Borrowing it
Nothing to install: this file belongs to whtoo/How_to_implment_PL_in_Antlr4. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/whtoo/How_to_implment_PL_in_Antlr4/main/.claude/skills/tech-blogger/SKILL.mdgit clone --depth 1 https://github.com/whtoo/How_to_implment_PL_in_Antlr4Wrote 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/whtoo/how_to_implment_pl_in_antlr4/tech-blogger)<a href="https://agentmods.dev/skills/whtoo/how_to_implment_pl_in_antlr4/tech-blogger"><img src="https://agentmods.dev/badge/skills/whtoo/how_to_implment_pl_in_antlr4/tech-blogger/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/whtoo/how_to_implment_pl_in_antlr4/tech-blogger"><img src="https://agentmods.dev/badge/skills/whtoo/how_to_implment_pl_in_antlr4/tech-blogger.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 | $0.00050 | $0.03645 |
| Opus 5.5 | $0.00020 | $0.01458 |
| Sonnet 5.5 | $0.00010 | $0.00729 |
| Haiku 4.5 | $0.00005 | $0.00364 |
Grade A, and why
tech-blogger 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 1mo 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术图书写作专家 (Tech Blogger Agent)
🎯 垂直职责
单一职责: 基于三层Prompt架构,系统化生成《AI Context Engineer 视角下的现代编译器实战》技术书籍章节内容。
📚 三层Prompt架构 (Three-Layer Prompt Architecture)
第1层:系统级提示词 (SYSTEM_PROMPT.md)
位置: book/SYSTEM_PROMPT.md
作用: 定义技术写作代理的角色、写作原则、结构要求
核心内容:
- 角色设定: 高级技术写作专家 + 编译器工程师 + AI 工程师
- 写作原则: 双线叙事(人类工程师线 + AI协作线)
- 目标读者: 1–5年Java工程师,有AI编程助手使用经验
- 技术栈约束: Java 21, ANTLR4 4.13.2, Maven 3.8+, JUnit 5
- 硬性要求: 每章必须包含6个强制小节(概述→动机→技术→AI→练习→小结)
第2层:章节级模板 (CHAPTER_TEMPLATE.md)
位置: book/CHAPTER_TEMPLATE.md
作用: 提供完整的章节结构模板,包含所有占位符
核心结构:
- 章节写作任务
- 本章基本信息(标题、模块、读者、EP范围等)
- 内容结构要求(6个强制小节)
- 章节内容检查清单(作者自检)
关键占位符:
{chapter_title}- 章节标题{module_title}- 模块标题{target_reader}- 读者特征{prerequisites}- 前置知识{ep_range}- 对应EP范围{previous_chapters}- 前一章{next_chapters}- 后一章{learning_goal_1/2/3}- 学习目标
第3层:章节实例提示词 (CHAPTER_PROMPT_EXAMPLES.md & assets/prompts/)
位置:
book/CHAPTER_PROMPT_EXAMPLES.md- 示例章节提示词(第1章、第12章)book/assets/prompts/chapterXX_prompt.md- 各章具体提示词
作用: 填充占位符后得到的具体章节Prompt,可直接发送给技术写作代理
🔗 关系图
→ ep-navigator (识别EP范围和技术上下文) → compiler-dev (理解编译器技术细节) ← document-writer (实际执行章节内容生成)
📖 书籍结构概览
5大模块,21个章节
模块 1: 基础语言与解释器 (EP1–EP12) - 第1-5章
模块 2: 从解释到编译 (EP13–EP16) - 第6-9章
模块 3: 现代编译器架构 (EP17–EP18R) - 第10-12章
模块 4: 中间表示与优化 (EP19–EP20) - 第13-16章
模块 5: 高级优化与AI协作 (EP21) - 第17-20章
双线叙事要求
人类工程师线:
- 正常编译器构造实践(概念 + 代码 + 实验)
- 从基础解析器到研究级优化的完整路径
AI协作线:
- 如何设计上下文(Context),让AI安全、高效地参与
- Prompt模板、验证策略、回滚方案
- AI应该做/不该做的明确边界
🚀 快速工作流
方法1:使用现有章节提示词(推荐)
# 1. 查看所有可用章节提示词
ls book/assets/prompts/
# 2. 阅读第N章提示词
cat book/assets/prompts/chapter02_prompt.md
# 3. 组合系统提示词 + 章节提示词
cat book/SYSTEM_PROMPT.md book/assets/prompts/chapter02_prompt.md > chapter02_full.md
# 4. 发送给技术写作代理(document-writer)
# 将chapter02_full.md内容发送给document-writer agent
方法2:创建新章节提示词
# 1. 复制章节模板
cp book/CHAPTER_TEMPLATE.md book/assets/prompts/chapterXX_prompt.md
# 2. 填充占位符(参考BOOK_IMPLEMENTATION_PLAN.md)
vim book/assets/prompts/chapterXX_prompt.md
# 3. 填充示例:
# {chapter_title}: 第2章:表达式、运算与解释器基础
# {module_title}: 模块 1:基础语言与解释器(EP1–EP12)
# {target_reader}: 会Java、有Maven使用经验...
# {prerequisites}: Java基础语法、命令行、基本Git操作
# {ep_range}: EP3–EP4(表达式求值、访问者模式、变量内存)
# {previous_chapters}: 第1章:为人和AI搭建最小工作台
# {next_chapters}: 第3章:语句与控制流
# {learning_goal_1}: 理解表达式求值的核心机制
# {learning_goal_2}: 掌握访问者模式的设计和应用
# {learning_goal_3}: 能够在编译器中复用表达式求值逻辑
# 4. 组合并发送(同方法1)
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.
- 1mo ago First seen · 337 lines · 50 tokens per session scan A 670b98e16212
tech-blogger is a skill published in the GitHub repository whtoo/How_to_implment_PL_in_Antlr4 (34 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 50 tokens to every session and 3,645 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
cangjie-skill
A process for turning a book, course, podcast, interview, long video, or other long material into reusable instructions for an AI agent. It extracts methods and principles, checks them, and packages them as skills.
scaffold-exercises
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
naval-almanack
A reference guide for applying ideas from The Almanack of Naval Ravikant, a book about wealth, work, happiness, judgment, and long-term thinking. It routes questions to the relevant topic guidance and notes when professional help is needed.
reading-metaskill
A reading and learning guide based on building a regular reading habit, choosing books, and understanding difficult subjects through original works and explanation.
life-meaning
A guide for reflecting on personal purpose, effort, suffering, and mortality when life feels empty or directionless.
principal-agent
A Chinese-language guide based on the principal-agent idea: the person who owns a decision or its result may have different incentives from someone acting on another person's behalf. It applies this lens to jobs, companies, and partnerships.