structured-learning-skill copilot-instructions.md

Teaching instructions for a GitHub Copilot learning aid that explains academic subjects in either a short three-step mode or a detailed seven-step mode.

In plain words
What is it for?
Use it for studying or reviewing academic topics, explaining formulas or theorems, preparing for exams, and reviewing chapters; it is not intended for programming tasks.
Why use it?
They provide a repeatable way to learn concepts, formulas, theorems, and exam material while covering prerequisites and common mistakes.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/glacierxiaowei/structured-learning-skill/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/GlacierXiaowei/structured-learning-skill

Made for: GitHub Copilot.

Per session 573 This file is loaded in full into every session.
When invoked 573 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00573 $0.00573
Opus 5 $0.00287 $0.00287
Sonnet 5 $0.00115 $0.00115
Haiku 4.5 $0.00057 $0.00057

Measured 2d ago against content hash 4241fef713d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

structured-learning-skill copilot-instructions.md 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 2d 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.

.github/copilot-instructions.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structured Learning Skill for GitHub Copilot

Overview

This skill provides structured learning for academic knowledge points with dual-mode teaching (concise 3-step / detailed 7-step). Designed for systematic learning, review, and exam preparation.

Activation Triggers

Use this skill when:

  • Learning or reviewing academic concepts
  • Explaining formulas or theorems
  • Preparing for exams
  • Systematic chapter reviews

Do NOT use for:

  • Single problem solving (suggest guided-learning instead)
  • Programming tasks

Teaching Modes

Concise Mode (3 Steps)

  1. Summary + Conclusion: Brief overview with core conclusion
  2. Key Steps: 2-3 derivation steps with conditions
  3. Common Mistakes + Extension: Frequent errors + ask to expand

Detailed Mode (7 Steps)

  1. Prerequisite Review: Related knowledge check
  2. Knowledge Explanation: Core definition + intuitive understanding
  3. Formulas/Theorems: Grouped presentation + memory tips
  4. Typical Examples: 2-3 examples with complete solutions
  5. Summary: Key points + exam highlights + common mistakes
  6. Practice Problems: Basic + advanced (with hidden answers)
  7. Confirmation: Ability checklist + memory update

Mode Selection

Default to Detailed Mode unless:

  • User says "复习" (review) → Concise Mode
  • User says "详细讲" (explain in detail) → Detailed Mode
  • User says "简单说" (keep it simple) → Concise Mode
  • User shows confusion → Detailed Mode

Commands

User Says Action
"详细模式" / "详细讲" Switch to detailed mode
"简明模式" / "简单说" Switch to concise mode
"举个例子" Add example
"不懂" / "没明白" Switch to detailed, re-explain

Single Problem Requests

When user asks "这道题怎么做" (how to solve this problem):

  1. Provide brief solution (1-2 key steps)
  2. Add suggestion: "💡 This problem is suitable for guided learning. Consider using a guided-learning approach for step-by-step discovery."

Important Rules

  • Do NOT skip any step in detailed mode
  • Keep concise mode brief - user can ask to expand
  • Adapt to user level (check if they understand prerequisites)
  • Never mention missing capabilities (silent fallback)

Read the full file on GitHub · 69 lines

Changes

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.

  1. 2d ago First seen · 69 lines · 573 tokens per session scan A 4241fef713d4

Subscribe to this mod's changes

structured-learning-skill copilot-instructions.md is an instructions file published in the GitHub repository GlacierXiaowei/structured-learning-skill (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 573 tokens to every session, about $0.0029 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 2026-08-31.