examples / rules
Cursor rule3k starsChanged 9 months agoMITView on GitHub
Keep content evergreen - avoid time-specific language. Never use: dates, "recently", "new", "coming soon", "cutting-edge" Always use: Present tense, evergreen phrasing See: .ai/writing-guidelines.md#timeless-content for complete guidance
We split this timeless-content.mdc into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Keep content evergreen - avoid time-specific language.
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 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
--- alwaysApply: true --- # Timeless Content Guidelines Keep content evergreen - avoid time-specific language. **Never use:** dates, "recently", "new", "coming soon", "cutting-edge" **Always use:** Present tense, evergreen phrasing **See:** **`.ai/writing-guidelines.md#timeless-content`** for complete guidance
Trending
Quiet this year.thin dataabout the whole repository
Who's talking about pinecone-io/examples
- langchain-ai/langchain“Add a langchain.embeddings.AnthropicEmbeddings class”GitHub · May 26, 2023 · 4 reactions
- A Hacker News story“Alternative Chunking Methods”Hacker News · Apr 30, 2024 · 2 points
- A Hacker News story“RAG with Groq and Llama 3”Hacker News · May 31, 2024 · 1 points
- Sstobo/Site-Sn33k“Integrate openAI to test the project”GitHub · Apr 24, 2023 · 1 reactions
- KIDA-BfR/App-Development“Chatbot FSKX: hook/injection for standardized agents”GitHub · Jun 3, 2024
The biggest 5 of 13 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 13
Talked about on GitHub, Hacker News and Stack Overflow (13 times).
On GitHub · 10
- May 26, 2023Add a langchain.embeddings.AnthropicEmbeddings class — langchain-ai/langchain4 reactions · 1 comment
- Apr 24, 2023Integrate openAI to test the project — Sstobo/Site-Sn33k1 reaction · 3 comments
- Jun 3, 2024Chatbot FSKX: hook/injection for standardized agents — KIDA-BfR/App-Development0 reactions
- Mar 22, 2024openai embedding models 비교 및 코드 예제 — mjkweon17/practice-python-api0 reactions
- Nov 23, 2023Prompt engineer the query variation prompt — CsabaConsulting/ThruThinkCohereWeaviateChat0 reactions · 1 comment
5 more on GitHub
- Nov 23, 2023Use cohere re-ranker after we got the reranked list of the fused documents — CsabaConsulting/ThruThinkCohereWeaviateChat0 reactions · 1 comment
- Jun 30, 2023AttributeError: module 'threading' has no attribute '_Condition' — googlecolab/colabtools0 reactions · 1 comment
- Mar 26, 2023Investigate Index & Vector databases for Embeddings — slevin48/openai0 reactions · 3 comments
- Mar 25, 2023Create ChatGPT Plugins — slevin48/openai0 reactions · 1 comment
- Mar 23, 2023Task 3: Image search using Pinecone — parvashah-create/image-search0 reactions
On Hacker News · 2
- Apr 30, 2024Alternative Chunking Methods2 points
- May 31, 2024RAG with Groq and Llama 31 point
On Stack Overflow · 1
- Apr 15, 2024Trouble converting RAG method code meant for Sagemaker in AWS Lambda0 votes · 1 answer
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 3,978 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 repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/notebook-guidelines.mdcCursor rule
- .cursor/rules/voice-and-styleguides.mdcCursor rule
- convert-to-marimoSkill
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.