civitas-learning
Skill14 starsChanged 5 months agoMITView on GitHub
Civitas Learning analytics platform — lets an agent retrieve student risk scores, graduation probability, course success predictions, and intervention outcome tracking.
- Reads credentials
In this repository9 other files it gives its agents.
- bannerSkill
- blackbaud-raisers-edgeSkill
- canvasSkill
- eab-navigateSkill
- handshakeSkill
- salesforce-education-cloudSkill
- servicenowSkill
- slateSkill
- workdaySkill
The file
Files
Civitas Learning
What it is
Civitas Learning is a predictive analytics platform purpose-built for higher education. It ingests SIS, LMS, and financial data to produce student-level risk scores, graduation probability estimates, course success predictions, and schedule optimization recommendations. Academic advisor and retention agents use it to identify at-risk students proactively and measure intervention effectiveness.
When to use this skill
- Pulling a student's graduation probability score and the top risk factors driving it
- Identifying the highest-risk student cohorts in a given term for targeted outreach
- Checking course success probabilities before a student finalizes their schedule
- Retrieving schedule optimization suggestions based on peer cohort outcomes
- Benchmarking institution-level retention rates and tracking intervention outcomes over time
Credentials
This skill authenticates using env vars declared in the frontmatter metadata field. Set these in ~/.openclaw/.env (template: .env.example):
CIVITAS_BASE_URL- Civitas Learning API base URL provided at onboardingCIVITAS_API_KEY- API key issued by Civitas Learning institutional account
Key operations
GET /students/:id/risk— graduation probability score and contributing risk factorsGET /students/:id/courseSuccess— per-course success probability for planned scheduleGET /cohorts/atRisk— ranked list of at-risk students by program and termGET /interventions/:id/outcomes— measured outcome change for a tracked interventionGET /students/:id/scheduleRecommendations— peer-cohort-informed schedule suggestions
Notes
- Risk scores are probabilistic; agents must present them as decision-support signals, not deterministic predictions, and always involve human advisors in intervention decisions.
- Score refresh cadence varies by institution contract (typically daily or weekly); surface the score's
as_of_datealongside the value. - Civitas data contains derived PII; access is governed by institutional data use agreement and FERPA.
- The API requires IP-allowlisting in addition to the API key; ensure the agent's egress IP is registered with Civitas.
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.

