跳到正文
cccskills
免费在 GitHub 公开

research

Isolated codebase exploration that preserves your main context. Use when you need to understand code structure, trace call paths, or gather evidence before making changes. Spawns an explorer subagent.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Research Skill

Explore the codebase without polluting your main context.

When to use

  • Need to understand how a module works before changing it
  • Need to find where a pattern is used across the codebase
  • Need to trace a call path end-to-end
  • Need to gather evidence before proposing a plan

Protocol

Option A — Spawn an explorer subagent (recommended)

"Spawn an explorer subagent to [describe the research goal]. Return a structured summary with: files examined, relevant symbols, call path trace, and key findings."

The explorer runs in read-only mode in isolated context — your main thread stays clean.

Option B — Inline research (for quick lookups)

Find files matching a pattern

find . -name '*.ts' -path '*/auth/*' | head -20

Search for symbol usage

grep -rn --color=never 'functionName' --include='*.ts' . | head -30

Trace a call path

# 1. Find where the function is defined
grep -rn --color=never 'def functionName\|function functionName\|functionName =' . | head -10

# 2. Find all callers
grep -rn --color=never 'functionName(' . | grep -v 'def functionName\|function functionName' | head -20

Read a specific file section

Use file reading tools — do NOT cat the whole file.

Research Output Format

After research, summarize findings:

## Research Summary: <topic>

### Files examined
- path/to/file.ts — reason

### Key symbols found
- SymbolName (file:line) — what it does

### Call path trace
Entry → ServiceA.method → ServiceB.method → DB query

### Key findings
1. Finding 1
2. Finding 2

### Open questions
- ?

Rules

  • Keep research scope tight — stop when you have enough evidence
  • Do NOT modify files during research
  • Save verbose intermediate output to claude/tasks/research-notes.md (not in main context)

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

ask

免费

Route a codebase question to the right tool — structural graph, semantic search, or risk analysis. Use when you need to find or understand code without knowing exact file names.

中文简介正在准备中。当前显示原文说明。

brain-bootstrap/claude-code-brain-bootstrap112026年4月25日 更新

bootstrap

免费

Auto-configure CLAUDE.md and claude/ knowledge docs for a new project. Use when setting up Brain Bootstrap in a new repository. Discovers the codebase, fills in templates, and writes project-specific configuration.

中文简介正在准备中。当前显示原文说明。

brain-bootstrap/claude-code-brain-bootstrap112026年4月25日 更新

Use before any new feature, component, or behavioral change — when you need to explore requirements and design before writing code

中文简介正在准备中。当前显示原文说明。

brain-bootstrap/claude-code-brain-bootstrap112026年4月25日 更新

careful

免费

Activate safety guards for the session. Use /careful before critical operations — blocks rm -rf, DROP TABLE, git push --force, kubectl delete namespace, docker system prune via PreToolUse hook.

中文简介正在准备中。当前显示原文说明。

brain-bootstrap/claude-code-brain-bootstrap112026年4月25日 更新

changelog

免费

Generate a user-facing changelog from git commits — categorize, filter noise, translate to user language. Runs in isolated fork context.

中文简介正在准备中。当前显示原文说明。

brain-bootstrap/claude-code-brain-bootstrap112026年4月25日 更新

Save session state before context gets full or before ending. Writes current task state, branch, and loaded docs to claude/tasks/todo.md so the next session can resume cleanly.

中文简介正在准备中。当前显示原文说明。

brain-bootstrap/claude-code-brain-bootstrap112026年4月25日 更新

查看 brain-bootstrap 的全部技能

报告此技能的问题