Borrowing it
Nothing to install: this file belongs to xi-kari/crossframe-skill. 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/xi-kari/crossframe-skill/main/.claude/skills/crossframe-teach/SKILL.mdgit clone --depth 1 https://github.com/xi-kari/crossframe-skillWrote 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/xi-kari/crossframe-skill/crossframe-teach)<a href="https://agentmods.dev/skills/xi-kari/crossframe-skill/crossframe-teach"><img src="https://agentmods.dev/badge/skills/xi-kari/crossframe-skill/crossframe-teach.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 | $0.00031 | $0.01318 |
| Opus 5 | $0.00015 | $0.00659 |
| Sonnet 5 | $0.00006 | $0.00264 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
crossframe-teach 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 8d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrossFrame Teach
本 skill 不独立触发。 所有 CrossFrame 任务统一从
crossframe-suite入口调度。用户无需直接调用本 skill；suite 根据路由规则在需要时自动加载。
如果概念教学要连接文章写作、案例沉淀、读书研究或输出评审，先读取 ../crossframe-suite/SKILL.md 做总调度；本 skill 只负责教学解释、误读边界和练习。
轻入口原则
中文是权威语义。CrossFrame Teach 只是教学入口，不重写、不替代、不压缩 canonical CrossFrame。
每次触发后先读取相邻 canonical 材料：
../crossframe/SKILL.md../crossframe/references/read-routing-map.md- 若概念教学触发高责任、公共制度、亲密关系、长期演化、框架治理、AI 现实验证、弱信号/不透明、无法退出、工具化、隐喻/来源透明或文章输出，追加读取
../crossframe/references/continuity-bundles.md，并按需使用../crossframe/worksheets/source-continuity-check.md；未完成联读时只能降档。 - 复用
../crossframe/templates/read-state-capsule.md规定的v5-read-state-capsule，并在高责任、公共、AI/过程性产物、生命周期、无法退出主体或文章输出场景执行../crossframe/worksheets/source-anchor-integrity-check.md。如果胶囊缺失，回到../crossframe/SKILL.md补齐；本 skill 不重新发明源路由。 - 若本 skill 产生新的中心命题、机制句、高风险概念判断、公共定性、行动建议、案例复用判断、组织处置建议或可成文材料，必须把这些内容作为
claim ledger delta交回../crossframe/templates/claim-ledger.md与../crossframe/worksheets/claim-ledger-check.md。本 skill 不得新增未登记判断；若无法登记claim_id、判断档位、行动上限、撤回条件和发布边界，只能删除、降档，或标为“本文推断 / 表达转译 / 外部思想映射”。
不要把 canonical 全文复制进回答。只按本次概念需要读取 canonical 的协议、术语保真材料、概念卡或模板；教学表达使用本 skill 的轻量协议和模板。
必读资源
- 读取
protocols/teach-protocol.md，确定本次是概念课、误读纠偏、现实信号训练，还是练习题生成。 - 读取
references/teaching-fidelity.md，防止术语堆砌、解释过短失真、道德化和漏练习。 - 需要成稿时使用
templates/concept-lesson.md；只生成练习时使用templates/micro-exercises.md。 - 需要对照样例时读取
examples/中对应概念；需要自测时读取evals/smoke-tests.md。
输出顺序
默认按这个顺序输出，不要把术语放在第一段当结论：
- 先说人话：用普通生活语言解释概念在说什么。
- 概念映射：把人话对应到 1-3 个 CrossFrame 结构问题。
- 反例与误读边界：写清不能误读成什么，给一个坏例或反例。
- 现实观察：列出现实里能看见的行为、资源、边界、反馈或责任变化。
- 练习：给 1-3 个小练习，帮助用户自己辨认概念边界。
如果用户要求极简，也至少保留一个极短自测问题，除非用户明确说不要练习。
教学边界
- 概念解释不是现实诊断；没有事实时，不给强判断。
- 不把 CrossFrame 概念当作道德要求、人格标签、命运预言或专业替代品。
- 不说“这是典型的 X，所以 Y”；先说事实模式，再给概念映射。
- 不把“爱/开放行动”讲成继续忍耐、继续牺牲或取消责任链。
- 不把“开放断言”讲成含糊、不负责或最终审判。
- 不把“承接/回流”讲成脾气好、会沟通、态度变好或单方负责。
最低合格标准
一次合格的教学回答必须能回答：
- 普通人第一段能不能听懂？
- 这个概念对应哪些现实行为或结构变化？
- 它最容易被误读成什么？
- 哪个反例能让用户知道边界在哪里？
- 用户可以观察什么信号？
- 用户可以做哪一个练习来验证自己是否理解？
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 378 B
- evals/smoke-tests.md 1.9 KB
- examples/chengjie-huiliu.md 1.4 KB
- examples/failure-patterns.md 1.1 KB
- examples/love-open-action.md 1.5 KB
- examples/open-assertion.md 1.3 KB
- protocols/teach-protocol.md 2.4 KB
- references/teaching-fidelity.md 1.8 KB
- templates/concept-lesson.md 1.0 KB
- templates/micro-exercises.md 882 B
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.
- 8d ago First seen · 78 lines · 31 tokens per session scan A ab4c90efbed8
crossframe-teach is a skill published in the GitHub repository xi-kari/crossframe-skill (18 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,318 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
lov-subtitle-freedom
Create learner-friendly English subtitles with level-aware glosses and optional spoiler-safe subtitle sidecars.
lov-thesis-polish
An academic editing tool for improving an MBA thesis or dissertation in Markdown, a plain-text format for structured documents. It addresses language, argument structure, logic, research contributions, and formatting.
book-to-skill
A workflow that turns personal notes from books into organised notes, practical AI skills, and a matching README.
coaching-grow
A coaching guide based on the GROW model: Goal, Reality, Options, and Will, a structure for helping someone think through a situation.
anki-expert
Generate high-quality Anki flashcards from user-provided text (inline, local .md/.txt/.pdf files, or URLs) and auto-export to .tsv, .apkg, or push directly via AnkiConnect. Trigger when the user mentions Anki, flashcards, spaced repetition, study cards, memory cards, make cards, help me memorize, or .apkg files.