skills / markdown-html
CLAUDE.md1 starsChanged 41 days agoMITView on GitHub
This file provides domain-specific guidance for skills in markdown-html/. The markdown-html domain converts long markdown files (the actual artifacts produced inside a Claude project — specs, reports, RFCs, PR writeups, slide outlines) into world-class, single-file, lightly-interactive HTML. Inspired by Thariq Shihipar's argument (Medium, 2026): markdown collapses past ~100 lines because it lacks visual machinery for density and lateral navigation; HTML restores both. It is not an interactive prompt-tuning playground (/playground plugin owns that lane), not a landing-page generator (marketing/landing/), not…
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
All three converters are shipped.
- Very specific: line 28
Single-file HTML output: All CSS and JS inline. The only permitted external CDN entries are Google Fonts CSS and Prism.js.
- Very specific: line 31
Customization in use, not decoration: Every converter MUST render differently when the user changes design_style, brand.primary, …
- Very specific: line 68
Every converter sub-skill imports config_loader.py and calls load_config() to read project > global > defaults.
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Markdown → HTML — Domain Guide
This file provides domain-specific guidance for skills in markdown-html/.
Purpose
The markdown-html domain converts long markdown files (the actual artifacts produced inside a Claude project — specs, reports, RFCs, PR writeups, slide outlines) into world-class, single-file, lightly-interactive HTML. Inspired by Thariq Shihipar's argument (Medium, 2026): markdown collapses past ~100 lines because it lacks visual machinery for density and lateral navigation; HTML restores both.
It is not an interactive prompt-tuning playground (/playground plugin owns that lane), not a landing-page generator (marketing/landing/), not a session-handoff brief generator (engineering/handoff/ + productivity/handoff/), and not a static-site generator (single-file artifacts, not site indices).
Skills (v2.10.3 — domain complete)
| Skill | Purpose | context: fork? | Status |
markdown-html-orchestrator | Domain orchestrator — classifies doctype, gates on threshold + onboarding, routes to converter | YES | ✓ live |
design-system | One-time onboarding wizard + WCAG-AA-validated brand palette (12 CSS custom properties) + shared config | NO | ✓ live |
md-document | Long-form converter: sticky TOC, collapsibles, search, code-copy, scrollspy | NO | ✓ live |
md-review | Code-review converter: 2-col diff + severity-tagged margin annotations + jump-nav | NO | ✓ live |
md-slides | Slide-deck converter: arrow-key nav + presenter mode + print-to-PDF | NO | ✓ live |
All three converters are shipped. Routing always targets the converter skill's scripts — never hand-render HTML inline.
Hard rules (domain-specific)
- Refuses input < 100 lines. Markdown still wins below the threshold (Shihipar). Every converter (and the orchestrator) prints the line count and a "keep as markdown" recommendation.
- Refuses without design-system onboarding. The orchestrator's
route_explainer.pychecksconfig_loader.setup_completed(). If false, refuse and surface onboarding (python3 markdown-html/skills/design-system/scripts/onboard.py). - WCAG AA enforced.
brand_palette_validator.pyrejects color combinations whose body-text contrast falls below 4.5:1 on bg. Link contrast is iteratively walked to 4.5:1 by adjusting luminance. - Single-file HTML output. All CSS and JS inline. The only permitted external CDN entries are Google Fonts CSS and Prism.js. No bundler, no build step, no JS framework runtimes (vanilla JS + IntersectionObserver only).
- Never silently chain converters. "Convert this markdown AND make slides from it AND a code review" is three operations. Pick one, finish, ask before chaining.
- Stdlib-only Python. Deterministic logic, no LLM calls in scripts.
- Customization in use, not decoration. Every converter MUST render differently when the user changes
design_style,brand.primary,code_theme, ortoc.behavior. If a token doesn't change behavior, it doesn't belong in the schema. - Onboarding-first. The orchestrator surfaces onboarding the moment it detects a missing
setup_completed_at. Don't render with placeholder defaults silently.
Build pattern
Path-B contract per skill: SKILL.md + 3 stdlib scripts + 3 references (each citing 5-7 sources) + (optional) 1 asset template. The orchestrator skill ships context: fork in its frontmatter. The design-system skill is the shared brand owner — every converter imports its config_loader.py via sys.path.insert(0, .../design-system/scripts).
Each SKILL.md ships a "Forcing-question library" section (cited-canon grilling, one question at a time) — same discipline as research-ops, commercial, and business-operations.
Agent + command pattern
cs-markdown-html-orchestrator— density-first markdown-to-HTML converter. Voice: "What decision does this HTML drive — is the reader skimming, deciding, or presenting?"/cs:markdown-html <path>.md— top-level router (classifier + route + recommend)/cs:grill-markdown-html <path>.md— Matt-Pocock-style 5-question grill before conversion/cs:design-system— surface the onboarding wizard
Per-sub-skill commands (all live):
/cs:md-document,/cs:md-review,/cs:md-slides
Anti-patterns (domain-level)
- ❌ Converting markdown < 100 lines — markdown still wins. Refuse + cite Shihipar.
- ❌ Skipping onboarding because "the user wants it done now." Surface onboarding — it's 60 seconds.
- ❌ Multi-file output (separate CSS / JS / image folders). Single file or nothing.
- ❌ External JS framework runtimes (React, Vue, Svelte, Alpine). Vanilla JS + IntersectionObserver only.
- ❌ Silently overwriting existing output files.
output_path_resolver.pysuffixes-2,-3, … by default. - ❌ Setting
MARKDOWN_HTML_NO_CONFIG=1silently for an interactive user. - ❌ Decorative tokens — every token must change at least one converter's output.
- ❌ Inventing brand colors when the user hasn't onboarded.
- ❌ A skill that overlaps Anthropic's official Playground plugin (sliders/knobs/prompt-copy-back).
- ❌ A skill that overlaps
marketing/landing/(landing-page generation from scratch).
Customization pipeline
- User runs
python3 markdown-html/skills/design-system/scripts/onboard.py. - Wizard validates brand colors via
brand_palette_validator.py, derives 12-token palette. - Result written to
~/.config/markdown-html/design-system.json(or./.markdown-html/design-system.jsonwith--scope project). - Every converter sub-skill imports
config_loader.pyand callsload_config()to read project > global > defaults. - Each converter's renderer emits a single
<style>block with:root { --md-bg: ...; }for all 12 tokens, then references those variables throughout the CSS. - Result: change a single field via
--set brand.primary=#FF6B35→ next conversion re-renders with the new brand.
References
- Spec: Thariq Shihipar — Claude Code HTML output: Why Markdown Lost and How to Switch (Medium, 2026)
- Forking pattern source:
research-ops/skills/research-ops-skills/SKILL.md(context: fork, two-signal routing) - Onboarding pattern source:
research-ops/skills/clinical-research/scripts/onboard.py+config_loader.py - Brand palette math source:
marketing/landing/skills/landing/scripts/brand_palette_validator.py - Matt Pocock grill-with-docs:
engineering/grill-with-docs - Single-file HTML discipline source:
marketing/landing/skills/landing/SKILL.md
Other versions8 projects use a version of this.
Word for word · 8
- sohaibdevv/claude-skills★ 2100% same
- ai-integr8tor/alirezarezvani-claude-skills★ 1100% same
- GongYuanCaiJi/dsh-claude-skills★ 1100% same
- skaahgroup-a11y/skills★ 1100% same
- DimonYarkin/claude-skills★ 0100% same
- gladkovtimoxa-alt/claude-skills★ 0100% same
- ls-ducournau/claude-skills★ 0100% same
- SirkoBot007/claude-skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository57 other files it gives its agents.
- agent-launcher/CLAUDE.mdCLAUDE.md
- agents/CLAUDE.mdCLAUDE.md
- business-growth/CLAUDE.mdCLAUDE.md
- business-operations/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- c-level-advisor/CLAUDE.mdCLAUDE.md
- commercial/CLAUDE.mdCLAUDE.md
- engineering-team/CLAUDE.mdCLAUDE.md
- finance/CLAUDE.mdCLAUDE.md
- marketing-skill/CLAUDE.mdCLAUDE.md
- product-team/CLAUDE.mdCLAUDE.md
- project-management/CLAUDE.mdCLAUDE.md
- ra-qm-team/CLAUDE.mdCLAUDE.md
- research-ops/CLAUDE.mdCLAUDE.md
- standards/CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- docs/llms-full.txtllms.txt
- docs/llms.txtllms.txt
- agent-memorySkill
- agent-securitySkill
- answer-verifierSkill
- api-securitySkill
- authorized-security-assessmentSkill
- container-securitySkill
- contract-first-clean-archSkill
- coordinate-implementationSkill
- dast-configSkill
- dependency-scanningSkill
- doubt-driven-developmentSkill
- evidence-gateSkill
- firewall-reviewSkill
- human-inputSkill
- hyperagent-eval-skillSkill
- iac-securitySkill
- intent-lockSkill
- interview-meSkill
- mcp-auditorSkill
- memory-graphSkill
- segmentationSkill
- owasp-top-10-webSkill
- prompt-injectionSkill
- prompt-injection-detectorSkill
- pr-reviewSkill
- repo-kickstartSkill
- restricted-defensive-validationSkill
- sast-configSkill
- secrets-managementSkill
- secure-code-reviewSkill
- security-and-hardeningSkill
- setup-project-memorySkill
- skill-auditorSkill
- solo-founderSkill
- source-driven-developmentSkill
- take-ownershipSkill
- threat-modelingSkill
- wrap-upSkill
- loop-librarySkill
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
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.

