ppt-creator
AGENTS.md0 starsChanged 3 months agoMITView on GitHub
This is a public, MIT-licensed skill repository. Review benchmarks/scenarios.md when changing decision behavior. A structure validator does not prove presentation quality.
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 31,774 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 repositoryOne other file it gives its agents.
- ppt-creatorSkill
The file
We split this AGENTS.md into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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
- Very specific: line 8
Put conditional or substantial guidance in references/ and link it from SKILL.md only where it becomes relevant.
- Distinctive: line 9
Keep public installation and usage instructions in the two README files.
- Very specific: line 10
Keep research provenance in docs/research-basis.md.
- Distinctive: line 14
Every new hard rule must address an observed failure, a tested behavior, or a clearly cited primary/reference source.
- Distinctive: line 16
Do not turn one user's taste, one deck, or one visual style into a universal rule.
- Distinctive: line 17
Do not include user decks, screenshots, private paths, customer names, or source material in the public repository.
- Distinctive: line 18
Prefer task-specific, verifiable checks over adjectives such as “beautiful” or “professional.”
- Distinctive: line 19
Keep fidelity, preservation, editability, accessibility, and technical integrity independently testable.
≈ “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.
Files
Maintainer instructions
This is a public, MIT-licensed skill repository.
Scope
SKILL.mdis the entrypoint and routing surface.- Put conditional or substantial guidance in
references/and link it fromSKILL.mdonly where it becomes relevant. - Keep public installation and usage instructions in the two README files.
- Keep research provenance in
docs/research-basis.md; do not copy external or proprietary skill text into this repository.
Quality rules
- Every new hard rule must address an observed failure, a tested behavior, or a clearly cited primary/reference source.
- Preserve the distinction between design judgment and presentation-file mechanics.
- Do not turn one user's taste, one deck, or one visual style into a universal rule.
- Do not include user decks, screenshots, private paths, customer names, or source material in the public repository.
- Prefer task-specific, verifiable checks over adjectives such as “beautiful” or “professional.”
- Keep fidelity, preservation, editability, accessibility, and technical integrity independently testable.
Before committing
Run:
python3 scripts/validate_skill.pyReview benchmarks/scenarios.md when changing decision behavior. A structure validator does not prove presentation quality.
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.