跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
教育

accreditation-mapper

Accreditation and program-assessment documentation for university professors. 4-agent team covering outcome mapping (course LO → program outcome → standard criterion), evidence package assembly, gap analysis, and self-study drafting that never overstates what the evidence shows. Triggers on: accreditation, ABET, AACSB, program outcomes, curriculum map, self-study, assessment report, learning outcomes assessment, continuous improvement report, 专业认证, 工程教育认证, 培养方案, 毕业要求, 课程目标达成, 自评报告, 持续改进, 课程矩阵.

YujxZJCN · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add YujxZJCN/teaching-skills --skill accreditation-mapper

技能说明


name: accreditation-mapper description: "Accreditation and program-assessment documentation for university professors. 4-agent team covering outcome mapping (course LO → program outcome → standard criterion), evidence package assembly, gap analysis, and self-study drafting that never overstates what the evidence shows. Triggers on: accreditation, ABET, AACSB, program outcomes, curriculum map, self-study, assessment report, learning outcomes assessment, continuous improvement report, 专业认证, 工程教育认证, 培养方案, 毕业要求, 课程目标达成, 自评报告, 持续改进, 课程矩阵." metadata: version: "1.0.0" last_updated: "2026-06-10" status: active pipeline_stage: 1 related_skills: - course-designer - teaching-pipeline - teaching-reflector

Accreditation Mapper — Outcomes-to-Standards Documentation Team

Handles the compliance layer above the course: mapping course outcomes to program outcomes to an accreditation standard's criteria, assembling the evidence behind each mapping, finding the gaps, and drafting self-study prose that a review panel can trust. This skill extends the suite's alignment idea one level up — the Alignment Gate checks outcome ↔ assessment ↔ schedule within a course; this skill checks course ↔ program ↔ standard, with the same discipline: claims are verified against artifacts, not accepted because they look complete.

Prime rule: the mapping is the professor's claim; the evidence check is this skill's job. A matrix cell saying "LO2 supports Program Outcome 3" is asserted by the professor — the skill then verifies whether assessment evidence actually exists behind it and labels the cell honestly. A beautiful matrix with hollow cells is documentation theater, and review panels can smell it.

Quick Start

Map my CS 201 outcomes to our ABET student outcomes
帮我把课程目标对应到毕业要求,做工程教育认证的课程矩阵
Assemble the evidence package for our program assessment report
Which of our program outcomes have weak assessment coverage?
Draft the continuous-improvement section of our self-study from last year's changes

Modes

ModeTrigger intentOutput
map"Map my course to the program outcomes / standard"; building a curriculum mapCourse-LO × program-outcome × criterion matrix with professor-claimed strength and per-cell evidence status (CLAIMED / EVIDENCED / HOLLOW)
evidence"Assemble the evidence for…"; preparing for a review visit or assessment reportEvidence package index for a confirmed matrix: what exists (from passport artifacts[] + iteration_history), provenance per item, what's missing
gap"Where is our coverage weak?"; pre-review self-checkGap analysis: criteria with no or weak coverage across the mapped course(s), prioritized remediation suggestions routed to course-designer redesign
self-study"Draft the self-study section…"; continuous-improvement narrativeSelf-study / continuous-improvement section drafted FROM the confirmed matrix + evidence index — every claim footnoted to evidence; thin evidence becomes a hedged claim or an explicit gap statement, never inflation

Mode dispatch rule: evidence, gap, and self-study all consume a confirmed matrix. If none exists, run map first — drafting compliance prose from an unverified mapping is exactly the failure mode this skill exists to prevent. Detect intent in any language.

Does NOT trigger

ScenarioUse instead
Designing or revising the learning outcomes themselvescourse-designer
Analyzing student evaluations or teaching evidence for its own saketeaching-reflector
Program-level curriculum redesign (re-sequencing courses, changing degree requirements)Out of scope — a possible future skill; this skill documents and flags, it does not restructure programs

Agent Team (4)

AgentRole
standards_analyst_agentNormalizes professor-supplied standards and program outcomes into a criteria register: id, verbatim text, evidence type each criterion demands; flags vague criteria for the professor's interpretation
matrix_builder_agentBuilds the mapping matrix: LO rows × outcome/criterion columns, professor-claimed strength (I/R/M), per-cell evidence status computed from the passport; flags hollow cells and over-mapping
evidence_assembler_agentInventories what evidence actually exists per confirmed claim, with provenance; lists what's missing with the cheapest honest fix; never fabricates data
selfstudy_writer_agentDrafts self-study / continuous-improvement prose from the confirmed matrix + evidence index; claim strength capped by evidence status

Workflow (map mode)

Phase 0  INTAKE      — professor supplies the program outcomes AND the standard's
                       criteria as actual current text (verbatim, with version/year).
                       The generic structures in references/accreditation_frameworks.md
                       are scaffolding for orientation only — never a substitute.
                       Missing standard text = [NEEDS PROFESSOR INPUT], full stop.
         🧑 checkpoint: standard version + text confirmed
Phase 1  REGISTER    — standards_analyst normalizes criteria into a register: ids,
                       verbatim text, evidence type demanded (direct / indirect /
                       process), measurability notes, vague-criterion flags
         🧑 checkpoint: register confirmed (incl. professor's reading of vague criteria)
Phase 2  MATRIX      — matrix_builder builds course-LO × program-outcome × criterion
                       matrix; professor claims each cell's strength (Introduce /
                       Reinforce / Master, or the institution's own scale)
Phase 3  VERIFY      — per-cell evidence status from the passport: LO.assessed_by →
                       assessment_plan → artifacts[] — does the evidence chain exist?
                       CLAIMED / EVIDENC
阅读完整来源 ↗