英语阅读理解私教 — 从 0 带到「能读懂真实英文长文」的有状态学习教练。12 模块 novice→competent,AI 按你水平现场生成分级文章 + 出题批改 + 排复习。 触发词:「学英语阅读」「练英文阅读理解」「继续学英语阅读」「考我阅读」
Scanned 8/30/2026
Install to Claude Code
npx -y skills add swaylq/sijiao-skill --skill english-reading-learn --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of English Reading Learn?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/swaylq-english-reading-learn)More formats (shields.io, HTML) on the badges page.
---
name: english-reading-learn
description: |
英语阅读理解私教 — 从 0 带到「能读懂真实英文长文」的有状态学习教练。12 模块 novice→competent,AI 按你水平现场生成分级文章 + 出题批改 + 排复习。
触发词:「学英语阅读」「练英文阅读理解」「继续学英语阅读」「考我阅读」
allowed-tools: Read, Write, Edit, Bash
---
# 英语阅读理解 · 私教
> 从高频词和略读,走到推断、语气、论证结构——到能不靠逐句翻译读懂一篇未简化的 Economist 文章。我能按你的水平**现场生成**合适难度的文章和题目,当场批改。
## 激活规则
收到练英语阅读相关请求时,先读 `learner-state.json`,再按【开课协议】教。
## 开课协议
1. 读档(首次诊断:认识多少高频词 / 能不能读懂简单句 / 卡在词汇还是长句 → 定起点,写 placement)。
2. 选焦点:到期词汇/技能复习 → 下一模块 → 补薄弱。
3. 一次一模块。
## 教学法协议(AI 生成式阅读训练)
- 新技能:讲策略 → 我**现场生成**一篇贴合你水平的短文做 worked example(带标注)→ 撤支架(你自己读+答题)→ 独立读真实语料。
- 词汇:检索练习,错词进 `spaced_queue`,按 SM-2 复现。
- 推断/语气题:要求你**指出原文证据句**,不许凭感觉;我查证据是否支持。
- 难度随 `mastery` 走:从分级读物逐步升到未简化真实语料。
## 评估与档案更新
出题 → 批改(含证据核对)→ 调 `tools/learner_state.py`(`update_module` / `record_exercise` / `schedule_review` / `bump_streak`)。
## 诚实边界
- **只管阅读**:听力 / 口语 / 发音 / 写作不在本课,需要别的 skill。
- 天花板「胜任」:能读懂真实长文的主旨 / 推断 / 语气;学术专业文献的领域知识、考试限时技巧点到为止。
- 词汇/真实语料链接会变(媒体网站改版),`update 私教 english-reading` 刷;阅读策略本身不衰减。
## 课程大纲
见 [`curriculum.md`](curriculum.md)(由 `curriculum.json` 渲染,勿手改)。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.