Rust Question Router

Version: 2.0.0 | Last Updated: 2026-01-17

New in v2.0: Meta-Cognition Routing – Three-layer cognitive model for deeper answers

Meta-Cognition Framework

Core Principle

Don’t answer directly. Trace through the cognitive layers first.

Layer 3: Domain Constraints (WHY)
├── Business rules, regulatory requirements
├── domain-fintech, domain-web, domain-cli, etc.
└── "Why is it designed this way?"

Layer 2: Design Choices (WHAT)
├── Architecture patterns, DDD concepts
├── m09-m15 skills
└── "What pattern should I use?"

Layer 1: Language Mechanics (HOW)
├── Ownership, borrowing, lifetimes, traits
├── m01-m07 skills
└── "How do I implement this in Rust?"

Routing by Entry Point

CRITICAL: Dual-Skill Loading

When domain keywords are present, you MUST load BOTH skills:

Example: “Web API 报错 Rc cannot be sent”

• Load: m07-concurrency (L1 – Send/Sync error)
• Load: domain-web (L3 – Web state management)
• Answer must include both layers

Trace Examples

User: "My trading system reports E0382"

1. Entry: Layer 1 (E0382 = ownership error)
2. Load: m01-ownership skill
3. Trace UP: What design led to this?
4. Check: domain-fintech (trading = immutable audit data)
5. Answer: Don't clone, use Arc<T> for shared immutable data

User: "How should I handle user authentication?"

1. Entry: Layer 2 (design question)
2. Trace UP to Layer 3: domain-web constraints
3. Load: domain-web skill (security, stateless HTTP)
4. Trace DOWN: m06-error-handling, m07-concurrency
5. Answer: JWT with proper error types, async handlers

INSTRUCTIONS FOR CLAUDE

Default Project Settings (When Creating Rust Code)

When creating new Rust projects or Cargo.toml files, ALWAYS use:

[package]
edition = "2024"  # ALWAYS use latest stable edition
rust-version = "1.85"

[lints.rust]
unsafe_code = "warn"

[lints.clippy]
all = "warn"
pedantic = "warn"

Rules:

• ALWAYS use edition = "2024" (not 2021 or earlier)
• Include rust-version for MSRV clarity
• Enable clippy lints by default
• DO NOT use WebSearch for Rust questions – use skills and agents

Meta-Cognition Routing Process

1. Identify Entry Layer

   • E0xxx errors → Layer 1
   • Design questions → Layer 2
   • Domain-specific → Layer 3

2. Load Appropriate Skill

   • Read the skill file for context
   • Note the “Trace Up” and “Trace Down” sections

3. Trace Through Layers

   • Don’t stop at surface-level fix
   • Ask “Why?” to trace up
   • Ask “How?” to trace down

4. Answer with Context

   • Include the reasoning chain
   • Reference which layers/skills informed the answer

When User Requests Intent Analysis

User may say: “analyze this question” / “what type of problem is this” / “analyze intent”

Execute these steps:

1. Extract Keywords – Identify Rust concepts, error codes, crate names
2. Identify Entry Layer – Which cognitive layer is this?
3. Map to Skills – Which m0x/m1x/domain skills apply?
4. Report Analysis – Tell user the layers and suggested trace
5. Invoke Skill – Load and apply the matched skill

Layer 1 Skills (Language Mechanics)

Layer 2 Skills (Design Choices)

Layer 3 Skills (Domain Constraints)

Error Code Routing

Unsafe-Specific Routing

For detailed unsafe rules, route to unsafe-checker skill:

Functional Routing Table

Priority Order

1. Identify cognitive layer (L1/L2/L3)
2. Load entry skill (m0x/m1x/domain)
3. Trace through layers (UP or DOWN)
4. Cross-reference skills as indicated in “Trace” sections
5. Answer with reasoning chain

Skill File Paths

Meta-Cognition Framework

_meta/reasoning-framework.md    # How to trace through layers
_meta/layer-definitions.md      # Layer definitions
_meta/externalization.md        # Cognitive externalization
_meta/error-protocol.md         # 3-Strike escalation rule
_meta/hooks-patterns.md         # Automatic triggers

Layer 1 Skills (Language Mechanics)

skills/m01-ownership/SKILL.md
skills/m02-resource/SKILL.md
skills/m03-mutability/SKILL.md
skills/m04-zero-cost/SKILL.md
skills/m05-type-driven/SKILL.md
skills/m06-error-handling/SKILL.md
skills/m07-concurrency/SKILL.md

Layer 2 Skills (Design Choices)

skills/m09-domain/SKILL.md
skills/m10-performance/SKILL.md
skills/m11-ecosystem/SKILL.md
skills/m12-lifecycle/SKILL.md
skills/m13-domain-error/SKILL.md
skills/m14-mental-model/SKILL.md
skills/m15-anti-pattern/SKILL.md

Layer 3 Skills (Domain Constraints)

skills/domain-fintech/SKILL.md
skills/domain-ml/SKILL.md
skills/domain-cloud-native/SKILL.md
skills/domain-iot/SKILL.md
skills/domain-web/SKILL.md
skills/domain-cli/SKILL.md
skills/domain-embedded/SKILL.md

OS-Checker Integration

For code review and security auditing:

Workflow Example with Meta-Cognition

User: "Why am I getting E0382 in my trading system?"

Analysis:
1. Entry: Layer 1 (E0382 = ownership/move error)
2. Load: m01-ownership skill
3. Context: "trading system" → domain-fintech

Trace UP ↑:
- E0382 in trading context
- Check domain-fintech: "immutable audit records"
- Finding: Trading data should be shared, not moved

Response:
"E0382 indicates a value was moved when still needed.
In a trading system (domain-fintech), transaction records
should be immutable and shareable for audit purposes.

Instead of cloning, consider:
- Arc<TradeRecord> for shared immutable access
- This aligns with financial audit requirements

See: m01-ownership (Trace Up section),
     domain-fintech (Audit Requirements)"