rufushsu9987rufushsu9987/claude-code-slides/AGENTS.md

claude-code-slides

AGENTS.md1 starsChanged 3 months agoMITView on GitHub

This repository ships one portable presentation core plus native Codex and Claude Code adapters. Portable skills: create-deck, review-deck, speaker-notes, claude-code-style, deck-architect, visual-director, deck-reviewer, and diagram-design. Codex invokes them as $skill-name. Claude Code exposes namespaced skills and three native subagents. CLI commands include templates, layouts, init, check, and doctor.

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository17 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- claude-code-styleSkill
- create-deckSkill
- deck-architectSkill
- deck-reviewerSkill
- diagram-designSkill
- review-deckSkill
- speaker-notesSkill
- visual-directorSkill
- claude-code-styleSkill
- create-deckSkill
- deck-architectSkill
- deck-reviewerSkill
- diagram-designSkill
- review-deckSkill
- speaker-notesSkill
- visual-directorSkill

The file

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

8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific
could be automatic: a setting could enforce it

Very specific:
Keep root plugin.json conformant to https://agent-plugins.org/schemas/1.0.0/plugin.schema.json.
line 27
Very specific:
Keep portable SKILL.md files free of host-specific runtime variables, command namespaces, and plugin-root placeholders.
line 28
Distinctive:
Do not edit generated skill-local copies without updating their canonical source.
line 32
Very specific:
Treat package.json as the release-version source and run npm run sync:metadata after changing synchronized descriptions or versions.
line 33
Very specific:
Keep claude-editorial as the canonical default and preserve documented aliases.
line 34
Distinctive:
Keep all manifests and package versions synchronized.
line 36
Distinctive:
Do not add root runtime dependencies unless Node-native capabilities are insufficient.
line 38
Distinctive:
Never imply official Anthropic or OpenAI affiliation.
line 39

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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

AGENTS.md

Repository instructions

This repository ships one portable presentation core plus native Codex and Claude Code adapters.

Architecture

plugin.json: Agent Plugins 1.0.0 portable manifest.
skills/: authoritative portable Agent Skills, including the vendored diagram-design visual diagram skill.
references/: canonical storytelling, visual, layout, output, review, and Python SVG planning guidance.
templates/catalog.json: visual-theme catalog; default is claude-editorial.
templates/layouts.json: authoritative semantic layout archetypes and diversity rules.
scripts/generate-slide-art.py and scripts/skill-cli-wrapper.mjs: canonical skill-local helper sources.
scripts/sync-skill-resources.mjs: generates skill-local references, helpers, CLI runtime bundles, and .agents/skills/ forwarders.
scripts/sync-release-metadata.mjs: keeps package, plugin, and marketplace descriptions and versions aligned.
.codex-plugin/, .agents/plugins/, .agents/skills/: Codex adapter.
.claude-plugin/, agents/, CLAUDE.md: Claude Code adapter.
bin/ and lib/: zero-dependency presentation CLI.

Public surface

Portable skills: create-deck, review-deck, speaker-notes, claude-code-style, deck-architect, visual-director, deck-reviewer, and diagram-design.

Codex invokes them as $skill-name. Claude Code exposes namespaced skills and three native subagents. CLI commands include templates, layouts, init, check, and doctor.

Rules

Keep root plugin.json conformant to https://agent-plugins.org/schemas/1.0.0/plugin.schema.json.
Keep portable SKILL.md files free of host-specific runtime variables, command namespaces, and plugin-root placeholders.
Reference bundled files with references/... and scripts/... paths relative to the skill root.
Edit canonical content under root skills/, references/, scripts/generate-slide-art.py, scripts/skill-cli-wrapper.mjs, bin/, lib/, or templates/, then run npm run sync:skills.
skills/diagram-design/ is a vendored, self-contained skill pack; edit it in place, preserve its attribution and licenses, and do not treat its gallery assets as generated presentation-core copies.
Do not edit generated skill-local copies without updating their canonical source.
Treat package.json as the release-version source and run npm run sync:metadata after changing synchronized descriptions or versions.
Keep claude-editorial as the canonical default and preserve documented aliases.
Select layout archetypes by semantic page role, not random visual variation.
Keep all manifests and package versions synchronized.
Preserve HTML, Marp, and editable PPTX output.
Do not add root runtime dependencies unless Node-native capabilities are insufficient.
Never imply official Anthropic or OpenAI affiliation.

Validation

npm ci
npm run sync:skills
npm run check

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