render-html

Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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 highly actionable, well-sequenced skill with strong validation feedback loops, held back by length and inline bulk that could be offloaded to reference files. Core execution guidance is excellent; the roadmap and full prompt-template material inflate the body.

Suggestions

Move the full Codex audit prompt template and the two-phase integration-plan table into a reference file (e.g., references/review-gate.md) and link to it, reducing inline bulk and improving progressive_disclosure.

Trim or relocate the 'External alternatives' html-anything section and the philosophy epigraph to tighten conciseness without losing the core execution guidance.

Consider a short 'Quick start' block at the top with the single most common invocation, deferring the multi-layer resolver chain to a Tool Location subsection.

Dimension	Reasoning	Score
Conciseness	Mostly operational and specific to ARIS (no basic-concept padding), but noticeably long with sections that could be tightened: the two-phase integration-plan table, the external-alternatives pointer to html-anything, and the philosophy epigraph; not a 2 because it avoids explaining concepts Claude already knows and the bulk earns its place.	3 / 5
Actionability	Fully executable guidance throughout: a copy-paste resolver bash chain, concrete invocation examples covering every flag, and a complete Codex audit prompt template with fill-in placeholders; matches the copy-paste-ready 5 anchor.	5 / 5
Workflow Clarity	A clearly sequenced 5-step workflow with an explicit Review Gate validation checkpoint and feedback loops (FAIL → fix source and re-render; WARN → deliver with warnings surfaced; review unavailable → REVIEW_UNAVAILABLE rather than fabricated PASS), matching the 5 anchor for explicit validation and error recovery.	5 / 5
Progressive Disclosure	Clear section headers and real, correctly-pathed bundle references (scripts/render_html.py, scripts/templates/{academic,dashboard}.html) that verify on disk, but substantial content that arguably belongs in separate reference files is inlined — the ~60-line Codex audit prompt, the resolver bash chain, and the two-phase integration table — exceeding minor organization gaps and keeping it below 4.	3 / 5
	Total	16 / 20 Passed

Description

95%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, well-scoped description that crisply states the capability and provides rich, natural bilingual trigger phrases. Minor room to expand the concrete action list beyond the single render operation.

Dimension	Reasoning	Score
Specificity	Names the domain (ARIS Markdown/JSON artifact) and the concrete action (render into a single-file HTML view for human reading) while enumerating multiple handled artifact types (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state); falls short of 5 because the action set is essentially a single render operation rather than multiple distinct concrete actions.	4 / 5
Completeness	Explicitly answers both what ("Render an ARIS Markdown / JSON artifact ... into a single-file HTML view designed for human reading") and when ("Use when the user says ...") with concrete trigger phrases, matching the 5 anchor directly.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say, in both Chinese and English ("渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html"), plus a prose trigger ("wants a polished web-rendered view of a Markdown artifact"); clearly above the 4 anchor which expects a few missing natural terms.	5 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (ARIS artifacts → single-file HTML) with distinctive bilingual trigger phrases unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

81%

Warnings & errors only

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

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/render-html/SKILL.md
Commit: 2132036

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.