npx skills add https://github.com/parcadei/continuous-claude-v3 --skill research你的任务是跨代码库进行全面研究,通过生成并行子代理并综合它们的发现来回答用户问题。
当调用此命令时,请回复:
我已准备好研究代码库。请提供你的研究问题或感兴趣的领域,我将通过探索相关组件和连接来彻底分析它。
然后等待用户的研究查询。
首先阅读任何直接提及的文件:
分析并分解研究问题:
生成并行子代理任务进行全面研究:
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
用于代码库研究:
* 使用 **scout** 代理进行全面的代码库探索(结合定位、分析和模式查找)
重要:所有代理都是记录员,不是评论家。他们将描述存在什么,而不建议改进或发现问题。
用于 thoughts 目录:
* 使用 **thoughts-locator** 代理来发现有关该主题存在哪些文档
* 使用 **thoughts-analyzer** 代理从特定文档中提取关键见解(仅限最相关的文档)
用于网络研究(仅当用户明确要求时):
* 使用 **web-search-researcher** 代理获取外部文档和资源
* 如果你使用网络研究代理,请指示他们返回带有其发现的链接,并请在你的最终报告中包含这些链接
用于 Linear 票据(如果相关):
* 使用 **linear-ticket-reader** 代理获取特定票据的完整详细信息
* 使用 **linear-searcher** 代理查找相关票据或历史上下文
关键是智能地使用这些代理:
* 从定位代理开始,以查找存在什么
* 然后对最有希望的发现使用分析代理,以记录它们如何工作
* 当它们搜索不同内容时,并行运行多个代理
* 每个代理都知道其工作 - 只需告诉它你在寻找什么
* 不要写关于如何搜索的详细提示 - 代理已经知道
* 提醒代理他们是记录员,不是评估员或改进者
4. 等待所有子代理完成并综合发现:
* 重要:在继续之前等待所有子代理任务完成
* 编译所有子代理结果(包括代码库和 thoughts 发现)
* 优先将实时代码库发现作为主要事实来源
* 使用 thoughts/ 发现作为补充的历史上下文
* 连接跨不同组件的发现
* 包含具体的文件路径和行号以供参考
* 验证所有 thoughts/ 路径是否正确(例如,个人文件使用 thoughts/allison/ 而不是 thoughts/shared/)
* 突出显示模式、连接和架构决策
* 用具体证据回答用户的具体问题
5. 收集研究文档的元数据:
* 运行 `hack/spec_metadata.sh` 脚本以生成所有相关元数据
* 文件名:`thoughts/shared/research/YYYY-MM-DD-ENG-XXXX-description.md`
* 格式:`YYYY-MM-DD-ENG-XXXX-description.md`,其中:
* YYYY-MM-DD 是今天的日期
* ENG-XXXX 是票据编号(如果没有票据则省略)
* description 是研究主题的简短 kebab-case 描述
* 示例:
* 有票据:`2025-01-08-ENG-1478-parent-child-tracking.md`
* 无票据:`2025-01-08-authentication-flow.md`
6. 生成研究文档:
* 确保目录存在:`mkdir -p thoughts/shared/research`
* 使用步骤 4 中收集的元数据
* 使用 YAML 前言后跟内容来构建文档:
---
date: [当前日期和时间,带时区,ISO 格式]
researcher: [来自 thoughts 状态的研究员姓名]
git_commit: [当前提交哈希]
branch: [当前分支名称]
repository: [仓库名称]
topic: "[用户的问题/主题]"
tags: [research, codebase, relevant-component-names]
status: complete
last_updated: [当前日期,YYYY-MM-DD 格式]
last_updated_by: [研究员姓名]
---
# 研究:[用户的问题/主题]
**日期**:[来自步骤 4 的当前日期和时间,带时区]
**研究员**:[来自 thoughts 状态的研究员姓名]
**Git 提交**:[来自步骤 4 的当前提交哈希]
**分支**:[来自步骤 4 的当前分支名称]
**仓库**:[仓库名称]
## 研究问题
[原始用户查询]
## 摘要
[高级别文档,描述发现的内容,通过描述存在什么来回答用户的问题]
## 详细发现
### [组件/领域 1]
- 存在内容的描述 ([file.ext:line](link))
- 它如何连接到其他组件
- 当前实现细节(不进行评估)
### [组件/领域 2]
...
## 代码引用
- `path/to/file.py:123` - 存在内容的描述
- `another/file.ts:45-67` - 代码块的描述
## 架构文档
[在代码库中找到的当前模式、约定和设计实现]
## 历史上下文(来自 thoughts/)
[来自 thoughts/ 目录的相关见解,附有引用]
- `thoughts/shared/something.md` - 关于 X 的历史决策
- `thoughts/local/notes.md` - 过去对 Y 的探索
注意:路径排除 "searchable/",即使在那里找到
## 相关研究
[指向 thoughts/shared/research/ 中其他研究文档的链接]
## 开放性问题
[任何需要进一步调查的领域]
7. 添加 GitHub 永久链接(如果适用):
* 检查是否在主分支上或提交是否已推送:`git branch --show-current` 和 `git status`
* 如果在 main/master 上或已推送,则生成 GitHub 永久链接:
* 获取仓库信息:`gh repo view --json owner,name`
* 创建永久链接:`https://github.com/{owner}/{repo}/blob/{commit}/{file}#L{line}`
* 在文档中用永久链接替换本地文件引用
8. 呈现发现:
* 向用户呈现发现的简明摘要
* 包含关键文件引用以便轻松导航
* 询问他们是否有后续问题或需要澄清
9. 处理后续问题:
* 如果用户有后续问题,请附加到同一研究文档
* 更新前言字段 `last_updated` 和 `last_updated_by` 以反映更新
* 在前言中添加 `last_updated_note: "为[简短描述]添加了后续研究"`
* 添加新部分:`## 后续研究 [时间戳]`
* 根据需要生成新的子代理以进行额外调查
* 继续更新文档并同步
thoughts/searchable/allison/old_stuff/notes.md → thoughts/allison/old_stuff/notes.mdthoughts/searchable/shared/prs/123.md → thoughts/shared/prs/123.mdthoughts/searchable/global/shared/templates.md → thoughts/global/shared/templates.mdlast_updated、git_commit)每周安装次数
204
仓库
GitHub 星标数
3.6K
首次出现
2026年1月22日
安全审计
安装于
opencode197
codex194
gemini-cli193
cursor191
github-copilot190
amp186
You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings.
When this command is invoked, respond with:
I'm ready to research the codebase. Please provide your research question or area of interest, and I'll analyze it thoroughly by exploring relevant components and connections.
Then wait for the user's research query.
Read any directly mentioned files first:
Analyze and decompose the research question:
Spawn parallel sub-agent tasks for comprehensive research:
For codebase research:
* Use the **scout** agent for comprehensive codebase exploration (combines locating, analyzing, and pattern finding)
IMPORTANT : All agents are documentarians, not critics. They will describe what exists without suggesting improvements or identifying issues.
For thoughts directory:
* Use the **thoughts-locator** agent to discover what documents exist about the topic
* Use the **thoughts-analyzer** agent to extract key insights from specific documents (only the most relevant ones)
For web research (only if user explicitly asks):
* Use the **web-search-researcher** agent for external documentation and resources
* IF you use web-research agents, instruct them to return LINKS with their findings, and please INCLUDE those links in your final report
For Linear tickets (if relevant):
* Use the **linear-ticket-reader** agent to get full details of a specific ticket
* Use the **linear-searcher** agent to find related tickets or historical context
The key is to use these agents intelligently:
* Start with locator agents to find what exists
* Then use analyzer agents on the most promising findings to document how they work
* Run multiple agents in parallel when they're searching for different things
* Each agent knows its job - just tell it what you're looking for
* Don't write detailed prompts about HOW to search - the agents already know
* Remind agents they are documenting, not evaluating or improving
4. Wait for all sub-agents to complete and synthesize findings:
* IMPORTANT: Wait for ALL sub-agent tasks to complete before proceeding
* Compile all sub-agent results (both codebase and thoughts findings)
* Prioritize live codebase findings as primary source of truth
* Use thoughts/ findings as supplementary historical context
* Connect findings across different components
* Include specific file paths and line numbers for reference
* Verify all thoughts/ paths are correct (e.g., thoughts/allison/ not thoughts/shared/ for personal files)
* Highlight patterns, connections, and architectural decisions
* Answer the user's specific questions with concrete evidence
5. Gather metadata for the research document:
* Run the `hack/spec_metadata.sh` script to generate all relevant metadata
* Filename: `thoughts/shared/research/YYYY-MM-DD-ENG-XXXX-description.md`
* Format: `YYYY-MM-DD-ENG-XXXX-description.md` where:
* YYYY-MM-DD is today's date
* ENG-XXXX is the ticket number (omit if no ticket)
* description is a brief kebab-case description of the research topic
* Examples:
* With ticket: `2025-01-08-ENG-1478-parent-child-tracking.md`
* Without ticket: `2025-01-08-authentication-flow.md`
6. Generate research document:
* Ensure directory exists: `mkdir -p thoughts/shared/research`
* Use the metadata gathered in step 4
* Structure the document with YAML frontmatter followed by content:
---
date: [Current date and time with timezone in ISO format]
researcher: [Researcher name from thoughts status]
git_commit: [Current commit hash]
branch: [Current branch name]
repository: [Repository name]
topic: "[User's Question/Topic]"
tags: [research, codebase, relevant-component-names]
status: complete
last_updated: [Current date in YYYY-MM-DD format]
last_updated_by: [Researcher name]
---
# Research: [User's Question/Topic]
**Date**: [Current date and time with timezone from step 4]
**Researcher**: [Researcher name from thoughts status]
**Git Commit**: [Current commit hash from step 4]
**Branch**: [Current branch name from step 4]
**Repository**: [Repository name]
## Research Question
[Original user query]
## Summary
[High-level documentation of what was found, answering the user's question by describing what exists]
## Detailed Findings
### [Component/Area 1]
- Description of what exists ([file.ext:line](link))
- How it connects to other components
- Current implementation details (without evaluation)
### [Component/Area 2]
...
## Code References
- `path/to/file.py:123` - Description of what's there
- `another/file.ts:45-67` - Description of the code block
## Architecture Documentation
[Current patterns, conventions, and design implementations found in the codebase]
## Historical Context (from thoughts/)
[Relevant insights from thoughts/ directory with references]
- `thoughts/shared/something.md` - Historical decision about X
- `thoughts/local/notes.md` - Past exploration of Y
Note: Paths exclude "searchable/" even if found there
## Related Research
[Links to other research documents in thoughts/shared/research/]
## Open Questions
[Any areas that need further investigation]
7. Add GitHub permalinks (if applicable):
* Check if on main branch or if commit is pushed: `git branch --show-current` and `git status`
* If on main/master or pushed, generate GitHub permalinks:
* Get repo info: `gh repo view --json owner,name`
* Create permalinks: `https://github.com/{owner}/{repo}/blob/{commit}/{file}#L{line}`
* Replace local file references with permalinks in the document
8. Present findings:
* Present a concise summary of findings to the user
* Include key file references for easy navigation
* Ask if they have follow-up questions or need clarification
9. Handle follow-up questions:
* If the user has follow-up questions, append to the same research document
* Update the frontmatter fields `last_updated` and `last_updated_by` to reflect the update
* Add `last_updated_note: "Added follow-up research for [brief description]"` to frontmatter
* Add a new section: `## Follow-up Research [timestamp]`
* Spawn new sub-agents as needed for additional investigation
* Continue updating the document and syncing
Weekly Installs
204
Repository
GitHub Stars
3.6K
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykFail
Installed on
opencode197
codex194
gemini-cli193
cursor191
github-copilot190
amp186
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
111,800 周安装
thoughts/searchable/allison/old_stuff/notes.md → thoughts/allison/old_stuff/notes.mdthoughts/searchable/shared/prs/123.md → thoughts/shared/prs/123.mdthoughts/searchable/global/shared/templates.md → thoughts/global/shared/templates.mdlast_updated, git_commit)