CtrlK
BlogDocsLog inGet started
Tessl Logo

html-to-interaction-prompts

Convert a supplied HTML page or generated HTML reference into a screenshot-backed article containing multiple reusable interaction prompts. Use when the user provides an HTML file, exported page, generated-page.html, or local/live reference and asks to extract animation/interactions, create prompts, capture screenshots for each prompt, add them to an article, or commit the resulting article/assets.

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear numbered workflow and explicit verification, but it loses conciseness to repetition and lacks progressive disclosure for a non-trivial single-file skill, and the verification step omits an explicit error-recovery feedback loop.

Suggestions

De-duplicate the full-page/section-crop and cover-image guidance so each rule lives in one place (e.g., keep the canonical version in the Capture Contract and reference it from the Workflow).

Add an explicit validate→fix→retry loop in step 7 so a failed verification check (missing screenshot, unreadable MP4, non-contiguous crops) routes back to the relevant capture step.

Move the long Library Guidance and/or the Daily UI Inspiration Capture Contract into reference files and link to them from SKILL.md so the main file stays a lean overview.

DimensionReasoningScore

Conciseness

It avoids explaining concepts Claude already knows, but the full-page/section-crop structure and the 'do not use cover image as motion' rule are restated across the Capture Contract, Workflow steps 4, 5, and 7, and Library Guidance, so not every token earns its place.

2 / 3

Actionability

It gives concrete, operational guidance — search terms like 'mousemove, ScrollTrigger', 'wait 2 seconds before taking the screenshot', and commands 'git diff --check', 'ffprobe', 'git add -f' — matching fully executable, specific instruction even though it is instruction-only rather than code.

3 / 3

Workflow Clarity

The numbered 8-step workflow has an explicit verification checklist in step 7, but for destructive/batch operations (narrow commits, batch capture) there is no validate→fix→retry feedback loop, which the rubric's feedback-loops note caps at 2.

2 / 3

Progressive Disclosure

The ~130-line skill is well-organized into clear sections with no nested references, but it is a monolithic single file with no bundle files and no one-level-deep references for content (Library Guidance, the Daily UI Contract) that could be split out.

2 / 3

Total

9

/

12

Passed

Description

100%

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 specific, trigger-rich, complete (what + explicit when), and clearly niche. It is dense and long, but the rubric rewards completeness and concrete triggers over brevity for this dimension and it uses third-person voice with no buzzword over-claims.

DimensionReasoningScore

Specificity

It enumerates multiple concrete actions — 'Convert a supplied HTML page... into a screenshot-backed article', 'capture screenshots for each prompt', 'add them to an article', 'commit the resulting article/assets' — matching the level-3 anchor for listing several specific actions.

3 / 3

Completeness

It states the what ('Convert... into a screenshot-backed article containing multiple reusable interaction prompts') and an explicit when ('Use when the user provides an HTML file... and asks to extract...'), clearly answering both per the level-3 anchor.

3 / 3

Trigger Term Quality

It covers natural user terms broadly — 'HTML file, exported page, generated-page.html, or local/live reference' and verbs like 'extract animation/interactions', 'create prompts', 'capture screenshots' — matching good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

The niche — turning HTML references into screenshot-backed interaction-prompt articles, triggered by 'generated-page.html' or 'local/live reference' — is distinct and unlikely to fire for unrelated skills, matching the level-3 clear-niche anchor.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MengTo/Skills
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.