菜单
Structured methods for finding connections across disciplines. Use when exploring how concepts from one field illuminate another, seeking novel applications, or analyzing structural similarities between domains.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Self-iterating autonomous loop where the main agent acts as a pure orchestrator, spawning isolated Implementor and Critic subagents in rounds until the artifact converges, an iteration cap is reached, or human escalation is needed. Domain-agnostic — works for code, documents, plans, designs, copy, specs, proposals, or anything with an iterable artifact and explicit acceptance criteria. Also addressable by the short alias "bvl".
Initialize the Engram memory system — creates configuration, memory files, and CLAUDE.md integration. Trigger when the user sets up persistent memory for a project, or when `.claude/memory-settings.json` is missing and a memory feature is requested.
Search and recall memories from the Engram files. Trigger when a topic may relate to past discussions, when the user references previous context, or when the user asks "do you remember…".
Store a memory into the appropriate Engram file. Trigger when a new preference, decision, milestone, or natural conversation summary point is identified, or when the user explicitly asks to remember something.
Display Engram memory system status — configuration, file sizes, entry counts, and health check. Trigger when the user asks about memory state, what's been remembered, or for diagnostics.
Manage the dynamic skill library. Initialize skill-library/ and SKILLUSE.md, add new skills, remove skills, edit existing skills, and list available skills. Use when the user wants to manage, create, or modify skills in the skill library.
| name | cross-domain-thinking |
| description | Structured methods for finding connections across disciplines. Use when exploring how concepts from one field illuminate another, seeking novel applications, or analyzing structural similarities between domains. |
A methodological toolkit for discovering and articulating connections across disciplines.
Identify structural similarities that transcend domain boundaries.
Process:
Examples:
Output format:
"The structure here is [abstract pattern]. This same structure appears in [Domain B] as [concrete manifestation]. What this reveals: [insight about the deeper principle]."
Use a principle from one field to illuminate another.
Process:
Examples:
Output format:
"In [Domain A], [concept] works by [mechanism]. Applying this lens to [Domain B]: [new interpretation]. This suggests [actionable insight or prediction]."
Transfer solutions or techniques across contexts.
Process:
Caution flags:
Output format:
"[Domain A] solved [problem] using [approach]. [Domain B] faces analogous challenge: [description]. Potential transfer: [adapted solution]. Transfer risk: [what might not hold]."
Find where different frameworks conflict instructively.
Process:
Examples:
Output format:
"[Framework A] says [X]. [Framework B] says [Y]. The tension: [specific conflict]. What A captures that B misses: [insight]. What B captures that A misses: [insight]. Resolution path: [synthesis or scope conditions]."
Analyze user request:
Select mode:
"How does X relate to Y?" -> Isomorphic Patterns or Conceptual Bridges
"Can we apply X to solve Y?" -> Novel Applications
"X says one thing, Y says another" -> Productive Tensions
"Find connections to X" -> Start with Isomorphic Patterns
For Isomorphic Patterns:
For Conceptual Bridges:
For Novel Applications:
For Productive Tensions:
Abstraction Ladder:
Epistemic Marking:
After generating cross-domain insights, consider:
Example integration:
User: "How does natural selection relate to algorithm design?"
Skill workflow:
1. Identifies Conceptual Bridge mode
2. Analyzes natural selection mechanisms
3. Maps to evolutionary algorithms
4. Presents insights with epistemic marking
Optional follow-up:
"Would you like me to save these insights to your knowledge base?"
-> Invokes add-content to capture for future reference
User: "I'm noticing that both social media viral content and disease outbreaks seem to spread similarly. What's the connection?"
Skill response:
The structure here is network propagation with threshold dynamics. In both cases:
- Transmission occurs through connected nodes (people)
- Each transmission has a probability of success
- Critical mass triggers exponential growth
- Network topology determines spread patterns
This same structure appears in:
- Neural activation cascades in the brain
- Bank run panics in financial systems
- Idea adoption in scientific communities
What this reveals: The mathematics of contagion is substrate-independent. Understanding one gives you tools for all. The key variables are: connection density, transmission probability, and recovery/immunity rate.
User: "Engineering uses 'margin of safety' - could that concept help with personal finance decisions?"
Skill response:
Engineering solved the problem of uncertainty in material properties using margin of safety: design for 2-3x expected load to handle unknowns.
Personal finance faces an analogous challenge: income volatility, unexpected expenses, lifestyle inflation.
Potential transfer:
- Instead of spending up to your income limit, maintain a 2x margin
- Emergency fund = "factor of safety" for income disruption
- Budget for 50% of actual income = structural margin for unknowns
Transfer risk: Unlike engineering where failure modes are understood, life has "black swan" events. Engineering margins are calculated; financial margins are estimated. The principle transfers, but calibration requires different methods.
User: "Economists say people are rational actors, but psychologists show we're full of biases. Who's right?"
Skill response:
Rational actor model says: People optimize utility given constraints and information.
Behavioral psychology says: People use heuristics that systematically deviate from optimization.
The tension: Both can't be fully true. If we're rational optimizers, biases shouldn't persist. If we're bias-driven, markets shouldn't work as well as they do.
What rational models capture that behavioral misses: Aggregate market behavior often looks rational even when individuals aren't. Markets select for rational-ish outcomes.
What behavioral captures that rational misses: Individual decision-making, especially under uncertainty or emotional load. Where arbitrage is difficult.
Resolution path: Bounded rationality - people are rational within cognitive constraints. Rational at the margin, biased at the baseline. Different scopes of application, not contradiction.