Docker best practices including multi-stage builds, compose patterns, image optimization, and security

Django architecture patterns including DRF, ORM optimization, signals, middleware, and project structure

CI/CD pipeline design with GitHub Actions, Docker, Kubernetes, Helm, and GitOps patterns

Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No external API needed.

Data engineering patterns for ETL pipelines, data warehousing, Apache Spark, and data quality validation

Query optimization, indexing strategies, and database performance tuning for PostgreSQL and MySQL

Auto-extract patterns from coding sessions, track corrections, and build reusable knowledge with confidence scoring

Persistent memory system for Claude Code. Two-layer architecture (hot cache + knowledge wiki), safety hooks, /close-day end-of-day synthesis. Zero external dependencies.

CI/CD pipeline patterns for GitHub Actions, GitLab CI, testing strategies, and deployment automation

AWS cloud patterns for Lambda, ECS, S3, DynamoDB, and Infrastructure as Code with CDK/Terraform

Authentication and authorization patterns including OAuth2, JWT, RBAC, session management, and PKCE flows

REST API design with resource naming, pagination, versioning, and OpenAPI spec generation

Route broad or ambiguous AgentKit SEO work to the right module while keeping context scoped. Use when a request spans multiple surfaces, asks for overall digital-presence strategy, involves provider or install architecture, needs agent-context planning, or the correct platform skill is unclear.

Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.

Create or refine glass UI with accessible solid fallbacks. Covers frosted surfaces and Liquid Glass; excludes unrelated UI and 3D glass rendering.

Helps your project comply with accessibility standards and best practices.

Helps with grouping, alignment, reading order, progressive disclosure and other details that make a good layout.

Focuses on type scale, spacing, sizing, variable fonts, OpenType features, wrapping, truncation and other details that make typography feel great across your product.

Deep startup profiling for OneKey mobile — per-module JS factory timings, HBC I/O/parse breakdown, per-segment timings. Gated behind the single env var `ONEKEY_STARTUP_PROFILE=1`. Zero overhead when disabled (default). Use when diagnosing cold-start regressions, sizing main.bundle parse cost, finding slow modules, measuring segment load, or auditing what a 1.7s `require('./App')` actually contains. Triggers on: startup profile, 启动性能分析, module timing, HBC parse time, segment timing, require cost, StartupProfile, ONEKEY_STARTUP_PROFILE, __d patcher, inline-requires.

当你要用 Kunlun-M（静态白盒漏洞扫描）扫描 PHP/JS/Solidity/Chrome Ext 源码，或需要通过命令 scan/generate 快速落地 source/sink（tamper/rule）并回归验证时使用。触发命令：kunlun.py scan / kunlun.py generate rule / kunlun.py generate tamper。