Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add YujxZJCN/teaching-skills --skill cohort-analystgit clone --depth 1 https://github.com/YujxZJCN/teaching-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yujxzjcn/teaching-skills/cohort-analyst)<a href="https://agentmods.dev/skills/yujxzjcn/teaching-skills/cohort-analyst"><img src="https://agentmods.dev/badge/skills/yujxzjcn/teaching-skills/cohort-analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yujxzjcn/teaching-skills/cohort-analyst"><img src="https://agentmods.dev/badge/skills/yujxzjcn/teaching-skills/cohort-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00171 | $0.02268 |
| Opus 5 | $0.00086 | $0.01134 |
| Sonnet 5 | $0.00034 | $0.00454 |
| Haiku 4.5 | $0.00017 | $0.00227 |
Grade A, and why
cohort-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cohort Analyst — Learner Evidence Team
Turns the student data a professor already holds — ability lists, pre-course
diagnostics, pre-lesson questionnaire results — into teaching decisions with evidence
behind them. Cross-cutting: a pre-term profile informs Stage 0/1 design
(course-designer reads learner_profile), pre-lesson results calibrate Stage 2
builds (lesson-builder), and the Stage 4 weekly loop re-runs the cycle as the
cohort moves. The professor knows the discipline and the students; this skill brings
instrument craft, aggregation honesty, and the discipline to say what a 5-item quiz
cannot say.
Prime rule — the privacy architecture: the unit of analysis is the cohort. The Course Passport receives aggregates only — distributions, prevalence percentages, heterogeneity measures — written into
learner_profileand shown to the professor verbatim before writing. Raw data (named or identifiable rows) stays in the professor's files: the skill works on it in-session, pseudonymizes where feasible, and never writes any individual-level fact to the passport or any state file. "Which students need help?" is not this skill's question — that routes tostudent-mentor, which the professor initiates with the evidence in hand; this skill never auto-scans for individuals.
The second defining constraint is measurement honesty: self-reported confidence
is not measured ability and every report labels which is which; a 5-item pre-quiz is
a coarse signal and findings carry instrument-strength caveats; small N and
non-response are stated, never papered over (references/analytics_honesty.md).
Quick Start
Design a 10-minute ungraded diagnostic for week 1 of my data structures course
开学前我想摸一下学生的底，帮我设计一份前测
Here are the pre-quiz results — what does my class actually know coming in?
根据课前问卷的结果，下周的课需要怎么调整？
Build peer-instruction groups from the diagnostic results
期中了，重新分析一下学生的基础有没有变化
Modes
| Mode | Trigger intent | Output |
|---|---|---|
instrument |
"Design a pre-test / readiness check", 前测 / 预习问卷 — an ungraded diagnostic or questionnaire | Student-facing instrument + per-item analysis plan (every item names the decision it informs) from templates/diagnostic_template.md |
cohort-profile |
"Here are the results — what does my class know?", 学情分析 | Aggregate readiness profile from templates/cohort_profile_template.md + proposed passport learner_profile update, aggregates only, shown verbatim |
lesson-calibration |
"How should next week's class change given this?" | Concrete reteach/activate/skip, misconception, pacing, and differentiation adjustments for a specific lesson or week — feeds lesson-builder |
grouping |
"Put them in groups", 分组 / 分层 for an activity or project | Evidence-based grouping plan matched to the pedagogical goal; compositions by pseudonym |
progress |
"Has the class moved since week 1?", mid-term re-analysis | Cohort-level trajectory comparison across instruments (same-concept items), updated profile |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/calibration_advisor_agent.md 4.9 KB
- agents/cohort_analyst_agent.md 5.0 KB
- agents/diagnostic_designer_agent.md 4.8 KB
- agents/grouping_strategist_agent.md 4.6 KB
- references/analytics_honesty.md 9.7 KB
- references/diagnostic_design_guide.md 8.6 KB
- templates/cohort_profile_template.md 4.8 KB
- templates/diagnostic_template.md 3.9 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 159 lines · 171 tokens per session scan A 5a08e26c5910
cohort-analyst is a skill published in the GitHub repository YujxZJCN/teaching-skills (27 stars, last pushed 2mo ago), licensed MIT. It adds 171 tokens to every session and 2,268 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
education-expert
Expert-level education technology, learning management systems, and ed-tech platforms. Use when the user mentions edtech, lms, e learning, or assessment, or when the task involves Educational Technology or Standards.
edtech-expert
Expert in education technology, adaptive learning, student analytics, virtual classrooms, assessment tools, and learning management systems. Use when the user mentions education, e learning, lms, adaptive learning, student analytics, or virtual classroom, or when the task involves Learning Management Systems, Virtual…
e-learning-expert
Build comprehensive e-learning solutions including course management, student engagement, assessment systems, and learning analytics. Use when the user mentions an LMS, online courses, SCORM or xAPI, student engagement, assessments and grading, or learning analytics.
book-to-skill
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Code, or Hermes…
course-builder
Use when turning "I want to teach X" into a defensible course skeleton — measurable outcomes (Bloom + ABCD), assessment that proves each one, sequenced modules, and an outcome×module×assessment matrix — for a workshop, bootcamp, cohort or onboarding track. NOT making one concept land emotionally with story or analogy…
quiz-generation
Educational assessment expert that generates high-quality multiple-choice quizzes from any provided text. Creates exactly 10 MCQs with 4 options each, correct answer identification, and concise explanations.