agentleFS
Makkov-designMakkov-design/makkov-harness/skills/html-report/SKILL.md

html-report

Skill8 starsChanged 10 days agoMITView on GitHub

Use whenever the result of a task is a research, analysis, comparison, plan, roadmap, audit, strategy, recommendation or any multi-section deliverable meant to be read, in an agent that has no Claude Artifacts (Codex, Cursor, Gemini CLI, Copilot, Windsurf, Cline, OpenCode, Aider, local models). Writes one polished, self-contained HTML file (tables, charts, timelines, navigation, both themes) into the project and, on revisions of the same topic, edits that same file. In Claude with Artifacts, use rich-report instead.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use code-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the agent cannot write files (a chat app), give the same structure as clean Markdown in the reply instead.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

HTML report: deliverables as one self-contained page

The same house style and structure as rich-report, delivered as a local .html file that opens in any browser and can be sent as an attachment. No hosting, no account, no build step.

When to apply

Research results, comparisons, plans and roadmaps, audits, strategies, recommendations, any report with 3+ sections or a data table. Short answers, explanations, code changes and command output stay in chat.

If the agent cannot write files (a chat app), give the same structure as clean Markdown in the reply instead.

One file per topic

  1. Save to reports/<topic-slug>.html in the current project (create reports/). Name the file after the topic and keep the name.
  2. A follow-up on the same topic ("add", "recalculate", "shorter", changed inputs) edits that file; it never creates a second one. Refresh every place the change affects and keep a short "What changed" block near the top (date plus 2-4 bullets, latest few only).
  3. A genuinely different topic gets a new file. If unsure, ask in one line.

Build

  1. Start from skeleton.html in this folder. Keep its tokens, fonts, radii, spacing and component CSS; replace the sample content; delete components the content does not need. Keep the two impeccable-disable comments at the top of <style> (they silence false contrast and padding findings from the Impeccable hook), and give any new bordered component at least 12px of padding.
  2. Unlike an Artifact, the file is a whole document: wrap the skeleton in <!doctype html><html lang="…"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1">…</head><body>…</body></html>, with <title> and <style> in the head.
  3. Everything inline: CSS, JS, SVG icons, data. Google Fonts is the only external request; the font stacks fall back to system fonts offline. If a chart library is truly needed, load one pinned version from a CDN and say the chart needs internet.
  4. Both themes through prefers-color-scheme; works at 400px wide with no horizontal page scroll; tables scroll inside their own container.
  5. Open it once if the agent can (start, open or xdg-open with the file path), fix what is visibly broken, then stop.
  6. In chat: the file path plus 2-3 lines (main conclusion, where to look first). Do not paste the report into chat.

House style, anatomy and content rules

Identical to rich-report: Linear-inspired neutral surfaces with one lavender-blue accent (#5e6ad2, #828fff as text on dark), Onest at 400/500/600, JetBrains Mono for IDs and dates, hairline borders, no shadows, gradients or emoji markers; header, 3-4 takeaway cards, contents rail, sections that open with their conclusion; real tables, charts drawn to scale, timelines, risks with severity pills, <details> for long reasoning. If rich-report is installed next to this skill, read its SKILL.md for the full component table; otherwise the skeleton shows every component.

Truthfulness

Numbers, quotes and sources come from the actual work. Never invent data to fill a chart. Mark estimates and low-confidence items visibly.

Checklist

  • Same-topic revision edited the same file
  • Answer visible without scrolling; takeaways match the body
  • Opens offline with no console errors; both themes readable; fine at phone width

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.