claude-skills/markdown-html
Alireza Rezvani ebbf6b0872
Some checks failed
Sync Codex Skills Symlinks / sync (push) Has been cancelled
fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048)
* fix(plugins): bump all plugins to 2.14.1 and gate unbumped changes

Claude Code caches plugins by version. 70 of 104 plugins changed between
v2.12.0 and v2.14.0 without a bump, so claude plugin update reported
"already at the latest version" and existing installs never received the
v2.13/v2.14 fixes. Every plugin moves to 2.14.1 so stale caches refresh once.

check_plugin_versions.py (G11, blocking in ci-quality-gate) fails when a
plugin's payload, including symlinked vendor files, changes without a higher
version, and when marketplace.json and plugin.json disagree.
bump_plugin_versions.py sets both together.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(codex): stop installing all skills by default

With the full library (~380 skills) Codex drops every skill description from
its prompt budget, so it cannot pick skills. codex-install.sh now asks for
--category (comma-separated), --skill or an explicit --all, lists categories
when run without arguments, and warns when more than ~100 skills are
installed. The Windows installer and install docs follow.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(gemini): link whole skill folders and drop duplicate mirror entries

Each .gemini/skills entry held only a SKILL.md symlink, so the relative
scripts/ and references/ a skill points to were missing. Entries are now
directory symlinks (Gemini CLI 0.65 discovers them). Dual-published copies
with identical SKILL.md are listed once, commands and agents that share a
skill's name are skipped, fixtures under assets/ and vendor/ re-exports are
excluded, discovery is sorted so reruns are stable, and stale generated
entries are pruned. gemini skills list: 20 conflicts -> 1 (handoff, fixed
next). GEMINI.md documents folder trust and fixes a dead example path.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(handoff): rename the productivity skill to session-handoff

engineering/handoff and productivity/handoff both shipped a skill named
handoff. Claude Code namespaces them, but Codex, Gemini CLI, Vibe and Hermes
key skills by name and silently kept one. The productivity skill is now
session-handoff (handoff-productivity:session-handoff); its folder, plugin
manifest, hook script paths, command paths, mirrors, harness manifest and
docs page follow. /cs-handoff, /cs-handoff-setup and ~/.config/handoff are
unchanged; the plugin README carries a migration note.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(convert): include plugins whose SKILL.md is at the plugin root

convert.sh searched at -mindepth 4, which skipped boost-asio-pro, deepread,
hivemind, loop-library, minimalist, strict-api and swedish-mentor for every
converted tool (opencode, Cursor, Windsurf, Kilo, Augment, Aider,
Antigravity). It now searches from depth 2 and skips assets/ fixtures.
opencode conversion: 375 -> 382 skills.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(codex): keep skill-tester's sample fixture from loading as a skill

Codex scans installed skill folders recursively and picked up
skill-tester/assets/sample-skill/SKILL.md as 'sample-text-processor'.
The installer renames SKILL.md files under assets/ in the installed copy.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(plugins): address scripts via ${CLAUDE_PLUGIN_ROOT} in commands and agents

343 script invocations in 90 command/agent files across 36 plugins used
repo-relative or ../ paths. Plugin commands and agents run from the user's
project, so those paths only resolved inside a clone of this repo; in the
v2.14.0 evals the agent fell back to find / to locate scripts. Every one now
uses ${CLAUDE_PLUGIN_ROOT}/. Two cross-plugin calls (write-a-skill ->
karpathy-coder, c-level-agents cpo -> product-manager-toolkit) go through
vendor/ symlinks, per the repo's install-cache lesson.

check_paths.py (G1) now fails a plugin command or agent that invokes a
script without ${CLAUDE_PLUGIN_ROOT}; on the v2.14.0 tree it reports 279.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(month-end-close): treat opening-balance rows as balances and pair transpositions

On a bank and GL export that each begin with an 'Opening balance' row, the
matcher returned RECONCILED_WITH_ITEMS and told the user to book a 25,000.00
journal entry for the opening balance, and it reported a 7,980/7,890
transposition as two unrelated items. Opening rows are now balances: a
difference between them is reported as carried in from the prior period
(R5, blocks sign-off, never booked). Same-date digit transpositions pair into
one correcting entry. The GL file's 'memo' column is read as description.
The v2.14.0 eval fixture now proves 1,405.00 = 150 opening + 90
transposition + 1,200 outstanding check - 35 bank fee. Bundled copy synced.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* fix(coding-agent-rollout): flag connection-URL passwords and production MCP servers

On a committed .claude/settings.json holding
env.DATABASE_URL=postgresql://admin:<password>@prod-db... and
enabledMcpjsonServers: ["postgres-prod"], the linter flagged neither: the
env check only matched token formats and KEY/TOKEN/SECRET names. S11 now
catches a password embedded in any connection URL (BLOCKER in shared files),
and new S13 warns when a shared file pre-approves an MCP server whose name
marks it as production. Bundled copy synced; --sample output unchanged.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

* docs: changelog and lessons for the v2.14.0 audit fixes

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016uNBQ6tRS5P1dRsgNfK4Wh

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-10-22 09:50:05 +02:00
..
.claude-plugin fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
agents fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
commands fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
skills fix(docs): replace 2,308 /cs:<name> references with names Claude Code can run 2026-10-21 07:48:14 +00:00
CLAUDE.md fix(docs): replace 2,308 /cs:<name> references with names Claude Code can run 2026-10-21 07:48:14 +00:00
README.md fix(docs): replace 2,308 /cs:<name> references with names Claude Code can run 2026-10-21 07:48:14 +00:00

markdown-html — Markdown to interactive HTML converter

"I generated a 200-line implementation plan in Claude Code last month. Markdown. … I skimmed the first 20 lines, scrolled past the diagram I could not actually parse, and closed the file. I never read the rest." — Thariq Shihipar, Claude Code HTML output (Medium, 2026)

Convert long markdown files in a Claude project into single-file, lightly-interactive HTML that respects your brand. One-time design-system onboarding captures brand primary + accent + typography + layout style + default save location. Every conversion reads that config and renders consistently.

Status — v2.10.3 (domain complete)

Skill Purpose Status
markdown-html-orchestrator Routes long markdown → converter sub-skill (context: fork) ✓ live
design-system Onboarding wizard + WCAG-AA-validated brand palette + shared config ✓ live
md-document Long-form: sticky TOC + collapsibles + search + code-copy + scrollspy ✓ live
md-review Code review: 2-col diff + severity-tagged margin annotations + jump-nav ✓ live
md-slides Slide deck: arrow-key nav + presenter mode + print-to-PDF ✓ live

Quick start

# 1. One-time onboarding (10 questions, ~60 seconds)
python3 markdown-html/skills/design-system/scripts/onboard.py

# 2. (or zero-touch defaults for first-test)
python3 markdown-html/skills/design-system/scripts/onboard.py --defaults

# 3. Inspect the saved config
python3 markdown-html/skills/design-system/scripts/config_loader.py --status

# 4. Classify a markdown file and see the routing decision
python3 markdown-html/skills/markdown-html-orchestrator/scripts/doctype_classifier.py \
    --input ./my-report.md --output json \
  | python3 markdown-html/skills/markdown-html-orchestrator/scripts/route_explainer.py

# 5. Resolve where it would save
python3 markdown-html/skills/markdown-html-orchestrator/scripts/output_path_resolver.py \
    --input ./my-report.md --doctype document

Slash commands

  • /cs-markdown-html <path>.md — top-level router (classify + route + recommend)
  • /cs-grill-markdown-html <path>.md — Matt-style 5-question grill before conversion
  • /cs-design-system — surface the onboarding wizard
  • /cs-md-document <path>.md — long-form converter
  • /cs-md-review <path>.md — code-review converter
  • /cs-md-slides <path>.md — slide-deck converter

Hard rules

  1. Refuses input < 100 lines — markdown still wins below the threshold (Shihipar). Keep short docs as markdown.
  2. Refuses without onboarding — without a captured brand, output renders with placeholder defaults. Run onboarding once.
  3. Refuses unwritable save location — onboarding asks where to save; the orchestrator honors it; collisions get suffixed (-2, -3, …).
  4. Single-file HTML only — all CSS + JS inline. The only external CDN entries are Google Fonts + Prism.js. No build step, no bundler, no JS framework.
  5. Never silently chain — "convert this AND make slides AND a code review" is three operations, asked explicitly.
  6. WCAG AA enforced — body-text contrast must reach 4.5:1. Onboarding refuses any combination that fails.

Distinct from

  • Anthropic Playground plugin (/playground) — builds interactive prompt-tuning controls (sliders, knobs, prompt-copy-back). Different tool entirely.
  • marketing/landing/ — generates landing pages from scratch. Doesn't take markdown input.
  • engineering/handoff/ + productivity/handoff/ — session continuity briefs. Different artifact type.

File layout

markdown-html/
├── .claude-plugin/
│   └── plugin.json
├── agents/
│   └── cs-markdown-html-orchestrator.md
├── commands/
│   ├── cs-markdown-html.md          # router
│   ├── cs-design-system.md          # onboarding surface
│   ├── cs-grill-markdown-html.md    # 5-question grill
│   ├── cs-md-document.md            # long-form converter
│   ├── cs-md-review.md              # code-review converter
│   └── cs-md-slides.md              # slide-deck converter
└── skills/
    ├── markdown-html-orchestrator/  # context: fork
    │   ├── SKILL.md
    │   ├── scripts/
    │   │   ├── doctype_classifier.py
    │   │   ├── route_explainer.py
    │   │   └── output_path_resolver.py
    │   └── references/
    │       ├── information_density_canon.md
    │       ├── orchestrator_routing_patterns.md
    │       └── single_file_html_discipline.md
    ├── design-system/
    │   ├── SKILL.md
    │   ├── scripts/
    │   │   ├── onboard.py
    │   │   ├── config_loader.py
    │   │   └── brand_palette_validator.py
    │   ├── references/
    │   │   ├── design_token_canon.md
    │   │   ├── wcag_accessibility.md
    │   │   └── typography_pairing.md
    │   └── assets/
    │       └── design_system_schema.json
    ├── md-document/                 # long-form: markdown_parser → html_renderer → interactivity_injector
    ├── md-review/                   # code review: diff_parser → annotation_extractor → review_html_renderer
    └── md-slides/                   # slide deck: slide_splitter → presenter_notes_parser → deck_html_renderer

License

MIT. See repo LICENSE.

Spec

Thariq Shihipar — Claude Code HTML output: Why Markdown Lost and How to Switch (Medium, 2026). The plugin operationalizes the article's central claim — markdown collapses past ~100 lines for agent-generated artifacts; HTML restores density, clarity, shareability, and lightweight interaction.