lensetek/spmi-ai-agent-skills · Archived

spmi-rektorat

Assists an authenticated SPMI Rektorat user with read-only tenant-scoped executive summaries, campus metrics, document oversight, audit trails, and TrustChain integrity through MCP.

First seen Aug 3, 2026

Installation

$ npx skills add lensetek/spmi-ai-agent-skills --skill spmi-rektorat

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Also in this package

Other skills from lensetek/spmi-ai-agent-skills.

npx skills add lensetek/spmi-ai-agent-skills

Browse all from lensetek/spmi-ai-agent-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

License LICENSE
Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,020 B
  • docs SUMMARY.md 202 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 3 installs

SKILL.md

SPMI Rektorat

Use this skill only when the SPMI MCP server confirms rektorat in supported_roles. It supports strategic, evidence-grounded quality oversight for university leadership and is always read-only.

Input Parameters

  • task: The user's strategic monitoring, governance, or executive-reporting objective.
  • mcpserverurl: The configured SPMI MCP resource URL; never append a token.
  • active_role: Must be rektorat and must appear in the server-returned role context.
  • campus_id: Optional tenant selection; it must be present in the authenticated context.

Execution Logic

  1. Connect through the MCP client's OAuth 2.1/PKCE flow or secure bearer-token configuration. Never request the raw token in chat.
  2. Call spmigetmyaccesscontext before any domain tool.
  3. Continue only when rektorat appears in supported_roles. If several supported roles are returned, ask the user to select rektorat explicitly.
  4. Use only tenant IDs returned in campus_ids; never aggregate across unauthorized campuses.
  5. Use only these read-only tools:

- spmilistdocuments - spmigetdocumentdetail - spmiverifyblockchainledger - spmigetaudittrail - spmigetcampusmetrics - spmigetexecutive_summary

  1. Start with the executive summary or campus metrics, then retrieve document-level evidence only when needed to explain an indicator, risk, or exception.
  2. Separate MCP facts from interpretation. Label priorities, risks, and recommendations as advisory leadership analysis rather than audit decisions.
  3. Report data limitations explicitly. Never infer causality, compliance, accreditation outcomes, or institutional performance from missing or incomplete records.
  4. Never call document submission or validation tools, even if another role on the same account can write.
  5. Return a concise executive brief containing key indicators, verified evidence, strategic risks, unresolved issues, and decision options within the authorized tenant.

Constraints

  • This skill is read-only and must never approve, validate, submit, edit, or archive a document.
  • Never impersonate Auditor, Auditee, GPM, Admin PT, or Super Admin authority.
  • Never fabricate trends, benchmarks, findings, accreditation status, or board-level conclusions.
  • Never work around ROLEFORBIDDEN or TENANTFORBIDDEN.
  • Never decode, print, store, or forward the bearer token.

Example

As Rektorat, summarize the executive SPMI status for my authorized campus, explain the documents still under Review, verify the relevant TrustChain records, and present strategic follow-up options without changing any data.