Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills/Documentation
actionbook avatar

Rust Router

actionbook/rust-skills

This is a meta-router that decides which specialized Rust skill Claude should load based on your question. It works in three layers: language mechanics (ownership, lifetimes, error codes), design patterns (performance, anti-patterns, domain modeling), and domain constraints (fintech, web, embedded). When you hit a borrow checker error or ask about async patterns, it traces through the layers to pull in the right combination of skills. The negotiation protocol is interesting: it forces Claude to show confidence levels and gaps when you ask comparative questions like "tokio vs async-std" or request best practices. It's essentially a dispatch table with 30+ routing rules, error code lookups, and domain keyword detection. If you work in Rust and want more structured responses that acknowledge what they don't cover, this shapes how Claude approaches your questions.

installs
2.7K
GitHub stars
1.5K
last updated
Aug 21, 2026
View on GitHubSave

Install

$ npx -y skills add actionbook/rust-skills --skill rust-router --agent claude-code

Installs into .claude/skills of the current project.

Files


Rust Question Router

Version: 2.0.0 | Last Updated: 2025-01-22

v2.0: Context optimized - detailed examples moved to sub-files

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

User SignalEntry LayerDirectionFirst Skill
E0xxx errorLayer 1Trace UP ↑m01-m07
Compile errorLayer 1Trace UP ↑Error table below
"How to design..."Layer 2Check L3, then DOWN ↓m09-domain
"Building [domain] app"Layer 3Trace DOWN ↓domain-*
"Best practice..."Layer 2Both directionsm09-m15
Performance issueLayer 1 → 2UP then DOWNm10-performance

CRITICAL: Dual-Skill Loading

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

Domain KeywordsL1 SkillL3 Skill
Web API, HTTP, axum, handlerm07-concurrencydomain-web
交易, 支付, trading, paymentm01-ownershipdomain-fintech
CLI, terminal, clapm07-concurrencydomain-cli
kubernetes, grpc, microservicem07-concurrencydomain-cloud-native
embedded, no_std, MCUm02-resourcedomain-embedded

INSTRUCTIONS FOR CLAUDE

CRITICAL: Negotiation Protocol Trigger

BEFORE answering, check if negotiation is required:

Query ContainsAction
"比较", "对比", "compare", "vs", "versus"MUST use negotiation
"最佳实践", "best practice"MUST use negotiation
Domain + error (e.g., "交易系统 E0382")MUST use negotiation
Ambiguous scope (e.g., "tokio 性能")SHOULD use negotiation

When negotiation is required, include:

## Negotiation Analysis

**Query Type:** [Comparative | Cross-domain | Synthesis | Ambiguous]
**Negotiation:** Enabled

### Source: [Agent/Skill Name]
**Confidence:** HIGH | MEDIUM | LOW | UNCERTAIN
**Gaps:** [What's missing]

## Synthesized Answer
[Answer]

**Overall Confidence:** [Level]
**Disclosed Gaps:** [Gaps user should know]

详细协议见: patterns/negotiation.md


Default Project Settings

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"

Layer 1 Skills (Language Mechanics)

PatternRoute To
move, borrow, lifetime, E0382, E0597m01-ownership
Box, Rc, Arc, RefCell, Cellm02-resource
mut, interior mutability, E0499, E0502, E0596m03-mutability
generic, trait, inline, monomorphizationm04-zero-cost
type state, phantom, newtypem05-type-driven
Result, Error, panic, ?, anyhow, thiserrorm06-error-handling
Send, Sync, thread, async, channelm07-concurrency
unsafe, FFI, extern, raw pointer, transmuteunsafe-checker

Layer 2 Skills (Design Choices)

PatternRoute To
domain model, business logicm09-domain
performance, optimization, benchmarkm10-performance
integration, interop, bindingsm11-ecosystem
resource lifecycle, RAII, Dropm12-lifecycle
domain error, recovery strategym13-domain-error
mental model, how to thinkm14-mental-model
anti-pattern, common mistake, pitfallm15-anti-pattern

Layer 3 Skills (Domain Constraints)

Domain KeywordsRoute To
fintech, trading, decimal, currencydomain-fintech
ml, tensor, model, inferencedomain-ml
kubernetes, docker, grpc, microservicedomain-cloud-native
embedded, sensor, mqtt, iotdomain-iot
web server, HTTP, REST, axum, actixdomain-web
CLI, command line, clap, terminaldomain-cli
no_std, microcontroller, firmwaredomain-embedded

Error Code Routing

Error CodeRoute ToCommon Cause
E0382m01-ownershipUse of moved value
E0597m01-ownershipLifetime too short
E0506m01-ownershipCannot assign to borrowed
E0507m01-ownershipCannot move out of borrowed
E0515m01-ownershipReturn local reference
E0716m01-ownershipTemporary value dropped
E0106m01-ownershipMissing lifetime specifier
E0596m03-mutabilityCannot borrow as mutable
E0499m03-mutabilityMultiple mutable borrows
E0502m03-mutabilityBorrow conflict
E0277m04/m07Trait bound not satisfied
E0308m04-zero-costType mismatch
E0599m04-zero-costNo method found
E0038m04-zero-costTrait not object-safe
E0433m11-ecosystemCannot find crate/module

Functional Routing Table

PatternRoute ToAction
latest version, what's newrust-learnerUse agents
API, docs, documentationdocs-researcherUse agent
code style, naming, clippycoding-guidelinesRead skill
unsafe code, FFIunsafe-checkerRead skill
code reviewos-checkerSee integrations/os-checker.md

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

Keyword Conflict Resolution

KeywordResolution
unsafeunsafe-checker (more specific than m11)
errorm06 for general, m13 for domain-specific
RAIIm12 for design, m01 for implementation
craterust-learner for version, m11 for integration
tokiotokio-* for API, m07 for concepts

Priority Hierarchy:

1. Error codes (E0xxx) → Direct lookup, highest priority
2. Negotiation triggers (compare, vs, best practice) → Enable negotiation
3. Domain keywords + error → Load BOTH domain + error skills
4. Specific crate keywords → Route to crate-specific skill if exists
5. General concept keywords → Route to meta-question skill

Sub-Files Reference

FileContent
patterns/negotiation.mdNegotiation protocol details
examples/workflow.mdWorkflow examples
integrations/os-checker.mdOS-Checker integration
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/actionbook/rust-skills
Categories
Documentation, Debugging, Productivity & Planning, Rust, Design & UI/UX
First seen
Jun 3, 2026

More from actionbook/rust-skills

All 38
  • Core Agent Browser2K
  • Core Dynamic Skills1.9K
  • Core Actionbook1.8K
  • Core Fix Skill Docs1.8K
  • M15 Anti Pattern8.6K
  • Coding Guidelines4K
  • M10 Performance3.6K
  • M07 Concurrency3.5K
  • M06 Error Handling3.5K
  • M01 Ownership3.4K
  • M04 Zero Cost3.4K
  • M05 Type Driven3.4K
  • M02 Resource3.4K
  • M03 Mutability3.4K
  • Rust Refactor Helper3.4K
  • M12 Lifecycle3.3K
  • M09 Domain3.3K
  • M14 Mental Model3.3K
  • M13 Domain Error3.3K
  • M11 Ecosystem3.3K
  • Unsafe Checker3.3K
  • Rust Code Navigator3.2K
  • Rust Trait Explorer3.2K
  • Rust Call Graph3.2K

Recommended

More Documentation
1wshobson avatarlora-qlora-recipeswshobson/agentsConfigure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA training configuration, c2.7Kinstalls
2phuryn avatarwwasphuryn/pm-skillsCreate product backlog items in Why-What-Acceptance format — independent, valuable, testable items with strategic context. Use when writing structured backlog i2.7Kinstalls
3minimax-ai avatarandroid-native-devminimax-ai/skillsAndroid native application development and UI design guide. Covers Material Design 3, Kotlin/Compose development, project configuration, accessibility, and buil2.7Kinstalls
4dynatrace avatardt-obs-logsdynatrace/dynatrace-for-aiLog querying, filtering, pattern analysis, and error rate calculation. Use when searching application or infrastructure logs, analyzing error patterns, or corre2.7Kinstalls
5dynatrace avatardt-obs-problemsdynatrace/dynatrace-for-aiDAVIS problem analysis including root cause identification, impact assessment, and correlation with other telemetry. Use when querying or investigating detected2.7Kinstalls
6anthropics avatardraft-offeranthropics/knowledge-work-pluginsDraft an offer letter with comp details and terms. Use when a candidate is ready for an offer, assembling a total comp package (base, equity, signing bonus), wr2.7Kinstalls