跳到正文
cccskills
免费在 GitHub 公开

filesystem

File system operations guidance - read, write, search, and manage files using Claude Code's built-in tools.

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(10)

  • SKILL.md4.3 KB
  • commands/filesystem.md110 B
  • hooks/post-execute.cjs298 B
  • hooks/pre-execute.cjs415 B
  • references/research-requirements.md378 B
  • rules/filesystem.md410 B
  • schemas/input.schema.json572 B
  • schemas/output.schema.json254 B
  • scripts/main.cjs1.1 KB
  • templates/implementation-template.md184 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Filesystem Skill

<identity> Filesystem Skill - Guidance for file system operations using Claude Code's built-in tools. Read, write, search, and manage files efficiently. </identity> <capabilities> - Reading single or multiple files - Creating or modifying files - Searching for files by pattern - Searching file contents - Directory navigation </capabilities> <instructions> <execution_process>

Claude Code Built-in Tools

Reading Files

Read Tool: Read file contents

Read file_path="/path/to/file.txt"

Options:

  • offset: Start line (for large files)
  • limit: Number of lines to read

Finding Files

Glob Tool: Find files by pattern

Glob pattern="**/*.ts"

Common patterns:

  • **/*.ts - All TypeScript files
  • src/**/*.tsx - React components in src
  • **/test*.js - Test files anywhere

Searching Content

Primary Search: Use pnpm search:code "query" or Skill({ skill: 'ripgrep' }) for content searching. The built-in Grep tool is fallback-only.

Grep Tool: Search file contents (fallback only — prefer pnpm search:code or ripgrep skill first)

Grep pattern="function myFunc" path="/src"

Options:

  • output_mode: "content", "files_with_matches", or "count"
  • -A, -B, -C: Context lines

Writing Files

Write Tool: Create or overwrite files

Write file_path="/path/to/file.txt" content="..."

Edit Tool: Modify existing files

Edit file_path="/path/to/file.txt" old_string="..." new_string="..."

Directory Operations

Bash Tool: For directory operations

# List directory
ls -la /path/to/dir

# Create directory
mkdir -p /path/to/new/dir

# Move/rename
mv /old/path /new/path

</execution_process>

<best_practices>

Common Workflows

Reading Multiple Files

# Read files in parallel (multiple Read calls in one message)
Read file_path="/src/app.ts"
Read file_path="/src/config.ts"
Read file_path="/src/utils.ts"

Search and Read

# 1. Find files
Glob pattern="**/*.config.ts"

# 2. Read matching files
Read file_path="/path/from/glob/result"

Find and Replace

# 1. Search for pattern
Grep pattern="oldFunction" path="/src"

# 2. Edit each file
Edit file_path="/src/file.ts" old_string="oldFunction" new_string="newFunction"

Best Practices

  1. Read Before Edit: Always read a file before editing it
  2. Use Glob Over Bash: Prefer Glob to find for file discovery
  3. Search Tool Hierarchy: Use pnpm search:code or Skill({ skill: 'ripgrep' }) first; use the Grep tool as fallback over raw bash grep only
  4. Parallel Reads: Read multiple files in one message for speed
  5. Verify Changes: Read file after editing to verify

</best_practices> </instructions>

<examples> <usage_example> **Find and read all TypeScript files**:
Glob pattern="src/**/*.ts"
# Then read the results
Read file_path="/src/app.ts"

</usage_example>

<usage_example> Search for a function and edit it:

Grep pattern="export function oldName" path="/src"
# Found in /src/utils.ts:23

Edit file_path="/src/utils.ts" old_string="export function oldName" new_string="export function newName"

</usage_example> </examples>

Rules

  • Always read files before editing
  • Use built-in tools (Read, Glob, Grep) instead of bash equivalents
  • Verify changes after editing

Memory Protocol (MANDATORY)

Before starting:

cat .claude/context/memory/learnings.md

After completing:

  • New pattern -> .claude/context/memory/learnings.md
  • Issue found -> .claude/context/memory/issues.md
  • Decision made -> .claude/context/memory/decisions.md

ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.

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

Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio432026年7月14日 更新

查看 oimiragieo 的全部技能

报告此技能的问题