Ohio state api

Skill sichengchen/ohio-state-agent-skills/ohio-state-api

Get public data from The Ohio State University Content APIs (content.osu.edu) across campus services (bus, buildings, dining, events, academic calendar, libraries, rec sports, parking, directory, student orgs, athletics, food trucks, BuckID merchants). Use when you need OSU campus data, want to build an OSU data feature, or need a repeatable way to fetch/inspect OSU API JSON.From its SKILL.md

Install

npx -y skills add sichengchen/ohio-state-agent-skills --skill ohio-state-api

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.1 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

What to use

Option A: Direct HTTP fetch (quickest)

Use the bundled fetch helper to pull JSON from OSU Content APIs.

Fetch by full URL:
- node ohio-state-api/scripts/osu-fetch.mjs https://content.osu.edu/v2/api/v1/dining/locations
Fetch by service + path:
- node ohio-state-api/scripts/osu-fetch.mjs --service dining --path /locations

Note: --path can be passed with or without a leading / (both work).

If the response is large, add --extract <dot.path> (e.g. --extract data) to print only a subtree.

Option A2: curl (no Node required)

If you just want raw JSON and have curl available, reference ohio-state-api/references/OSU_API.md:

Full URL:
- curl -sS -H 'accept: application/json' 'https://content.osu.edu/v2/api/v1/dining/locations'
With query params:
- curl -sS -H 'accept: application/json' 'https://content.osu.edu/v2/classes/search?q=cse&p=1'

Optional: pipe to jq for readability:

curl -sS -H 'accept: application/json' 'https://content.osu.edu/v2/api/v1/dining/locations' | jq .

Option B: MCP server (best for MCP-compatible clients)

This skill bundles the original MCP server under ohio-state-api/mcp-server/.

Build it:

cd ohio-state-api/mcp-server && npm install && npm run build

Then configure your MCP client to run:

command: node
args: ["/ABSOLUTE/PATH/TO/ohio-state-api/mcp-server/build/index.js"]

After it’s running, use tools like:

get_bus_routes, get_bus_vehicles
get_buildings, search_buildings, get_building_details
get_dining_locations, get_dining_menu
get_campus_events, get_events_by_date_range
search_classes
get_parking_availability

(See ohio-state-api/mcp-server/README.md and the tool definitions in ohio-state-api/mcp-server/src/ for the full list.)

Recommended workflow for “get OSU data” requests

Identify the service area (dining, bus, buildings, events, etc.).
Prefer a list/search endpoint first, then follow IDs into detail endpoints.
For time-based data, always include both:
- the query window (absolute dates/times), and
- the retrieval timestamp.
When returning data to a user, summarize key fields and attach the raw JSON as an artifact when possible.

Common base URLs (public)

These are used by the bundled MCP server and work with osu-fetch.mjs:

Athletics: https://content.osu.edu/v3/athletics
Bus: https://content.osu.edu/v2/bus
Buildings: https://content.osu.edu/v2/api
Calendar: https://content.osu.edu/v2/calendar
Classes: https://content.osu.edu/v2/classes
Dining: https://content.osu.edu/v2/api/v1/dining
Directory: https://content.osu.edu
Events: https://content.osu.edu/v2
Food trucks: https://content.osu.edu/v2/foodtruck
Library: https://content.osu.edu/v2/library
Merchants: https://content.osu.edu/v2
Parking: https://content.osu.edu/v2/parking/garages
Rec sports: https://content.osu.edu/v3
Student orgs: https://content.osu.edu/v2/student-org

Examples (copy/paste)

Dining locations:
- curl -sS -H 'accept: application/json' 'https://content.osu.edu/v2/api/v1/dining/locations'
Parking availability:
- curl -sS -H 'accept: application/json' 'https://content.osu.edu/v2/parking/garages/availability'
Buildings “search” (filter client-side with jq):
- curl -sS -H 'accept: application/json' 'https://content.osu.edu/v2/api/buildings' | jq -r '.data.buildings[] | select((.name // \"\") | test(\"union\";\"i\")) | \"\\(.buildingNumber)\\t\\(.name)\"'

Extra reference

API reference: ohio-state-api/references/OSU_API.md

What ships with it: 24 files

93.4 KB alongside SKILL.md, 17 of them executable

Gives 0 of the 12 instructions most education skills give in ~1.0k tokens

Counted across 169 of the 171 authors here whose files we hold, read 2026-08-07

Search for existing resources before creating new onesin 7 of 169, across 3 files
Check tool responses for errors before proceedingin 7 of 169, across 3 files
Reduce request frequency on rate limit errorsin 7 of 169, across 3 files
Confirm connection status is ACTIVE before running workflowsin 7 of 169, across 3 files
Execute prerequisite steps first in workflowsin 7 of 169, across 3 files
Handle pagination by fetching until exhaustedin 7 of 169, across 3 files
Re-authenticate if the connection expiredin 6 of 169, across 2 files
Always call RUBE_SEARCH_TOOLS first to get schemasin 6 of 169, across 2 files
Pass strictly schema-compliant tool argumentsin 6 of 169, across 2 files
Run the skill generator if the shared file is missingin 6 of 169, across 3 files
Create the coursein 5 of 169, across 3 files
List enrolled studentsin 5 of 169, across 3 files

Said here and by no other author read

use list endpoints before detail endpoints
include query window and retrieval timestamp for time data
summarize key fields for the user
attach raw JSON as an artifact
identify the needed service area first

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.