菜单
Installs Ollama, sets up local models, and deploys a custom system prompt. Invoke when user wants offline/local LLM setup or to run a model with a specific prompt.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Read MEMORY.md at session start and apply [LEARN:tag] corrections; when the user corrects you, append [LEARN:category] wrong → right to MEMORY.md. Use when starting work on this project or when the user gives a correction to remember.
Run holistic pedagogical review on lecture slides. Checks 13 patterns: narrative arc, notation density, pacing, motivation before formalism, worked examples, fragment reveals, box hierarchy. Use when the user asks for pedagogy or teaching-quality review of slides.
Run proofreading on lecture files (.tex or .qmd). Checks grammar, typos, overflow, consistency, and academic quality. Produces a report only; does not edit files. Use when the user asks to proofread slides or check grammar/typos in lecture content.
Adversarial QA comparing Quarto slides to Beamer benchmark. Run critic (find issues) then fixer (apply fixes); repeat until approved or max 5 rounds. Use when the user asks to QA Quarto vs Beamer or validate a lecture translation.
Review R scripts for code quality, reproducibility, and domain correctness. Checks set.seed, paths, structure, figure quality, and conventions. Use when the user asks to review R code or check scripts in scripts/R or Figures.
Run combined multi-dimensional slide review: visual audit, pedagogy review, and proofreading (and optionally TikZ parity). Use when the user asks for full or comprehensive slide review before a milestone.
| name | ollama-local-setup |
| description | Installs Ollama, sets up local models, and deploys a custom system prompt. Invoke when user wants offline/local LLM setup or to run a model with a specific prompt. |
Use this skill when the user asks to install a local model, avoid downloading at runtime, or deploy a system prompt for a chatbot.
ollama --version
ollama --version
ollama pull llama3.2:1b
If you already have the model files, copy them into the Ollama model directory.
macOS:
models folder into:
~/.ollama/modelsWindows:
models folder into:
%USERPROFILE%\.ollama\modelsThen verify:
ollama list
Modelfile:FROM llama3.2:1b
SYSTEM """
You are an academic presentation coach for PhD students. Help them craft clear, rigorous, and engaging research talks.
Focus on:
1. Core contribution and novelty
2. Research question, methods, and evidence
3. Slide structure and narrative flow
4. Concise wording and visual clarity
5. Anticipating questions and limitations
Ask one focused question at a time. Keep responses concise, actionable, and tailored to the student's field and audience.
"""
ollama create phd-presentation-coach -f Modelfile
ollama run phd-presentation-coach
ollama serve
API endpoint:
http://localhost:11434/api/chatollama run phd-presentation-coach "ok"