cloudai-docs-contribution
Skill103 starsChanged 58 days agoApache-2.0View on GitHub
Write, edit, or review CloudAI documentation, including README.md, doc/, release notes, and docstrings.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- cloudai-config-contributionSkill
- cloudai-remote-experimentSkill
- cloudai-remote-installSkill
- cloudai-workload-contributionSkill
- pr-managementSkill
- security-assessmentSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Write for the intended reader, not the PR reviewer.
- Distinctive: line 18
Prefer a small concrete example over vague prose.
- Distinctive: line 22
Check the rendered result when changing docs: list nesting, code blocks and links can look correct in source but fail in the published page.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
CloudAI docs contribution
- Write for the intended reader, not the PR reviewer. User docs explain how to use CloudAI; implementation and packaging details belong only where they help the reader's task.
- Describe behavior in the revision being documented. Keep PR stages, roadmap promises and proof-of-concept narration out of product docs; put change history in release notes.
- Explain supported behavior rather than listing everything not implemented. Deliberate product scope is not a known issue. Include constraints when readers need them to use the feature correctly.
- Cut obvious benefits, boilerplate introductions and sentences that repeat the heading. Be concise without becoming cryptic: distinguish test cases, iterations and DSE steps instead of calling everything a "run".
- Extend the relevant page and link existing explanations instead of duplicating them. Keep usage instructions, reference details and implementation rationale distinct; no new page hierarchy for a small feature.
- Prefer a small concrete example over vague prose. Show the actual option, input or output and explain its meaning; don't turn examples into exhaustive schemas or invent behavior to make an explanation sound complete.
- Docstrings should explain non-obvious behavior, not restate names. For an unclear transformation, a short input/output example is more useful than a paragraph describing the implementation.
- Check the rendered result when changing docs: list nesting, code blocks and links can look correct in source but fail in the published page.
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.