base-rules
General development rules including comment length, testing protocol, and command aliasing (puro).
发现 部署与运维 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
General development rules including comment length, testing protocol, and command aliasing (puro).
Guidelines for structuring applications using the view_model package, promoting a simplified, mixin-based architecture.
Workflow for publishing view_model packages (annotation, generator, view_model) in the correct order.
The master guide for the view_model ecosystem. Start here to navigate to specific sub-skills.
Guide for writing effective system prompts for LLM agents. Use when creating or editing system prompts for applications, agent configurations, or development tools.
Guide for writing effective technical documentation, specs, and markdown files. Use when creating or editing specs, documentation, READMEs, AGENTS.md files, or any markdown content in the codebase.
Firmware extraction and IoT security analysis (RE Level 5) for routers and embedded systems. Use when analyzing IoT firmware, extracting embedded filesystems (SquashFS/JFFS2/CramFS), finding hardcoded credentia...
Advanced AgentDB Vector Search Implementation operates on 3 fundamental principles:
Use Gemini CLI for research with Google Search grounding and 1M token context
Create Claude Code hooks with proper schemas, RBAC integration, and performance requirements. Use when implementing PreToolUse, PostToolUse, SessionStart, or any of the 10 hook event types for automation, valid...
Build reliable GitHub integrations, webhooks, and automation bridges
Use when conducting comprehensive code review for pull requests across multiple quality dimensions. Orchestrates 12-15 specialized reviewer agents across 4 phases using star topology coordination. Covers automa...
Run code in Codex fully isolated sandbox - network disabled, CWD only, Seatbelt/Docker isolation
Use Codex CLI in full-auto mode to fix issues iteratively until tests pass. Autonomous debugging and test-fixing loop with sandbox safety.
Fix bug command
End-to-end testing workflow for validating complete user journeys through web applications using claude-in-chrome MCP. Specializes in test assertions, suite organization, evidence collection, and pass/fail repo...
Zero Data Retention mode for sensitive/proprietary code - no code stored on OpenAI servers
Screenshot-based visual comparison and regression testing using claude-in-chrome MCP. Captures, compares, and validates UI states to detect layout shifts, visual bugs, and design regressions across viewports.
Advanced binary analysis with runtime execution and symbolic path exploration (RE Levels 3-4). Use when need runtime behavior, memory dumps, secret extraction, or input synthesis to reach specific program state...
Multi-model consensus using Karpathy LLM Council pattern for critical decisions
Apply quantization to reduce memory by 4-32x. Enable HNSW indexing for 150x faster search. Configure caching strategies and implement batch operations. Use when optimizing memory usage, improving search speed,...
Systematic technology and market reconnaissance for extracting actionable intelligence from repositories, papers, and competitive landscapes.
Use Codex CLI sandbox mode to try risky changes safely. Isolated experimentation with network disabled and directory restrictions.
Structured data extraction from web pages using claude-in-chrome MCP with sequential-thinking planning. Focus on READ operations, data transformation, and pagination handling for multi-page extraction.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。