Agent skill
deepinit
深度代码库初始化,生成分层 AGENTS.md 文档
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/deepinit
SKILL.md
oh-my-ccg Deep Init
Generate comprehensive codebase documentation for agent context.
Workflow
- Root scan: Use explore agent to map top-level structure
- Module discovery: Identify each module/package/directory
- Per-module analysis: For each module:
- Entry points and exports
- Key classes and functions
- Dependencies (internal and external)
- Test coverage
- Generate AGENTS.md: Hierarchical documentation:
# Project: <name> ## Architecture Overview ## Module: <name> ### Entry Points ### Key Symbols ### Dependencies - Generate module-level docs: Create AGENTS.md in each major directory
- Update project memory: Store structure in .oh-my-ccg/project-memory.json
Output
- Root AGENTS.md with full project map
- Per-module AGENTS.md files
- Updated project memory
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?