TS Evals — Development skill for Claude Code
TS teaching-reflector eval-analysis mode — student evaluation analysis.
How to install TS Evals
Installs to ~/.claude/skills/yujxzjcn-teaching-skills-ts-evals/SKILL.md
mkdir -p ~/.claude/skills/yujxzjcn-teaching-skills-ts-evals && curl -fsSL https://raw.githubusercontent.com/YujxZJCN/teaching-skills/HEAD/commands/ts-evals.md -o ~/.claude/skills/yujxzjcn-teaching-skills-ts-evals/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What TS Evals does
description: TS teaching-reflector `eval-analysis` mode — student evaluation analysis
Trigger the `teaching-reflector` skill in `eval-analysis` mode. Thematic coding of comments with prevalence and verbatim exemplars; scalar reading with mandatory bias and small-N caveats; prioritized changes.
Mode reference: `MODE_REGISTRY.md`. Skill entry: `teaching-reflector/SKILL.md`.
Alternatives in Development
- Quick Eval — Quick job evaluation 473 ★
- Write Teaching Chapter — Write bilingual (CN+EN) Claude Code source code teaching chapters 386 ★
- Live Eval And Cost — Live Evaluation & Cost Analysis — GenAI IDP Accelerator 295 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Blickwechsel
A change of perspective on your own teaching. Audits a lecture you already teach from the student's point of v
Eval Advisory
Eval advisory is a skill for planning, reviewing, and developing your evals.
Agent Evals Playground
A shopping agent, a labelled eval suite, and the wiring to score it against a real cluster instead of a fixtur
Skill Eval Loop
Agent Skill: harden another skill from its automatic agent evals. Score every Claude Code, Codex and Gemini CL
Eval Skill
/eval-skill — Six-Dimension Evaluation
Vibememo Eval
Periodic VibeMemo evaluation and capture. Runs on a loop (default 30m) to assess whether significant decisions
Related Agents
AI Eval Designer
Use this agent to design a risk-tiered evaluation set for an AI feature. Trigger when the user says "design ev
Instructor
Elite AI instructor agent (Dr. Kiran). Use for training design, curriculum development, coaching white-collar
Eval Failure Analyzer
Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a skills-works