CtrlK
BlogDocsLog inGet started
Tessl Logo

research-to-website

Build informative websites from research reports. Transforms research output (markdown or typst/pdf) into polished, domain-appropriate websites with professional design, data visualization, and scroll-based animations. Triggers on research-to-website tasks, report visualization, or when converting research into web presentations.

64

Quality

75%

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 ./src/ii_agent/agents/skills/builtin/research-to-website/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The skill body is thorough and well-structured for design decisions, but it leans verbose with inline detail that should live in referenced files, its build/deploy workflow lacks executable guidance and validation checkpoints, and its referenced bundle files do not exist.

Suggestions

Tighten the body: remove the duplicated 'Use image search first for accuracy, realism, and credibility.' bullet and move large inline sections (Image Strategy, Brand Color Rules, Anti-Patterns) into reference files the body points to, keeping SKILL.md a lean overview.

Make the Workflow actionable: replace 'Build Website → Implement based on design-spec.md' and 'Deploy → Publish and provide live URL' with concrete commands/steps, and add an explicit validate-then-proceed checkpoint before deployment.

Create the referenced bundle (domains/, components/) or remove the 'Required Reference Files' paths; progressive disclosure scores only when signaled references resolve to real files.

DimensionReasoningScore

Conciseness

The body is well-organized but runs long (~250 lines) with repeated guidance (e.g., the 'Use image search first' bullet is duplicated verbatim) and some explanatory restating of principles Claude already understands, so it is mostly efficient but could be tightened rather than fully lean.

2 / 3

Actionability

It gives a concrete design-spec template, tech stack, and classification tables, but the build and deploy steps are abstract placeholders (e.g., 'Build Website → Implement based on design-spec.md') with no executable code or commands, fitting the anchor for some concrete guidance but incomplete.

2 / 3

Workflow Clarity

The six-step Workflow lists a clear sequence, but steps like 'Build Website' and 'Deploy' are vague with no validation checkpoints; for a destructive/output-publishing operation the rubric caps workflow clarity at 2 when feedback loops are missing.

2 / 3

Progressive Disclosure

It references external paths (domains/*.md, components/*.md) that would support one-level-deep disclosure, but no bundle files are actually present, so the references are unsignaled-to-nonexistent files and a large amount of reference-style detail (image strategy, brand rules, anti-patterns) sits inline rather than being split out.

2 / 3

Total

8

/

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 strong: it states concrete capabilities, natural trigger terms, an explicit 'Use when'-style clause, and occupies a clear niche with low conflict risk. No meaningful weaknesses to address.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'Transforms research output (markdown or typst/pdf) into polished, domain-appropriate websites', 'professional design', 'data visualization', and 'scroll-based animations' — matching the highest anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Build informative websites from research reports') and when ('Triggers on research-to-website tasks, report visualization, or when converting research into web presentations'), meeting the anchor for clear what-and-when with explicit triggers.

3 / 3

Trigger Term Quality

Covers natural user terms such as 'research-to-website tasks', 'report visualization', and 'converting research into web presentations', giving good coverage of phrases users would actually say.

3 / 3

Distinctiveness Conflict Risk

The niche of converting research output into websites with design/visualization/animations is distinct and tied to specific triggers unlikely to conflict with other skills.

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
Intelligent-Internet/ii-agent
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.