CtrlK
BlogDocsLog inGet started
Tessl Logo

moai-domain-html-report

Markdown-to-single-file-HTML report renderer. Six modes (status, incident, plan, explainer, financial, pr) selected by report type, crossed with three audience tiers (expert, basic, learn) derived from the active output style. The basic and learn tiers enrich the HTML with mermaid flowcharts, worked examples, and plain-language primers; the expert tier stays dense. Zero external JS/CSS framework dependencies — inline SVG charts, a font-CDN exception for Korean readability, and a tier-gated mermaid-CDN exception. Self-contained output for email attachment, print, and offline viewing.

59

Quality

70%

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 ./.claude/skills/moai-domain-html-report/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 detailed, actionable body for a complex six-mode/three-tier renderer, with strong concrete code blocks and per-mode variable specs. It is held back by repeated restatements of the same invariant, missing validation checkpoints in the render workflow, and a broken design-tokens.md reference alongside an orphaned craft-fundamentals.md file.

Suggestions

Fix the broken reference: either add references/design-tokens.md (holding the full contrast verification and print tokens) or remove the two links to it and inline only what exists.

Link references/craft-fundamentals.md from the body (or remove it from the bundle) so every bundled file is discoverable from SKILL.md.

Add an explicit validation checkpoint after rendering — e.g., verify output size against the ≤50KB/≤120KB budget and confirm the .md twin carries no tier enrichment — with a fix-and-retry loop if the check fails.

Consolidate the markdown-twin-lean / asymmetry invariant into one authoritative statement and reference it from the other sections instead of restating it four to five times.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the markdown-twin-lean / asymmetry invariant is restated four to five times across Purpose, the dedicated asymmetry section, the Audience Tiers table, and Non-goals, which could be tightened without losing the rule.

3 / 5

Actionability

Concrete, copy-paste-ready material abounds — the mermaid-CDN module script with real URLs and themeVariables, the cross-platform bash opener, the :root design-token CSS, and per-mode template variable lists — with only a minor gap in that usage examples are natural-language prompts rather than a single end-to-end render invocation.

4 / 5

Workflow Clarity

The sequence is clear (resolve tier → select mode → fill template → write .html and .md twin → summarize and auto-open) and tier-resolution precedence is explicit, but there are no explicit validation checkpoints such as verifying the size budget (≤50KB/≤120KB) or confirming the twin omits tier enrichment.

3 / 5

Progressive Disclosure

Structure is good — an overview with one-level-deep references to templates and fonts and a dedicated References section — but references/design-tokens.md is referenced in two places yet absent from the bundle, and references/craft-fundamentals.md exists but is never linked, so navigation is not clean.

3 / 5

Total

13

/

20

Passed

Description

83%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 strong, specific description that names concrete modes, tiers, and dependency constraints with a clear niche. Its only gap is that the 'when to use' trigger sits in a separate when_to_use field rather than the description string, and a few natural trigger synonyms are absent.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — six named modes (status, incident, plan, explainer, financial, pr), three audience tiers, inline SVG charts, font-CDN and tier-gated mermaid-CDN exceptions, and self-contained output for email/print/offline — giving comprehensive coverage rather than a few actions.

5 / 5

Completeness

The description field gives a clear, detailed 'what', and the frontmatter's separate when_to_use field supplies an explicit 'Use when a markdown report must be rendered...' trigger; because that trigger lives in a sibling field rather than the description itself, it is just short of a fully self-contained 5.

4 / 5

Trigger Term Quality

Natural terms a user would say are present ('HTML report', 'markdown report', 'render', 'single self-contained HTML file'), but a few common synonyms and the .html extension are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clear niche — single-file HTML report rendering with six specific modes and a tier system, zero JS/CSS framework dependencies — with distinct triggers and minimal overlap risk against generic markdown or document skills.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 2 missing, 6 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 4 missing, 12 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
modu-ai/moai-adk
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.