agentleFS
Sign inStart free
rufushsu9987rufushsu9987/claude-code-slides/CLAUDE.md

claude-code-slides

CLAUDE.md1 starsChanged 3 months agoMITView on GitHub

This repository is a Claude Code plugin backed by a portable Agent Plugins 1.0.0 core shared with Codex and other compatible clients. After editing skills/, agents/, .claude-plugin/, references/, or the template catalogs, run /reload-plugins or start a new Claude Code session.

The file

We split this CLAUDE.md into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After editing skills/, agents/, .claude-plugin/, references/, or the template catalogs, run /reload-plugins or start a new Claude Code …

    line 15
  2. Very specific:

    Keep package.json as the version source, then run npm run sync:metadata to update plugin.json, both native manifests, both marketplaces, …

    line 46
  3. Distinctive:

    Do not use official Anthropic or OpenAI marks or wording that implies endorsement.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 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.

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

Claude Code repository guide

This repository is a Claude Code plugin backed by a portable Agent Plugins 1.0.0 core shared with Codex and other compatible clients.

Development

npm ci
npm run sync:skills
npm run check
claude plugin validate .
claude --plugin-dir .

After editing skills/, agents/, .claude-plugin/, references/, or the template catalogs, run /reload-plugins or start a new Claude Code session.

Claude Code surface

  • /claude-code-slides:create-deck
  • /claude-code-slides:review-deck
  • /claude-code-slides:speaker-notes
  • /claude-code-slides:claude-code-style
  • /claude-code-slides:diagram-design
  • subagents: deck-architect, visual-director, deck-reviewer
  • Bash CLI alias: claude-slides
  • theme discovery: claude-slides templates
  • layout discovery: claude-slides layouts

Theme and layout rules

  • claude-editorial is the default visual theme.
  • terminal-editorial remains a backward-compatible alias.
  • templates/layouts.json is the authoritative source for semantic layout archetypes and diversity rules.
  • A 10+ slide deck should normally use at least eight distinct archetypes, avoid consecutive repeats, limit card-based pages, and change rhythm every three to four slides.
  • HTML uses data-layout, Marp uses slide classes, and PPTX keeps LAYOUT_SEQUENCE.

Portability rules

  • Root skills/ are authoritative and must remain host-neutral.
  • Skill resources are local to each skill under references/, scripts/, and (for CLI-using skills) runtime/.
  • skills/diagram-design/ is a vendored self-contained skill pack with its own attribution and third-party license records.
  • Root skills/, references/, scripts/generate-slide-art.py, scripts/skill-cli-wrapper.mjs, bin/, lib/, and templates/ are canonical; run npm run sync:skills after edits.
  • .agents/skills/ forwarders and skill-local resources are generated; do not edit them without changing their canonical source.
  • Claude-specific behavior belongs in .claude-plugin/, agents/, or this guide.
  • Codex-specific behavior belongs in .codex-plugin/ and .agents/.
  • Keep package.json as the version source, then run npm run sync:metadata to update plugin.json, both native manifests, both marketplaces, package-lock.json, and lib/runtime.mjs.
  • Preserve HTML, Marp, and PPTX support.
  • Do not use official Anthropic or OpenAI marks or wording that implies endorsement.

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.

Check your setup, free