appears verbatim in references/rule.md's "Why It Matters"; keep the body's opening to the Quick Reference or a one-line summary.

Trim the "Explain" section's re-teaching of figure/figcaption semantics (Claude already knows these) and keep only the screen-reader consequence specific to this rule.

Add a post-fix validation step to the Fix workflow (e.g., "re-run the Check conditions on each changed image; see the Verification section of references/rule.md for tooling").

DimensionReasoningScore

Conciseness

The opening paragraph ("Using a <p> tag as a caption is invisible to assistive technology...") duplicates references/rule.md's "Why It Matters" section verbatim, and the "Explain" section re-teaches figure/figcaption semantics Claude already knows ("The <figure> element represents self-contained content... that could be moved without affecting the document flow"). These are more than minor over-explanations, so anchor 3 fits better than 4.

3 / 5

Actionability

The Check and Fix sections give concrete numbered steps ("Verify: 1) Such image-caption pairs are wrapped in <figure>... 4) The alt text on the <img> is not identical"; "1) Wrap the <img> and its caption text in a <figure> element"), which is directive and specific. Not 5 because no good/bad markup example appears inline — all code examples are deferred to the reference; not 3 because the guidance is concrete, not pseudocode.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sequence is clear with explicit numbered verification conditions acting as checkpoints. It falls short of 5 because there is no post-fix re-validation step in the body workflow — the reference file's Verification section is never surfaced in the body.

4 / 5

Progressive Disclosure

The body is a concise overview with a clearly signaled, one-level-deep pointer ("For full implementation details, code examples, and framework-specific guidance, see references/rule.md") and the referenced file exists and delivers exactly that. Not 5 because the duplicated "Why It Matters" paragraph blurs the split between overview and reference content.

4 / 5

Total

15

/

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 explicitly covers what and when with a concrete four-part checklist, but the templated, circular "Use when... related to Use <figure> and <figcaption>..." clause muddles the trigger and the size/loading checklist misaligns with the skill's actual focus on semantic caption markup. It is serviceable but reads as boilerplate shared across sibling image rules rather than a tailored description.

Suggestions

Rewrite the when-clause to state the trigger directly (e.g., "Use when reviewing HTML for images with visible captions, or when the user mentions figure, figcaption, image captions, or caption semantics") instead of the circular "related to Use <figure> and <figcaption> for image captions".

Align the checklist with the skill's actual topic — replace the generic "encoded size, rendered size, loading strategy, and above-the-fold impact" checks with caption-specific ones (figure/figcaption structure, alt vs figcaption duplication) to reduce conflict with sibling image-performance skills.

Add natural trigger synonyms users would actually say — "alt text", "caption", "accessibility", "screen reader" — to broaden trigger term coverage.

DimensionReasoningScore

Specificity

"Check encoded size, rendered size, loading strategy, and above-the-fold impact together" lists several concrete actions, matching the anchor for specific actions with minor coverage gaps. It is not 5 because the leading clause "reviewing image assets, markup, and CDN or build transforms related to Use <figure> and <figcaption> for image captions" is garbled and omits actions tied to the skill's actual caption-markup task.

4 / 5

Completeness

Both are explicitly present: the what ("Check encoded size, rendered size, loading strategy, and above-the-fold impact together") and the when ("Use when reviewing image assets, markup, and CDN or build transforms..."). It falls short of 5 because the when-clause is circular ("related to Use <figure> and <figcaption> for image captions") and reads as template text rather than a crisp trigger.

4 / 5

Trigger Term Quality

Natural terms like "image captions", "figure", "figcaption", "image assets", and "markup" give good keyword coverage. A few natural terms users would say are missing ("alt text", "accessibility", "screen reader"), so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The rule-specific phrase "Use <figure> and <figcaption> for image captions" gives real specificity, but the templated "reviewing image assets, markup, and CDN or build transforms" plus the generic size/loading checklist would overlap heavily with sibling image-performance skills — anchor 3 ("could still overlap with similar skills"). Not 4: the overlap is broader than "minor"; not 2: the figcaption phrase prevents generic collision.

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

Path

skills/figure-figcaption/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.