html-review-artifact
Framework-wide guidance for crafting polished human-review artifacts as markdown or HTML
- License 许可
- MIT
- 最近更新
- 2026-06-13
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- html-review-artifact
- description
- Framework-wide guidance for crafting polished human-review artifacts as markdown or HTML
03 SKILL.md 正文
HTML Review Artifact Skill
When to Use This Skill
Use this skill when the deliverable is a human-review artifact that may be:
- a concise
*.mdsummary for fast review, or - a standalone
*.htmlpage for richer visual review.
If the artifact is HTML, treat it like a polished review surface, not a raw dump of content.
Output Modes
Mode 1: Markdown Review Artifact
Use markdown when the goal is speed, traceability, or lightweight review.
Keep it structured:
- short title
- one-sentence summary
- sections for context, decision, evidence, and next steps
- tables for comparisons
- checklists for action items
Mode 2: HTML Review Artifact
Use HTML when the artifact should feel like a polished review page.
HTML review artifacts should have:
- a strong hero area with title, summary, and status
- one clear primary column for the content under review
- one secondary column for metadata, decisions, or timeline
- card-based sections with clear hierarchy
- visible pills/badges for status and decision
- responsive behavior on mobile and desktop
- accessible semantic structure
Tailwind-Style Guidance
If the environment already uses Tailwind, you may express the artifact with utility classes. If there is no Tailwind build step, keep the same visual language with self-contained CSS.
In either case, aim for Tailwind-like qualities:
- consistent spacing scale
- restrained color palette
- rounded cards and chips
- readable typography hierarchy
- strong contrast
- minimal decorative noise
- no cluttered layouts
Hard Rules
- Make the review obvious - the page should immediately tell the human what to inspect.
- Prefer semantic HTML -
header,main,section,aside,article. - Keep it responsive - the artifact must work on a narrow browser window.
- Use realistic content - no placeholder text, no lorem ipsum.
- Avoid generic white-page layouts - the artifact should feel intentionally designed.
- No external dependency by default - do not require a CDN unless the task explicitly allows it.
- No inline clutter - keep styles organized and minimal.
Recommended Structure
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>[Artifact Title]</title>
</head>
<body>
<main>
<header>
<!-- title, summary, status -->
</header>
<section class="grid">
<article>
<!-- primary artifact content -->
</article>
<aside>
<!-- review metadata, decision, timeline -->
</aside>
</section>
</main>
</body>
</html>
Quality Checklist
- [ ] Title and status are obvious at a glance
- [ ] Content is split into readable sections
- [ ] Metadata is separated from the main content
- [ ] Mobile layout still reads cleanly
- [ ] The page looks intentional, not boilerplate
- [ ] The artifact is easy to review in one pass
04 同仓库更多 Skills
hello-checker
Use this skill when asked to "verify", "check", or "validate" a file's existence and content. It provides a reliable workflow for confirming files meet their spec.
ask-skill
暂无简介
converge-planning
Design a Converge playbook end-to-end. Use when the user says "plan a project", "design a playbook", "decompose into tasks", "scaffold a Converge workflow", "onboard to Converge", or asks how to write TASK.md / playbook.yml. Two entry points: plan a new playbook or update an existing one. Hand off to `/converge-control` after producing the playbook structure.
converge-control
Operate a Converge playbook end-to-end — start runs, monitor progress, narrow failures with `--select`, inspect runtime state, validate definitions, surgically reset subtrees, and stop stuck or orphaned runs. Use this skill whenever the user says "run my playbook", "execute this", "monitor the run", "converge failed", "the run is stuck", "retry failures", "babysit this playbook", "what's the status?", "show me the gantt", or asks how to use `converge run` / `--select` / `inspect` / `doctor` / `clean` / `stop`. Also use it for `HTTP 401` / `Invalid API key` failures on the first task — those are environment-not-playbook problems — and for any post-run cleanup work. Hand off to `converge-planning` if the user wants to design or restructure the playbook itself.
repair-taskts
Fix task.ts definition issues — Seed syntax, missing .build(), empty checks, import errors, TypeScript errors
repair-spawn-intermediate
Generate a new intermediate task when no existing task produces a required output