terminal

Local shell copilot for command planning, safe execution, preview-first workflows, output summarization, privacy-aware history controls, and step-by-step terminal help. Use whenever the user wants to run terminal commands, inspect files, debug shell issues, automate local tasks, or translate natural language into shell actions. Prefer safe preview before mutation. Require explicit confirmation for destructive commands. Local-only.

3,891 stars

Best use case

terminal is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Local shell copilot for command planning, safe execution, preview-first workflows, output summarization, privacy-aware history controls, and step-by-step terminal help. Use whenever the user wants to run terminal commands, inspect files, debug shell issues, automate local tasks, or translate natural language into shell actions. Prefer safe preview before mutation. Require explicit confirmation for destructive commands. Local-only.

Teams using terminal 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

$curl -o ~/.claude/skills/terminal/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/agistack/terminal/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/terminal/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How terminal Compares

Feature / AgentterminalStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Local shell copilot for command planning, safe execution, preview-first workflows, output summarization, privacy-aware history controls, and step-by-step terminal help. Use whenever the user wants to run terminal commands, inspect files, debug shell issues, automate local tasks, or translate natural language into shell actions. Prefer safe preview before mutation. Require explicit confirmation for destructive commands. Local-only.

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

SKILL.md Source

# Terminal

Local shell copilot. Plan clearly, run carefully.

## Core Philosophy
1. Translate intent into executable shell steps.
2. Prefer preview and inspection before mutation.
3. Require explicit confirmation for destructive operations.
4. Summarize results in human language after execution.
5. Offer privacy-aware history controls for sensitive workflows.

## Runtime Requirements
- Python 3 must be available as `python3`
- Standard shell utilities should be available in the local environment
- No external packages required

## Safety Model
- Local-only execution
- No external credential requests
- No hidden network activity
- Destructive operations require explicit confirmation
- Prefer read-only inspection first
- Blocked and previewed commands are recorded in local history
- Risk detection covers destructive, privilege-escalation, remote-fetch, and code-execution patterns

## Privacy Controls
- History is stored locally only
- History file permissions are restricted to the local user when possible
- Use `--preview` to inspect before execution
- Use `--no-store-output` to avoid storing stdout/stderr in history for sensitive commands
- Use `--redact-display` to mask sensitive-looking values in displayed output
- Sensitive-looking tokens are redacted before history is written

## Storage
All local data is stored only under:
- `~/.openclaw/workspace/memory/terminal/history.json`

No cloud sync. No third-party APIs. No telemetry.

## Workflows
- **Plan command**: Turn user intent into a safe shell command suggestion
- **Preview risk**: Explain command effects before execution
- **Execute**: Run a local command and capture stdout/stderr
- **Summarize**: Explain what happened in plain language
- **History**: Save executed, previewed, and blocked command runs locally

## Scripts
| Script | Purpose |
|---|---|
| `init_storage.py` | Initialize local terminal history storage |
| `plan_command.py` | Generate a shell command from user intent |
| `run_command.py` | Execute or preview a local command with safety checks and privacy controls |
| `summarize_result.py` | Summarize command output in plain language |
| `show_history.py` | Show recent command history |

Related Skills

terminal-command-execution

3891
from openclaw/skills

Execute terminal commands safely and reliably with clear pre-checks, output validation, and recovery steps. Use when users ask to run shell/CLI commands, inspect system state, manage files, install dependencies, start services, debug command failures, or automate command-line workflows.

DevOps & Infrastructure

ghostling-libghostty-terminal

3819
from openclaw/skills

Build minimal terminal emulators using the libghostty-vt C API with Raylib for windowing and rendering

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation