datasl / rules
Cursor rule0 starsChanged 18 days agoMITView on GitHub
Working on the Data SL Consulting toolkit (datasl CLI and SDKs, agent skill, plugin manifests) or writing code that calls the Data SL Consulting public API or MCP server
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 4,183 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.
The file
We split this datasl.mdc into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Keep js/ and python/ dependency-free and behaviourally identical (same commands, --json output, exit codes 0/1/2).
- Distinctive: line 23
Never hard-code prices or offers: the API is the source of truth.
- Very specific: line 25
Run cd js && npm test and cd python && PYTHONPATH=src python -m unittest discover -s tests before proposing a change.
≈ “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: Working on the Data SL Consulting toolkit (datasl CLI and SDKs, agent skill, plugin manifests) or writing code that calls the Data SL Consulting public API or MCP server
globs: ["js/**", "python/**", "skills/**", "*.json"]
alwaysApply: false
---
# Data SL Consulting toolkit
Full instructions: see `AGENTS.md` at the repository root.
## API facts
- REST base URL: `https://data-slconsulting.com/wp-json/datasl/v1` (read-only, public, no authentication). OpenAPI 3.1: https://data-slconsulting.com/openapi.json
- Routes: `GET /offres` (filters `cible`, `categorie`, `champs`), `GET /offres/{slug}`, `GET /cabinet`, `GET /contact`; search: `GET /wp-json/wp/v2/search?search=...`
- MCP server: `https://data-slconsulting.com/api/mcp-server` (Streamable HTTP; tools `get_offers`, `search_site`, `fetch_page`).
- Errors: JSON `{"code", "message", "data": {"status", "hint"}}`; show `hint` to the user.
- Rate limit: 120 requests per minute per IP (`RateLimit-Policy`, `RateLimit` headers); on 429, wait `Retry-After` seconds.
## Rules
- Keep `js/` and `python/` dependency-free and behaviourally identical (same commands, `--json` output, exit codes 0/1/2).
- Validate inputs before any network call; `lire` only reads pages of data-slconsulting.com.
- Never hard-code prices or offers: the API is the source of truth.
- User-facing text stays in French.
- Run `cd js && npm test` and `cd python && PYTHONPATH=src python -m unittest discover -s tests` before proposing a change.
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.