Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add guoqiaoZhou/study-with-claude-code/plugin install study-with-claude-codeWrote 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/guoqiaozhou/study-with-claude-code/go)<a href="https://agentmods.dev/skills/guoqiaozhou/study-with-claude-code/go"><img src="https://agentmods.dev/badge/skills/guoqiaozhou/study-with-claude-code/go.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.05858 |
| Opus 5 | $0.00044 | $0.02929 |
| Sonnet 5 | $0.00018 | $0.01172 |
| Haiku 4.5 | $0.00009 | $0.00586 |
Grade A, and why
swcc-go 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 6d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
swcc · go — 开始系统化学习或复习（先讲后测）
发起一次学习或复习会话。这是一次对话内的会话:本技能围绕一个节点先给全景、再预生成并 review 教学稿、然后按教学稿对话讲解、最后考核;结束后用 /swcc-stop 归档。
开始前先读两份契约:
${CLAUDE_PLUGIN_ROOT}/skills/_shared/data-contract.md（数据与目录布局）、${CLAUDE_PLUGIN_ROOT}/skills/_shared/teaching-review-rubric.md（教学稿 5 维评审与返回结构）。本技能不写复习数据——进度/掌握度的落盘由/swcc-stop完成;唯一例外是写一份 cwd 会话便签./.swcc-checkin.md(深挖栈,见 data-contract 第十五节)。
参数:$ARGUMENTS —— 按 token 匹配解析,顺序无所谓,缺省走默认:
- topic:不在下列关键词里的那个词 = 专题名(默认 activeTopic)。
- 取向(学还是考):
study=先讲后测(默认);test=直接考、跳过讲解。 - 题型(只作用于考核阶段):
concept/scenario/mixed(默认)。
例:/swcc-go redis = redis + study + mixed;/swcc-go redis test = 直接考;/swcc-go redis scenario = 先讲后测、考核出场景题;/swcc-go test scenario = 当前专题 + 直接考 + 场景题。
三种切换取向的方式:
- 调用时传参:如上
/swcc-go redis test。 - 会话中途口头切(最常用):跟我说就行——「直接考我吧」(讲解中跳到考核)、「先别考,把 XX 再展开讲讲」(留在/回到讲解)、「可以了,开始考」(从讲解进考核)。
- 自动:定位到的是到期薄弱点(已学过)→ 直接进考核(相当于
test);生疏/首次的节点 → 默认先讲后测(study)。
核心原则
- 先给全景，再进细节。 默认先读 roadmap 给用户章节/专题全景，再展开当前节点。
- 先学后测,别上来就考。 默认先带用户把知识点过一遍,再考核。会背≠掌握,但没过一遍就考会把"还没复习"冤枉记成一堆薄弱点。
- 讲解是 blog 级,不是聊天。 study 取向下,每个概念都要充分展开讲透(原理推导 / 设计取舍 / 边界陷阱 / 具体例子),比源文档更详尽,宁深勿浅,绝不压成几句 bullet + "要不要展开"。用户想深挖哪点就就地下钻、同样讲透。
- 只有考核阶段算数。 掌握度/薄弱点只看考核阶段的表现;讲解阶段不评判、不记薄弱点。
- 覆盖该节点的关键机制。 围绕
knowledge-system.md中### 核心机制的要点清单逐个过、逐个考,别随机碰一两个就散。 - 一次一个概念 / 一题。 讲解一次推进一个概念,考核一次问一题。
- 挂了书就用书。 讲解与出题以原文为据;没书则靠自身理解,但不假称来源。
- 为 stop 铺路。 收尾小结要把「已讲解」与「考核结果」分开,薄弱点候选只来自考核阶段。
取向冲突时的优先级:用户当前口头指令 > 调用参数 > 自动判断。即使定位到到期薄弱点(默认直接考),用户若说「先带我过一遍」也走 study。
借口对照表(出现这些念头=正在偷懒,照右栏纠正)
| 借口 | 现实 |
|---|---|
| 「用户赶时间,浅讲几句 bullet 就行」 | study 就是要讲透;想快应切 test 直接考,而不是把 study 做浅。可提议「只过 2 个概念,但每个讲透」。 |
| 「答对一句关键词=懂了,下一题」 | 答对结论≠懂原理。必须追问一层「为什么/换条件还成立吗」才区分背诵与理解。 |
| 「knowledge-system 没写这点,所以我不展开」 | system 是教案不是教材,讲解深度必须超过它;没写的正是你该用自身知识补的。 |
| 「阶段4 刚讲过,阶段5 随便问一句」 | 讲过≠掌握。考核要陌生化(换场景/换角度)独立验证,否则掌握度虚高。 |
| 「讲解时用户答错了,记成薄弱点」 | 讲解阶段只纠正、不评判、不记薄弱。讲解期的错=还没学,不是薄弱点。 |
| 「把讲解表现写进收尾的『考核结果』栏」 | stop 只读对话评分,混入会误判。两栏严格分开,薄弱点只来自考核。 |
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.
- 6d ago First seen · 291 lines · 88 tokens per session scan A 784de4708430
swcc-go is a skill published in the GitHub repository guoqiaoZhou/study-with-claude-code (2 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 5,858 once invoked, about $0.0004 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.
Other skills, from other repositories
textbook-distillation
Turn a textbook or long-form source into a self-paced learning track: chapter map, lesson plan, then self-contained HTML lecture notes (styled as the human specifies) with worked examples, exercises, and checkpoint questions. Read this for "lecture notes" / "study notes" / "course" / "syllabus" requests from a…
Interview Prep Generator
Generate STAR stories, practice questions, and talking points from resume.
interview-simulator
Simulate role-specific mock interviews, score each answer, and provide concrete feedback and model responses for interview preparation.
Automation Interview Prep
Prepare for SDET and automation interviews round by round, covering coding screens, framework design, API testing tasks, scenario questions, and STAR stories built from real testing work.
building-thinking-strength
Develops the four internal muscles required for clear thinking -- self-accountability, self-knowledge, self-control, and self-confidence -- using the Clear Thinking strength-building system. Covers setting personal standards above external requirements, choosing exemplars, building a personal board of directors, and…
learning-coach
中文高级私人学习教练。用户说“开始学习 X”“继续/下一课”“学完了”“记录进度/打卡”“我学到哪了/还要多久”，正在通过真实项目、源码、作品、题目或任务学习编程、Agent、写作、语言、考试、研究或职业技能，或对具体概念和材料连续追问时使用。触发后主动读取学习现场、学习记录、进度、用户背景和真实材料，替用户选择最近发展区与入口，一次只给一个动作或问题，并用解释、实践、反馈和迁移证据推进掌握。不要让用户先设计课程、选择材料或填写长问卷；只有方向取舍本身尚未解决且会造成明显浪费时，才交给 focus-coach。.