explore by parcadei/continuous-claude-v3
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill explore用于在不同深度探索内部代码库的元技能。只读工作流 - 不进行代码更改。
/explore <depth> [options]
如果用户只输入 /explore 而没有参数或参数不完整,请引导他们完成以下问题流程。每个阶段使用 AskUserQuestion。
question: "How would you like to explore?"
header: "Explore"
options:
- label: "Help me choose (Recommended)"
description: "I'll ask questions to pick the right exploration depth"
- label: "Quick - fast overview"
description: "Chain: tldr tree → tldr structure (~1 min)"
- label: "Deep - comprehensive analysis"
description: "Chain: onboard → tldr → research → document (~5 min)"
- label: "Architecture - layers & dependencies"
description: "Chain: tldr arch → call graph → layer mapping (~3 min)"
映射关系:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
question: "I want to understand how deep you want to explore. Did you mean..."
header: "Clarify"
options:
- label: "Help me choose"
description: "Not sure - guide me through questions"
- label: "Quick - fast overview"
description: "Just want to see what's here"
- label: "Deep - comprehensive analysis"
description: "Need thorough understanding"
- label: "Neither - let me explain differently"
description: "I'll describe what I need"
question: "What are you trying to understand?"
header: "Goal"
options:
- label: "Get oriented in the codebase"
description: "Quick overview of structure"
- label: "Understand how something works"
description: "Deep dive into specific area"
- label: "Map the architecture"
description: "Layers, dependencies, patterns"
- label: "Find where something is"
description: "Locate specific code/functionality"
映射关系:
question: "What area should I focus on?"
header: "Focus"
options:
- label: "Entire codebase"
description: "Explore everything"
- label: "Specific directory or module"
description: "I'll specify the path"
- label: "Specific concept/feature"
description: "e.g., 'authentication', 'API routes'"
如果选择"Specific directory"或"Specific concept" → 询问后续的路径/关键词。
question: "What should I produce?"
header: "Output"
options:
- label: "Just tell me what you find"
description: "Interactive summary in chat"
- label: "Create a documentation file"
description: "Write to thoughts/shared/docs/"
- label: "Create handoff for implementation"
description: "Prepare context for coding agent"
映射关系:
如果选择了 architecture 深度:
question: "Where should I start the analysis?"
header: "Entry point"
options:
- label: "Auto-detect (main, cli, app)"
description: "Find common entry points"
- label: "Specific function/file"
description: "I'll specify the entry point"
Based on your answers, I'll run:
**Depth:** deep
**Focus:** "authentication"
**Output:** handoff
**Path:** src/
Proceed? [Yes / Adjust settings]
| 深度 | 时间 | 功能 |
|---|---|---|
quick | ~1 分钟 | 仅使用 tldr-explorer - 快速结构概览 |
deep | ~5 分钟 | onboard + tldr-explorer + research-codebase + 编写文档 |
architecture | ~3 分钟 | tldr arch + 调用图 + 层次映射 + 循环依赖检测 |
| 选项 | 描述 | 示例 |
|---|---|---|
--focus "area" | 聚焦特定区域 | --focus "auth", --focus "api" |
--output handoff | 为下一个智能体创建交接文件 | --output handoff |
--output doc | 创建文档文件 | --output doc |
--entry "func" | 从特定入口点开始 | --entry "main", --entry "process_request" |
# 快速结构概览
/explore quick
# 聚焦认证的深度探索
/explore deep --focus "auth" --output doc
# 从特定入口开始的架构分析
/explore architecture --entry "cli" --output handoff
# 快速聚焦探索
/explore quick --focus "hooks"
使用 tldr-explorer 进行快速结构概览。最适合:
步骤:
tldr tree 获取文件结构tldr structure 获取代码映射--focus,运行 tldr search 获取针对性结果命令:
# 1. 文件树
tldr tree ${PATH:-src/} --ext .py
# 2. 代码结构
tldr structure ${PATH:-src/} --lang python
# 3. 聚焦搜索(如果提供了 --focus)
tldr search "${FOCUS}" ${PATH:-src/}
包含文档输出的全面探索。最适合:
步骤:
.claude/cache/tldr/),如果没有则运行 onboard子流程:
# 1. 初始化检查
if [ ! -f .claude/cache/tldr/arch.json ]; then
# Spawn onboard agent
fi
# 2. 结构分析
tldr structure src/ --lang python
tldr calls src/
# 3. 研究模式(通过 scout 智能体)
Task: research-codebase → "Document existing patterns in ${FOCUS:-codebase}"
# 4. 写入输出
→ thoughts/shared/research/YYYY-MM-DD-explore-{focus}.md
→ OR thoughts/shared/handoffs/{session}/explore-{focus}.yaml
专注于架构的分析,包含层次检测。最适合:
步骤:
tldr arch 进行层次检测tldr calls 获取跨文件调用图命令:
# 1. 架构检测
tldr arch ${PATH:-src/}
# Returns: entry_layer, middle_layer, leaf_layer, circular_deps
# 2. 调用图
tldr calls ${PATH:-src/}
# Returns: edges, nodes
# 3. 从入口点进行影响分析(如果提供了 --entry)
tldr impact ${ENTRY} ${PATH:-src/} --depth 3
输出结构:
layers:
entry: [routes.py, cli.py, main.py] # Controllers/handlers
middle: [services.py, auth.py] # Business logic
leaf: [utils.py, helpers.py] # Utilities
call_graph:
total_edges: 142
hot_paths: [process_request → validate → authorize]
circular_deps:
- [module_a, module_b] # A imports B, B imports A
boundaries:
- name: API layer
files: [src/api/*]
calls_to: [src/services/*]
创建:thoughts/shared/research/YYYY-MM-DD-explore-{focus}.md
---
date: {ISO timestamp}
type: exploration
depth: {quick|deep|architecture}
focus: {focus area or "full"}
commit: {git hash}
---
# Codebase Exploration: {focus}
## Summary
{High-level findings}
## Structure
{File tree / codemaps}
## Architecture
{Layer analysis - for architecture depth}
## Key Components
{Important files and their roles}
## Patterns Found
{Existing patterns - for deep depth}
## References
- `path/to/file.py:line` - Description
创建:thoughts/shared/handoffs/{session}/explore-{focus}.yaml
---
type: exploration
ts: {ISO timestamp}
depth: {quick|deep|architecture}
focus: {focus area}
commit: {git hash}
---
summary: {One-line summary of findings}
structure:
entry_points: [{main.py}, {cli.py}]
key_modules: [{auth.py}, {routes.py}]
test_coverage: [{tests/}]
architecture:
layers:
entry: [{files}]
middle: [{files}]
leaf: [{files}]
circular_deps: [{pairs}]
findings:
- {key finding with file:line}
next_steps:
- {Recommended action based on exploration}
refs:
- path: {file.py}
role: {what it does}
探索技能设计用于为 /build brownfield 提供输入:
# 步骤 1:探索以理解
/explore architecture --output handoff
# 步骤 2:使用探索的上下文进行构建
/build brownfield --from-handoff thoughts/shared/handoffs/session/explore-full.yaml
当用户调用 /explore <depth> [options] 时:
depth = args[0] # quick | deep | architecture
focus = extract_option(args, "--focus")
output = extract_option(args, "--output") # handoff | doc
entry = extract_option(args, "--entry")
快速:
# 仅 tldr 命令,无智能体
tldr tree ${src_dir} --ext .py
tldr structure ${src_dir} --lang python
if [ -n "$focus" ]; then
tldr search "$focus" ${src_dir}
fi
深度:
# 1. 检查/运行初始化
if [ ! -f .claude/cache/tldr/meta.json ]; then
# Spawn onboard agent via Task tool
fi
# 2. 结构
tldr structure src/ --lang python
# 3. 研究(启动 scout 智能体)
# Task tool with subagent_type: "scout"
# Prompt: "Research patterns in ${focus:-codebase}"
# 4. 写入输出
# → doc or handoff based on --output
架构:
# 1. 架构检测
arch_output=$(tldr arch ${src_dir})
# 2. 调用图
calls_output=$(tldr calls ${src_dir})
# 3. 从入口点的影响分析(如果提供)
if [ -n "$entry" ]; then
impact_output=$(tldr impact $entry ${src_dir} --depth 3)
fi
# 4. 综合并写入输出
thoughts/shared/research/ 或交接目录| 技能 | 何时使用 |
|---|---|
| tldr-explorer | 直接 tldr 命令(由 explore 内部使用) |
| tldr-code | 特定分析命令(cfg、dfg、slice) |
| onboard | 首次项目设置(由 deep 深度使用) |
| research-codebase | 模式文档(由 deep 深度使用) |
| create_handoff | 交接格式(由 --output handoff 使用) |
tldr 未找到:
# 检查是否安装
which tldr
# 如果缺失则安装
uv tool install llm-tldr
# 或:pip install llm-tldr
未找到 Python 文件:
# 检查语言,调整 --lang
tldr structure src/ --lang typescript # 或 go, rust
架构输出为空:
# 可能需要指定 src 目录
tldr arch ./ # 当前目录
tldr arch src/ # 显式指定 src
每周安装数
227
仓库
GitHub 星标
3.6K
首次出现
Jan 22, 2026
安全审计
已安装于
opencode215
codex211
gemini-cli205
cursor204
github-copilot202
amp197
Meta-skill for exploring an internal codebase at varying depths. READ-ONLY workflow - no code changes.
/explore <depth> [options]
If the user types just /explore with no or partial arguments, guide them through this question flow. Use AskUserQuestion for each phase.
question: "How would you like to explore?"
header: "Explore"
options:
- label: "Help me choose (Recommended)"
description: "I'll ask questions to pick the right exploration depth"
- label: "Quick - fast overview"
description: "Chain: tldr tree → tldr structure (~1 min)"
- label: "Deep - comprehensive analysis"
description: "Chain: onboard → tldr → research → document (~5 min)"
- label: "Architecture - layers & dependencies"
description: "Chain: tldr arch → call graph → layer mapping (~3 min)"
Mapping:
If Answer is Unclear (via "Other"):
question: "I want to understand how deep you want to explore. Did you mean..."
header: "Clarify"
options:
- label: "Help me choose"
description: "Not sure - guide me through questions"
- label: "Quick - fast overview"
description: "Just want to see what's here"
- label: "Deep - comprehensive analysis"
description: "Need thorough understanding"
- label: "Neither - let me explain differently"
description: "I'll describe what I need"
question: "What are you trying to understand?"
header: "Goal"
options:
- label: "Get oriented in the codebase"
description: "Quick overview of structure"
- label: "Understand how something works"
description: "Deep dive into specific area"
- label: "Map the architecture"
description: "Layers, dependencies, patterns"
- label: "Find where something is"
description: "Locate specific code/functionality"
Mapping:
question: "What area should I focus on?"
header: "Focus"
options:
- label: "Entire codebase"
description: "Explore everything"
- label: "Specific directory or module"
description: "I'll specify the path"
- label: "Specific concept/feature"
description: "e.g., 'authentication', 'API routes'"
If "Specific directory" or "Specific concept" → ask follow-up for the path/keyword.
question: "What should I produce?"
header: "Output"
options:
- label: "Just tell me what you find"
description: "Interactive summary in chat"
- label: "Create a documentation file"
description: "Write to thoughts/shared/docs/"
- label: "Create handoff for implementation"
description: "Prepare context for coding agent"
Mapping:
If architecture depth selected:
question: "Where should I start the analysis?"
header: "Entry point"
options:
- label: "Auto-detect (main, cli, app)"
description: "Find common entry points"
- label: "Specific function/file"
description: "I'll specify the entry point"
Based on your answers, I'll run:
**Depth:** deep
**Focus:** "authentication"
**Output:** handoff
**Path:** src/
Proceed? [Yes / Adjust settings]
| Depth | Time | What it does |
|---|---|---|
quick | ~1 min | tldr-explorer only - fast structure overview |
deep | ~5 min | onboard + tldr-explorer + research-codebase + write doc |
architecture | ~3 min | tldr arch + call graph + layer mapping + circular dep detection |
| Option | Description | Example |
|---|---|---|
--focus "area" | Focus on specific area | --focus "auth", --focus "api" |
--output handoff | Create handoff for next agent | --output handoff |
--output doc | Create documentation file | --output doc |
# Quick structure overview
/explore quick
# Deep exploration focused on auth
/explore deep --focus "auth" --output doc
# Architecture analysis from specific entry
/explore architecture --entry "cli" --output handoff
# Quick focused exploration
/explore quick --focus "hooks"
Fast structure overview using tldr-explorer. Best for:
Steps:
tldr tree for file structuretldr structure for codemaps--focus provided, run tldr search for targeted resultsCommands:
# 1. File tree
tldr tree ${PATH:-src/} --ext .py
# 2. Code structure
tldr structure ${PATH:-src/} --lang python
# 3. Focused search (if --focus provided)
tldr search "${FOCUS}" ${PATH:-src/}
Comprehensive exploration with documentation output. Best for:
Steps:
.claude/cache/tldr/), if not run onboardSubprocess:
# 1. Onboard check
if [ ! -f .claude/cache/tldr/arch.json ]; then
# Spawn onboard agent
fi
# 2. Structure analysis
tldr structure src/ --lang python
tldr calls src/
# 3. Research patterns (via scout agent)
Task: research-codebase → "Document existing patterns in ${FOCUS:-codebase}"
# 4. Write output
→ thoughts/shared/research/YYYY-MM-DD-explore-{focus}.md
→ OR thoughts/shared/handoffs/{session}/explore-{focus}.yaml
Architecture-focused analysis with layer detection. Best for:
Steps:
tldr arch for layer detectiontldr calls for cross-file call graphCommands:
# 1. Architecture detection
tldr arch ${PATH:-src/}
# Returns: entry_layer, middle_layer, leaf_layer, circular_deps
# 2. Call graph
tldr calls ${PATH:-src/}
# Returns: edges, nodes
# 3. Impact analysis from entry point (if --entry provided)
tldr impact ${ENTRY} ${PATH:-src/} --depth 3
Output Structure:
layers:
entry: [routes.py, cli.py, main.py] # Controllers/handlers
middle: [services.py, auth.py] # Business logic
leaf: [utils.py, helpers.py] # Utilities
call_graph:
total_edges: 142
hot_paths: [process_request → validate → authorize]
circular_deps:
- [module_a, module_b] # A imports B, B imports A
boundaries:
- name: API layer
files: [src/api/*]
calls_to: [src/services/*]
Creates: thoughts/shared/research/YYYY-MM-DD-explore-{focus}.md
---
date: {ISO timestamp}
type: exploration
depth: {quick|deep|architecture}
focus: {focus area or "full"}
commit: {git hash}
---
# Codebase Exploration: {focus}
## Summary
{High-level findings}
## Structure
{File tree / codemaps}
## Architecture
{Layer analysis - for architecture depth}
## Key Components
{Important files and their roles}
## Patterns Found
{Existing patterns - for deep depth}
## References
- `path/to/file.py:line` - Description
Creates: thoughts/shared/handoffs/{session}/explore-{focus}.yaml
---
type: exploration
ts: {ISO timestamp}
depth: {quick|deep|architecture}
focus: {focus area}
commit: {git hash}
---
summary: {One-line summary of findings}
structure:
entry_points: [{main.py}, {cli.py}]
key_modules: [{auth.py}, {routes.py}]
test_coverage: [{tests/}]
architecture:
layers:
entry: [{files}]
middle: [{files}]
leaf: [{files}]
circular_deps: [{pairs}]
findings:
- {key finding with file:line}
next_steps:
- {Recommended action based on exploration}
refs:
- path: {file.py}
role: {what it does}
The explore skill is designed to feed into /build brownfield:
# Step 1: Explore to understand
/explore architecture --output handoff
# Step 2: Build with context from exploration
/build brownfield --from-handoff thoughts/shared/handoffs/session/explore-full.yaml
When user invokes /explore <depth> [options]:
depth = args[0] # quick | deep | architecture
focus = extract_option(args, "--focus")
output = extract_option(args, "--output") # handoff | doc
entry = extract_option(args, "--entry")
Quick:
# Just tldr commands, no agents
tldr tree ${src_dir} --ext .py
tldr structure ${src_dir} --lang python
if [ -n "$focus" ]; then
tldr search "$focus" ${src_dir}
fi
Deep:
# 1. Check/run onboard
if [ ! -f .claude/cache/tldr/meta.json ]; then
# Spawn onboard agent via Task tool
fi
# 2. Structure
tldr structure src/ --lang python
# 3. Research (spawn scout agent)
# Task tool with subagent_type: "scout"
# Prompt: "Research patterns in ${focus:-codebase}"
# 4. Write output
# → doc or handoff based on --output
Architecture:
# 1. Arch detection
arch_output=$(tldr arch ${src_dir})
# 2. Call graph
calls_output=$(tldr calls ${src_dir})
# 3. Impact from entry (if provided)
if [ -n "$entry" ]; then
impact_output=$(tldr impact $entry ${src_dir} --depth 3)
fi
# 4. Synthesize and write output
thoughts/shared/research/ or handoff directory| Skill | When to Use |
|---|---|
| tldr-explorer | Direct tldr commands (used internally by explore) |
| tldr-code | Specific analysis commands (cfg, dfg, slice) |
| onboard | First-time project setup (used by deep depth) |
| research-codebase | Pattern documentation (used by deep depth) |
| create_handoff | Handoff format (used by --output handoff) |
tldr not found:
# Check if installed
which tldr
# Install if missing
uv tool install llm-tldr
# or: pip install llm-tldr
No Python files found:
# Check language, adjust --lang
tldr structure src/ --lang typescript # or go, rust
Empty architecture output:
# May need to specify src directory
tldr arch ./ # Current directory
tldr arch src/ # Explicit src
Weekly Installs
227
Repository
GitHub Stars
3.6K
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode215
codex211
gemini-cli205
cursor204
github-copilot202
amp197
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
107,800 周安装
--entry "func" | Start from specific entry point | --entry "main", --entry "process_request" |