bambu-studio-ai
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Delegate coding tasks to Claude Code CLI via background process. Use when: building features, reviewing PRs, refactoring codebases, or iterative coding that needs file exploration. Supports interactive PTY mode for confirmations/permissions and headless pipe mode for automation. NOT for: simple one-liner fixes (just edit), reading code (use read tool), or any work in ~/.openclaw/ workspace.
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install atelypham/claude-code-cliInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
Delegate coding tasks to the Claude Code CLI via background process with PTY or headless pipe mode.
Claude Code is an interactive terminal application that needs a pseudo-terminal (PTY). Without PTY, output breaks or the agent hangs.
Always use pty:true for interactive mode:
# ✅ Correct - with PTY
exec pty:true command:"claude 'Your prompt'"
# ❌ Wrong - no PTY, agent may break
exec command:"claude 'Your prompt'"
For tasks where Claude Code may ask confirmations, need input, or show permission prompts.
# Foreground (waits for completion)
exec pty:true workdir:~/project command:"claude 'Add dark mode toggle'"
# Background (returns sessionId)
exec pty:true workdir:~/project background:true command:"claude 'Build REST API for todos'"
For automation, scripting, CI-like usage. Uses -p flag for non-interactive.
# Simple one-shot
exec command:"claude -p 'Explain what src/main.ts does' --output-format json"
# With structured output validation
exec command:"claude -p 'List all exported functions in src/' --output-format json --json-schema '{\"type\":\"object\",\"properties\":{\"functions\":{\"type\":\"array\",\"items\":{\"type\":\"string\"}}}}'"
# Budget-capped automation
exec command:"claude -p 'Refactor auth module' --max-budget-usd 5.00 --output-format json"
# Real-time streaming output (JSON chunks as they arrive)
exec command:"claude -p 'Build a helper function' --output-format stream-json"
| Parameter | Type | Description |
|---|---|---|
command |
string | The shell command to run |
pty... |
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
An OpenClaw skill for delegating coding tasks to the Claude Code CLI.
-p flag for automation, CI, structured JSON output--continue / --resume SESSION_ID across conversations--max-budget-usd for unattended runs--allowedTools "Bash(git:*,npm:*),Read,Edit"
openclaw system event wake trigger on completionopenclaw skills install claude-code-cli
git clone https://github.com/AtelyPham/openclaw-claude-code-skill.git ~/clawd/claude-code-cli
openclaw skills install --local ~/clawd/claude-code-cli
claude binary)pty:true
MIT
# Claude Code Skill
Delegate coding tasks to the **Claude Code CLI** via background process with PTY or headless pipe mode.
## PTY Mode Required (Interactive)
Claude Code is an **interactive terminal application** that needs a pseudo-terminal (PTY). Without PTY, output breaks or the agent hangs.
**Always use `pty:true`** for interactive mode:
```bash
# ✅ Correct - with PTY
exec pty:true command:"claude 'Your prompt'"
# ❌ Wrong - no PTY, agent may break
exec command:"claude 'Your prompt'"
```
---
## Two Modes
### 1. Interactive PTY Mode
For tasks where Claude Code may ask confirmations, need input, or show permission prompts.
```bash
# Foreground (waits for completion)
exec pty:true workdir:~/project command:"claude 'Add dark mode toggle'"
# Background (returns sessionId)
exec pty:true workdir:~/project background:true command:"claude 'Build REST API for todos'"
```
### 2. Headless Pipe Mode
For automation, scripting, CI-like usage. Uses `-p` flag for non-interactive.
```bash
# Simple one-shot
exec command:"claude -p 'Explain what src/main.ts does' --output-format json"
# With structured output validation
exec command:"claude -p 'List all exported functions in src/' --output-format json --json-schema '{\"type\":\"object\",\"properties\":{\"functions\":{\"type\":\"array\",\"items\":{\"type\":\"string\"}}}}'"
# Budget-capped automation
exec command:"claude -p 'Refactor auth module' --max-budget-usd 5.00 --output-format json"
# Real-time streaming output (JSON chunks as they arrive)
exec command:"claude -p 'Build a helper function' --output-format stream-json"
```
---
## Exec & Process Tool Reference
### Exec Tool Parameters
| Parameter | Type | Description |
| ------------ | ------- | --------------------------------------------------------------------------- |
| `command` | string | The shell command to run |
| `pty`...# claude-code-cli An [OpenClaw](https://github.com/openclaw/openclaw) skill for delegating coding tasks to the [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code). ## Features - **Interactive PTY mode** — full terminal with confirmations, permissions, input - **Headless pipe mode** — `-p` flag for automation, CI, structured JSON output - **Session continuity** — `--continue` / `--resume SESSION_ID` across conversations - **Parallel workflows** — git worktrees + multiple Claude Code processes - **PR reviews** — safe temp-dir patterns, never in live workspace - **Budget-capped automation** — `--max-budget-usd` for unattended runs - **Granular tool restrictions** — `--allowedTools "Bash(git:*,npm:*),Read,Edit"` - **Auto-notify** — `openclaw system event` wake trigger on completion - **HANDOFF.md pattern** — context continuity across long sessions - **Fan-out / Writer-Reviewer** — advanced parallel session patterns ## Install ### From ClawHub ```bash openclaw skills install claude-code-cli ``` ### Local ```bash git clone https://github.com/AtelyPham/openclaw-claude-code-skill.git ~/clawd/claude-code-cli openclaw skills install --local ~/clawd/claude-code-cli ``` ## Requirements - [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code) (`claude` binary) - OpenClaw with exec tool that supports `pty:true` ## License MIT
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Search and hire real humans for tasks — photography, delivery, research, and more
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...
Reusable skill templates for OpenClaw AI agents. Templates for API integration, data processing, web scraping, CLI tools, and file processing.