Loading...
Loading...
Found 49 Skills
Agent skill for test-long-runner - invoke with $agent-test-long-runner
Use when writing, testing, and running CodeQL queries in VS Code, or setting up workspace configuration for the CodeQL extension.
Apply and validate SOLID principles in object-oriented design
Intelligent project knowledge base construction tool that automatically analyzes code to extract implicit knowledge, generates structured documents and architecture diagrams, and supports 13+ mainstream frameworks (React/Vue/Django/Spring Boot, etc.)
Multi-Model Collaboration — Invoke gemini-agent and codex-agent for auxiliary analysis **Trigger Scenarios** (Proactive Use): - In-depth code analysis: algorithm understanding, performance bottleneck identification, architecture sorting - Large-scale exploration: 5+ files, module dependency tracking, call chain tracing - Complex reasoning: solution evaluation, logic verification, concurrent security analysis - Multi-perspective decision-making: requiring analysis from different angles before comprehensive judgment **Non-Trigger Scenarios**: - Simple modifications (clear changes in 1-2 files) - File searching (use Explore or Glob/Grep) - Read/write operations on known paths **Core Principle**: You are the decision-maker and executor, while external models are consultants.
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings
Explore a codebase with parallel Haiku agents. Modes - --fast (1 agent), default (3), --deep (5). Use when user says "learn [repo]", "explore codebase", "study this repo".
Use when mapping code paths, entrypoints, and likely hot files before profiling.
Analyze brownfield codebase and create initial continuity ledger
Get a token-efficient overview of any project using the TLDR stack
Systematic codebase investigation to extract architectural patterns and implementation details from an existing project, with findings persisted for long-term reuse. Use when the user wants to explore an open-source or existing codebase to understand how it works and inform the development of a new project. Triggers include: "explore this codebase", "investigate this repo", "how does X implement Y", "I want to build X, study how Y does it", "deep dive into this project", "understand how this works".