OpenClaw Boot Camp

Auto-generates a CLI reference doc so your agent stops guessing OpenClaw commands and starts working. Discovers all commands, subcommands, and flags from you...

Security Scan

The skill's code and instructions are coherent with its stated purpose (discover local OpenClaw CLI structure and write a reference file); it does not request credentials or perform network installs, though you should review/output files before trusting them.

Purpose & Capability

Name/description match the code: the script parses the OpenClaw bash completion and `openclaw --help`, then writes a markdown reference into the OpenClaw workspace. No unrelated credentials, binaries, or services are requested.

Instruction Scope

Instructions and script operate locally (read completion file, run `openclaw --help`, optionally run `openclaw completion --shell bash`) and write output to ~/.openclaw/workspace/notes. Enrich mode mentions agent-driven web searches (docs.openclaw.ai) — the script itself does not appear to call external endpoints, but using Enrich will involve your agent/web search capability and could expose generated/related data to that agent or external docs.

Install Mechanism

No install spec; this is an instruction-only skill with a single bash script. Nothing is downloaded from external URLs or written outside the user's OpenClaw workspace.

Credentials

The script optionally respects OPENCLAW_STATE_DIR but does not require any secrets, tokens, or unrelated environment variables. It writes to the OpenClaw directory (~/ .openclaw by default), which is proportional to its function.

Persistence & Privilege

always:false and no modifications to other skills or global agent settings. The script writes/overwrites files in the user's OpenClaw workspace only and offers overwrite/keep-both choices.

Assessment

This script appears to do exactly what it says: parse your OpenClaw completion/help output and produce a Markdown reference in ~/.openclaw/workspace/notes. Before running it: 1) Review the bootcamp.sh file yourself (it’s included) to confirm behavior. 2) Backup any existing reference docs if you care about preserving them (the script offers overwrite/keep options). 3) Run it as a normal user (not root). 4) If you enable 'Enrich' or let an agent perform enrichment, be aware your agent may query external docs/search and could send some command/flag text to external services — avoid Enrich if you don’t want that data shared. 5) Ensure the installed openclaw binary is trusted (the script invokes it). Overall the skill is internally consistent and low-risk, but standard caution about running third-party scripts still applies.

OpenClaw Boot Camp — Agent CLI Training

Every OpenClaw agent wastes tokens fumbling with CLI syntax. The --help command is broken on most subcommands. Flags get guessed wrong. Commands that don't exist get tried.

Boot Camp fixes that by discovering your actual CLI commands and generating a clean reference your agent can read.

Usage

bash bootcamp.sh

Follow the wizard. Your agent gets a cheat sheet at ~/.openclaw/workspace/notes/openclaw-cli-reference.md.

Modes

• Local Only (Quickest) — Discovers commands from your CLI. No internet, no API calls, no token cost.
• Local + Enrich (Recommended) — Local discovery + searches docs.openclaw.ai for your version. Still free.

What It Discovers

• All top-level commands with descriptions
• Every subcommand per command
• Every flag per command
• Which commands support --json
• Doc links for key commands (Enrich mode)
• Tips and gotchas baked in

Non-Interactive Mode

bash bootcamp.sh --yes --enrich

Version Management

Detects existing reference docs and offers to overwrite or keep both versions side-by-side.

Requirements

• OpenClaw installed and in PATH
• Bash 4+
• No other dependencies