Loading...
Loading...
Found 2,219 Skills
Document finalized technology selections, architecture decisions, long-term constraints, and coding conventions in the project into searchable permanent documents. No one will remember why X was chosen six months later, but with decision documents, at least the background can be understood before making changes next time. Four types: tech-stack (which tools/libraries/frameworks to use), architecture (how the system is organized), constraint (what is not allowed), convention (what is uniformly done). Trigger scenarios: Proactively push when important choices are made after feature-design or issue-analyze, or when the user says "record decision", "archive technology selection", "ADR", "record this constraint", "write down the convention". Only archive finalized decisions; do not archive under-discussion solutions.
Write a lightweight technical design document for ambiguous or consequential architecture decisions before implementation.
Curated guide for implementing design patterns, architecture decisions, and verified design rules in software projects
Interprets authoritative specs and helps design a new implementation collaboratively, preserving required business, API, and database contracts while exploring architecture, stack, and delivery options with the user. Use when the user wants to start a new project from frozen specs, discuss implementation approaches, or plan an incremental rebuild without depending on the legacy codebase.
Builds and queries code knowledge graph for dependency analysis, references, implementations, and architecture overview. Use when starting work on unfamiliar codebase or before refactoring.
Build and maintain project-specific review policy for `agentic-review` by combining repository docs (`AGENTS.md`, `ENGINEERING.md`, `CONTEXT.md`/`CONTEXT-MAP.md`, ADRs), repository-mined conventions, and structured user input, then writing machine-usable policy files under `<docs-dir>/review/policies/`, including audit-governance metadata consumed by `agentic-review`. Use when the user wants architecture integrity checks (onion/clean/hexagonal), module-specific review rules, dependency-direction policy, naming/inheritance convention enforcement, stricter project/domain review standards, or explicit auditability requirements for specialist review coverage.
Create Excalidraw hand-drawn style diagrams (architecture, flowchart, swimlane, sequence, wireframe). Trigger words: draw diagram, architecture diagram, flowchart, swimlane, excalidraw, diagram
Learn mode for explaining code, concepts, and architecture. Use when user asks to explain how things work, understand concepts, or learn about code patterns. Provides explanations from simple to complex with examples and analogies.
Automates architecture validation for Clean Architecture, Hexagonal, Layered, and MVC patterns. Detects layer boundary violations, dependency rule breaches, and architectural anti-patterns. Use when asked to "validate architecture", "check layer boundaries", "architectural review", before major refactoring, or as pre-commit quality gate. Adapts to project's architectural style by reading ARCHITECTURE.md.
Gate 3: Technical architecture document - defines HOW/WHERE with technology-agnostic patterns before concrete implementation choices.
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.
This skill is used when users request to draw charts in Feishu Cloud Docs, or use Feishu Whiteboard to draw architecture diagrams, flowcharts, mind maps, sequence diagrams, or other visual charts.