CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

html

Create interactive calculators, configurators, dashboards, widgets, and prototypes as self-contained HTML artifacts.

62

Quality

78%

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 ./docker/sandbox/skills/html/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 lean, highly actionable single-file skill with an exemplary verify-fix-reverify feedback loop that even bounds regeneration to avoid looping. Its main flaws are redundant bullets across the two requirements sections and a few unconcretized placeholders in the save/verify examples.

DimensionReasoningScore

Conciseness

The body is composed of terse, viewer-specific imperatives Claude would not know on its own ('Do not call fetch, XMLHttpRequest, WebSocket', 'Images must be data: URIs'), but the 'Authoring contract' and 'Web design requirements' sections duplicate each other — responsive layout/no horizontal overflow, prefers-reduced-motion, accessible labels, and native controls each appear twice. It sits above the 'mostly efficient' anchor but the repeated bullets keep it from 'every token earns its place'.

4 / 5

Actionability

Guidance is concrete and executable — exact tool invocations with kwargs ('Call verify_artifact(path=output_path, format="html")', 'save_artifact(path=output_path, title="...", markdown_representation="...")', 'load_artifact_for_revision'), named prohibited APIs, and explicit allowed hosts (fonts.googleapis.com, fonts.gstatic.com). Minor gaps remain: placeholders like title="..." are never concretized and no example fragment or markdown_representation sample is shown, so it falls short of fully copy-paste ready.

4 / 5

Workflow Clarity

The verify-and-save flow has an explicit validation step and a bounded feedback loop: 'fix all blockers together, regenerate once at the same output path, and reverify. If a blocker remains, stop and explain it instead of looping', followed by a sequenced save call. This matches the anchor for clear sequencing with explicit validation and error-recovery loops; no validation gaps are visible.

5 / 5

Progressive Disclosure

No bundle files exist and the four sections are well-organized with nothing that clearly belongs in a separate file, but at ~59 body lines it exceeds the under-50-line simple-skill exception, and the overlapping content between 'Authoring contract' and 'Web design requirements' is a minor organization gap. Good structure overall — fits the 'most content appropriately placed, minor gaps' anchor rather than the clean-split anchor.

4 / 5

Total

17

/

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.

A specific, third-person description with strong natural trigger nouns and a distinct niche, but it omits any explicit 'when to use' guidance, which caps its completeness and slightly limits trigger coverage. Adding a 'Use when...' clause would resolve the main weakness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a calculator, configurator, dashboard, widget, prototype, or single-file interactive web page.'

Include common synonyms and file extensions users say naturally, such as '.html', 'web app', or 'single-file web page', to broaden trigger-term coverage.

Mention the revision capability (editing an existing artifact via load_artifact_for_revision) so the 'what' covers the full scope the body documents.

DimensionReasoningScore

Specificity

The description enumerates five concrete artifact types ('interactive calculators, configurators, dashboards, widgets, and prototypes') plus a concrete format constraint ('self-contained HTML artifacts'), which is several specific capabilities with only a minor gap — the single verb 'Create' omits the revise/edit workflow the body documents. It names far more than 1-2 actions (anchor 3) but is not comprehensive (anchor 5).

4 / 5

Completeness

The 'what' is clear (create self-contained interactive HTML artifacts of the listed kinds), but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. The 'when' is only weakly implied by the artifact-type nouns.

3 / 5

Trigger Term Quality

Natural user terms are well covered — 'calculators', 'dashboards', 'widgets', 'prototypes', 'configurators', 'HTML' are all phrases users would plausibly say. A few natural variants are missing (e.g., 'web app', 'web page', 'single-file', '.html'), so it fits 'good keyword coverage; a few natural terms missing' rather than comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

'Self-contained HTML artifacts' combined with the specific artifact types carves a mostly distinct niche with minor overlap risk against generic frontend/web-development or visualization skills. It is more distinct than the 'could still overlap with similar skills' anchor but lacks the explicit distinct triggers of the top anchor.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

MODSetter/SurfSense

Path

docker/sandbox/skills/html/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.