Learn Project
技能 已验证 活跃Scan project code to detect patterns, dependencies, and conventions. Propose domain rules based on what the code actually does.
To automatically detect and document project-specific patterns, dependencies, and conventions by analyzing the codebase, enabling the generation of domain rules for better governance.
功能
- Detects dependency files across multiple languages
- Scans imports to identify top libraries
- Analyzes project structure and configuration files
- Classifies patterns in ORM, Auth, Testing, Build, API, State Management, Deployment
- Scans for remote-host usage (SSH/VPS)
- Proposes domain rules based on detected patterns
使用场景
- Understanding the technology stack of a new project
- Identifying common libraries and frameworks used
- Proposing standard conventions for code quality and consistency
- Documenting infrastructure and deployment patterns
非目标
- Modifying existing rules or project code
- Running or installing any code or dependencies
- Guessing patterns without direct evidence in the codebase
- Reading dotforge memory or agent memory
工作流
- Detect dependency files (package.json, pyproject.toml, etc.)
- Scan top 20 most-imported libraries across the codebase
- Scan project structure (directories, config files)
- Scan for remote-host usage (SSH/VPS)
- Classify detected patterns (ORM, Auth, Testing, etc.)
- Present proposals for domain rules based on findings
- Generate approved rule files in .claude/rules/domain/
Documentation
- info:READMEA README exists, but it is very long and detailed, primarily focused on the `dotforge` toolset rather than this specific skill's immediate use.
安装
请先添加 Marketplace
/plugin marketplace add luiseiman/claude-kit/plugin install claude-kit@dotforge质量评分
已验证类似扩展
VoltAgent Best Practices
95VoltAgent 架构模式和约定。涵盖代理与工作流、项目布局、内存、服务器和可观测性。
Metal
100Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.
Lean Ctx
100AI 代理的上下文运行时 — 包含 59 个 MCP 工具、10 种读取模式、95+ 种 shell 模式、支持 18 种语言的 tree-sitter AST。将 LLM 上下文压缩高达 99%。用于读取文件、运行 shell 命令、搜索代码或探索目录。如果不存在，则自动安装。
Pathfinder
100将代码库映射为按功能分组的流程图，识别不同功能之间的重复关注点，并提出统一的架构。在被要求“寻找理想路径”、统一重复系统或在重构前审计架构时使用。输出一个建议的统一流程图以及针对每个系统的“制定计划”提示。
Codacy Audit
100Codacy Cloud workflow for this repository -- run Codacy's analyzers locally before `git push` (mirrors what Codacy CI runs), and fetch/cluster Codacy issues for any PR via the v3 API. Use when the user mentions Codacy, "codacy analysis", `codacy-analysis-cli`, "codacy issues on PR", "fix codacy CI", "codacy markdownlint findings", or any Codacy gate failing on a netdata-org PR. Ships scripts analyze-local.sh (docker/binary runner for codacy-analysis-cli) and pr-issues.sh (paginated v3 issue fetch + group-by tool/pattern/severity/file). Token-safe -- CODACY_TOKEN never reaches assistant-visible stdout. Read-only by design in the current SOW; write actions (mark FP, mark fixed) are deferred.
Domain Extract
100Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.