contextdb / rules
Cursor rule18 starsChanged 3 months agoApache-2.0View on GitHub
SEO, AEO, examples, links, and claim gate for every publication
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,144 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 repository6 other files it gives its agents.
- ai-tools/AGENTS.mdAGENTS.md
- ai-tools/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/open-core-boundary.mdcCursor rule
- ai-tools/llms-full.txtllms.txt
- ai-tools/llms.txtllms.txt
The file
We split this publication-content.mdc into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Use the customer's vocabulary in title, opening, headings, links, and examples.
- Distinctive: line 28
Use descriptive link text, not "here" or bare URLs.
- Distinctive: line 35
No publication is complete until every hyperlink resolves, examples run, claims are substantiated, and one clear next action is visible.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
--- description: SEO, AEO, examples, links, and claim gate for every publication alwaysApply: true --- # Publication Content Gate Applies to releases, package pages, READMEs, changelogs, launch posts, public PRs, docs intros, landing pages, and announcements. Before publishing, include: 1. A human title containing the category, customer job, and product name. 2. An answer-first summary that explains what shipped, for whom, and why. 3. The world shift or old workflow this makes obsolete. 4. Install/get-started commands and at least one runnable code example. 5. Two or more concrete use cases tied to named users or buyer roles. 6. Descriptive links to source, docs, package registries, changelog, examples, related guides, and the lowest-friction CTA. 7. Direct FAQ questions and concise answers that search/answer engines can quote. 8. Current status, limitations, compatibility, and migration/upgrade guidance. 9. A proof object: measured number, JSON, code, screenshot, or verified behavior. SEO/AEO: - Use the customer's vocabulary in title, opening, headings, links, and examples. - Answer the primary query in the first paragraph; never bury the definition. - Use descriptive link text, not "here" or bare URLs. - Include canonical package/product names consistently. Hype must be earned from concrete objects and defensible measurements. Never invent a superlative, SLA, customer, benchmark, scale result, or comparison. Alpha/beta/planned status stays explicit. No publication is complete until every hyperlink resolves, examples run, claims are substantiated, and one clear next action is visible.
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.