When to Use This Skill
- Use when
crossframe-suiteroutes explicit CrossFrame work into concept teaching, misreading correction, plain-language examples, observable signals, or exercises. - Use when the user wants to understand a CrossFrame concept without turning terms into slogans.
- Do not use independently unless the user explicitly names this sibling skill.
Packaged Source Note
This AAS-ready copy preserves the original CrossFrame skill body below. Chinese remains the canonical semantic layer; English metadata is only for discovery, installation, and repository review.
Limitations
- The skill body is intentionally Chinese-canonical; English metadata is for discovery and does not replace the original Chinese terms.
- Use only after explicit CrossFrame invocation or
crossframe-suiterouting; do not apply it as a generic default reasoning layer. - It structures analysis, drafting, and review, but does not replace source verification, domain expertise, or legal, medical, or financial judgment.
This skill does not trigger independently. All CrossFrame tasks are uniformly dispatched from the
crossframe-suiteentry point. Users do not need to call this skill directly; the suite loads it automatically when needed according to routing rules.
If concept teaching needs to connect to article writing, case consolidation, reading research, or output review, first read ../crossframe-suite/SKILL.md for overall dispatch; this skill is only responsible for teaching explanations, misreading boundaries, and exercises.
Light entry principle
Chinese is the authoritative semantics.CrossFrame Teach is only a teaching entry point; it does not rewrite, replace, or compress canonical CrossFrame.
After each trigger, first read the adjacent canonical materials:
../crossframe/SKILL.md../crossframe/references/read-routing-map.md- If concept teaching triggers high responsibility, public institutions, intimate relationships, long-term evolution, framework governance, AI reality verification, weak signals/opacity, inability to exit, instrumentalization, metaphor/source transparency, or article output, additionally read
../crossframe/references/continuity-bundles.md, and use as needed../crossframe/worksheets/source-continuity-check.md; if the joint reading is not completed, you can only downgrade. - Reuse
../crossframe/templates/read-state-capsule.mdas specifiedv5-read-state-capsule, and in scenarios of high responsibility, public, AI/process artifacts, lifecycle, subjects that cannot exit, or article output, execute../crossframe/worksheets/source-anchor-integrity-check.md. If the capsule is missing, return to../crossframe/SKILL.mdto fill it in; this skill does not reinvent source routing.
Do not copy the full canonical text into the answer. Read only the canonical protocols, terminology fidelity materials, concept cards, or templates needed for this concept; use this skill's lightweight protocols and templates for teaching expression.
Required resources
- Read
protocols/teach-protocol.mdto determine whether this is a concept lesson, misreading correction, reality signal training, or exercise generation. - Read
references/teaching-fidelity.mdto prevent terminology piling, distortion from overly short explanations, moralization, and missing exercises. - Use when a finished draft is needed
templates/concept-lesson.md; use when only generating exercisestemplates/micro-exercises.md。 - When comparison examples are needed, read the corresponding concept in
examples/; when self-testing is needed, readevals/smoke-tests.md。
Output order
By default, output in this order; do not put terminology in the first paragraph as a conclusion:
- First speak plainly: explain what the concept is saying in ordinary everyday language.
- Concept mapping: map the plain language to 1-3 CrossFrame structural questions.
- Counterexamples and misreading boundaries: clearly state what it cannot be misread as, and give a bad example or counterexample.
- Reality observation: list the behaviors, resources, boundaries, feedback, or responsibility changes that can be seen in reality.
- Exercises: give 1-3 small exercises to help users identify the concept boundaries themselves.
If the user requests extreme brevity, still keep at least one very short self-test question, unless the user explicitly says no exercises.
Teaching boundaries
- Concept explanation is not reality diagnosis; when there are no facts, do not give strong judgments.
- Do not treat CrossFrame concepts as moral requirements, personality labels, fate predictions, or professional substitutes.
- Do not say "this is a typical X, therefore Y"; first state the factual pattern, then give the concept mapping.
- Do not explain "love/open action" as continuing to endure, continuing to sacrifice, or canceling the chain of responsibility.
- Do not explain "open assertion" as vague, irresponsible, or a final judgment.
- Do not explain "receiving/return flow" as being good-tempered, good at communication, having a better attitude, or being unilaterally responsible.
Minimum passing standard
A qualified teaching answer must be able to answer:
- Can an ordinary person understand the first paragraph?
- Which real-world behaviors or structural changes does this concept correspond to?
- What is it most easily misread as?
- Which counterexample can let users know where the boundary is?
- What signals can users observe?
- Which exercise can users do to verify whether they understand?
Resource Index
protocols/teach-protocol.md: Teaching explanation process.references/teaching-fidelity.md: Teaching fidelity and anti-misuse rules.templates/concept-lesson.md: Complete concept lesson template.templates/micro-exercises.md: Exercise template.examples/chengjie-huiliu.md: Teaching examples for receiving/returning.examples/open-assertion.md: Teaching example for open assertions.examples/love-open-action.md: Teaching examples for love/open action.examples/failure-patterns.md: Failure examples.evals/smoke-tests.md:smoke tests。