skill-claude-code
Use when the user asks to run Claude Code CLI (claude) for code analysis, refactoring, debugging, or automated edits, or references Claude Code workflows, sessions, permissions, or CLI flags.
Best use case
skill-claude-code is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when the user asks to run Claude Code CLI (claude) for code analysis, refactoring, debugging, or automated edits, or references Claude Code workflows, sessions, permissions, or CLI flags.
Teams using skill-claude-code should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/skill-claude-code/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How skill-claude-code Compares
| Feature / Agent | skill-claude-code | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when the user asks to run Claude Code CLI (claude) for code analysis, refactoring, debugging, or automated edits, or references Claude Code workflows, sessions, permissions, or CLI flags.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Claude Code ## Overview Run Claude Code from the terminal to analyze, plan, refactor, or edit codebases via the `claude` CLI. Default to non-interactive print mode in this environment and summarize results back to the user. ## Quick Start 1. Use non-interactive (print) mode: `claude -p "prompt"` for one-shot tasks. Interactive sessions are disabled here due to flaky TTY prompts. 2. Select model (ask the user). Default suggestion: `opus`. 3. Choose permissions and scope. 4. Run the command, capture output, and summarize key results and next steps. ## Workflow ### 1) Ask for model and session intent - Ask the user which model to use. - If the user doesn't specify, propose `--model opus` and confirm. - `--model` accepts `sonnet` or `opus` aliases, or a full model name. ### 2) Pick the right command form Non-interactive / print mode (default): - `claude -p "prompt"` to run a single request and exit. - `cat file | claude -p "prompt"` to pipe content in. - Use `--output-format json` or `--output-format stream-json` for machine-readable output when scripting. - Use `--max-turns N` to limit agentic turns in print mode. - Use `--input-format` for `text` or `stream-json` inputs. - Use `--no-session-persistence` to avoid saving sessions in print mode. - Use `--include-partial-messages` with `--output-format stream-json` to emit partial streaming events. Session management (print mode only): - Continue the most recent session in print mode: `claude -c -p "prompt"`. - Resume a specific session in print mode: `claude -r "<session-id>" -p "prompt"`. - `--fork-session` creates a new session ID when resuming. ### 3) Permissions and safety - Prefer default permission prompts. Only use `--dangerously-skip-permissions` if the user explicitly approves and the task is low-risk or sandboxed. - Use `--permission-mode` to start in a specific mode and `--allow-dangerously-skip-permissions` only to permit the bypass option. - For larger changes, explore first, then plan, then implement. - Use `--allowedTools`/`--disallowedTools` or `--tools` to control tool access when needed. ### 4) Run, summarize, and follow up - Execute the command, capture stdout (and stderr if needed). - Summarize results, list changes or findings, and ask the user for next steps. ## Notes Assume the user already has Claude Code installed and configured. If `claude` is not found, report the error and ask the user to fix their environment before retrying. When prompting, prefer rich context: reference files with `@` and pipe logs. ## Troubleshooting If the prompt passed to `--print` / `-p` is misinterpreted (e.g., flags inside the prompt), use `--` before the prompt or pipe it via stdin: - `claude -p -- "prompt with -dashes or --flags"` - `echo "prompt" | claude -p`
Related Skills
video-to-claude
Analyze videos with Gemini and get build instructions for Claude. Supports YouTube URLs, GIFs, screen recordings, and local video files. Use when user shares a video/GIF and wants to understand how to build it, clone a UI, reverse engineer a product, or extract tutorial steps. Triggers on "watch this video", "clone this", "reverse engineer", "how do I build this", "analyze this demo".
omega-claude-cli
Use when the user wants to use Claude (Claude Code CLI) for analysis or brainstorming. Triggers on "use Claude", "ask Claude", "analyze with Claude", "brainstorm with Claude".
developing-claude-code-plugins
Build, test, and distribute Claude Code plugins with slash commands, agents, skills, hooks, MCP servers, and LSP servers. MUST be loaded when creating, reviewing, debugging, or distributing plugins. Use PROACTIVELY when user mentions plugins, extensions, marketplaces, or wants to add custom commands/agents to Claude Code.
claude-skill-creator
Guide for creating effective Claude Code skills with proper YAML frontmatter, directory structure, and best practices. Use when creating new skills, updating existing skills, or learning about skill development.
claude-settings-audit
Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.
claude-plan
Anthropic 風格的專業計畫管理 Skill - 自然語言驅動、預設並行、全自動 GitHub 整合
claude-md-editor
Edit and maintain CLAUDE.md and project documentation files. Use when modifying documentation, asking about best practices, or performing documentation maintenance tasks.
claude-improve-config
Self-reflect on the current session to identify mistakes and propose improvements to .claude configuration (CLAUDE.md, hooks, skills).
claude-hooks-reference-2026
Complete reference for Claude Code hooks system (January 2026). Use when creating hooks, understanding hook events, matchers, exit codes, JSON output control, environment variables, plugin hooks, or implementing hook scripts.
claude-ecosystem
Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles creation), CLAUDE.md (project instructions, optimization). Actions: configure, troubleshoot, create, deploy, integrate, optimize Claude Code. Keywords: Claude Code, Anthropic, CLI tool, slash command, MCP server, Agent Skill, hook, plugin, CI/CD, enterprise, CLAUDE.md, agentic coding, agent, skill, output-style, SKILL.md, subagent, Task tool, project instructions, token optimization. Use when: learning Claude Code features, configuring settings, creating skills/agents/hooks, setting up MCP servers, troubleshooting issues, CI/CD integration, initializing or optimizing CLAUDE.md files.
claude-code
Claude Code CLI and development environment. Use for Claude Code features, tools, workflows, MCP integration, configuration, and AI-assisted development.
claude-code-slash-commands
This skill should be used when the user asks to "create a command", "write a slash command", "build a plugin command", or wants to add custom commands to Claude Code.