manage-job-board
Skill2 starsChanged 28 days agoMITView on GitHub
Operate a Cavuno job board through the Cavuno MCP server: list, create, update, publish, pause and expire jobs, and manage companies. Use when the user asks to work on jobs, listings, employers or board operations in Cavuno.
In this repositoryOne other file it gives its agents.
- publish-blogSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 18
Call search to find the API path, method and request schema for the jobs or companies operation you need.
- Distinctive: line 20
Run the operation with whichever tools you have:
- Very specific: line 21
If an execute tool is available, call cavuno.request({ method, path, body?, query?
- Distinctive: line 30
Look up the records you will change.
- Distinctive: line 33
After a write, read the record or list again to confirm the new state, and report IDs and titles.
- Distinctive: line 38
Never invent job or company IDs.
- Distinctive: line 39
Prefer creating a draft and then publishing over publishing immediately while the user is iterating.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Manage a Cavuno job board
Prerequisites
- Cavuno MCP connected with OAuth or an API key, either at
https://mcp.cavuno.com/mcpor athttps://mcp.cavuno.com/mcp/connector. - Work on the board the user is signed into unless they name another.
Calling the API
The two endpoints expose the same Cavuno API through different tools.
- Call
searchto find the API path, method and request schema for the jobs or companies operation you need. - Run the operation with whichever tools you have:
- If an
executetool is available, callcavuno.request({ method, path, body?, query? })inside it. Never put Authorization headers in that code. - Otherwise use
readfor GET requests,queryfor the read-only search operations (such as/jobs/searchand/companies/search),createfor POST,updatefor PUT and PATCH, anddeletefor DELETE.
- If an
Workflow
- Look up the records you will change; list or search before writing.
- Confirm destructive actions (delete, expire, bulk pause) with the user before running them.
- After a write, read the record or list again to confirm the new state, and report IDs and titles.
Safety
- Never invent job or company IDs; look them up first.
- Prefer creating a draft and then publishing over publishing immediately while the user is iterating.
- Respect plan limits; check usage if bulk operations fail.
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.

