More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    CLI Help to README — Usage Table From --help

    1

    You get back the usage table for your README: every command, argument and option, with its value name, its default, and whether it is required.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    CLI Help to README — Usage Table From --help

    CLI Help to README — Usage Table From --help

    Example session with this skill installed

    Write the README usage table from examples/sample_scan_help.txt and tell me which options have no description.

    • Read your context and instructions
    • Compiled the cli help to

    Summary

    CLI Help to README wrote the usage, arguments and options tables for logsift scan, and listed one gap: --limit has no description.

    $ python3 scripts/cli_help_to_readme.py --file examples/sample_scan_help.txt
    
    ## Usage
    
    ```text
    usage: logsift scan [-h] [--level {debug,info,warn,error}] [--since DURATION] [--limit LIMIT] file
    ```
    
    ### Arguments
    
    | Argument | Required | Description |
    |---|---|---|
    | `file` | yes | path to the log file |
    
    
    ### Options
    
    | Option | Value | Default | Required | Description |
    |---|---|---|---|---|
    | `-h`, `--help` | - | - | no | show this help message and exit |
    | `--level` | `{debug,info,warn,error}` | `info` | no | lowest level to keep (default: info) |
    | `--since` | `DURATION` | - | no | only lines newer than this, such as 90m or 2h |
    | `--limit` | `LIMIT` | - | no | - |
    
    
    ### Gaps
    
    - `--limit`: option has no description
    

    Next steps

    • Add a description for --limit in the command's help text, then run --lint again.
    • Use --write README.md to keep the table in your README, and --check README.md in CI.
    README.md--check README.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    You send a command's --help output. You get back the usage table for your README: every command, argument and option, with its value name, its default, and whether it is required.

    A README usage section is copied from --help once and then drifts: a flag is added, a default changes, and the README still shows last month's tool. Nobody notices that an option has no description until a user asks what it does.

    CLI Help to README reads the help text (argparse, click, or GNU style) and writes the table, and tells you what is missing. --lint prints only the gaps and exits 1, which is what you want in CI.

    What it does

    • Reads help text from a file, from a pipe, or by running the command itself (--run), and follows its subcommands (mytool scan --help, mytool report --help)
    • Writes Markdown tables or JSON: flags, value name, allowed values, default, required, description
    • --write README.md keeps the table between two markers and leaves the rest of your README alone; --check README.md exits 1 when that table is missing or stale
    • --lint lists options and commands with no description; --strict also counts a missing default and a missing example
    • Standard library only; --run uses no shell and a timeout, and the tool makes no network calls

    Honest limits

    It reads the words your help prints, so a default that is not in the help sentence stays -. Layouts other than argparse, click and GNU-style lists are not recognized and exit 2.

    What is inside

    SKILL.md, README.md, LICENSE, scripts/cli_help_to_readme.py, tests/test_package.py (44 tests), and examples/ with a small example command and its saved help text.

    Requirements and safety

    Python 3.8+, macOS or Linux, standard library only. --run executes COMMAND --help only; do not point it at a program whose --help has side effects.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.

    Only supports argparse, click, and GNU-style help. Cannot detect defaults not printed in help text. Does not support shells for --run.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Software
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listedtoday

    What's inside

    Frequently Asked Questions

    It reads your tool's --help output and writes the usage table for your README, and --lint lists the options your help text forgot to describe. With --check in CI the build fails when the README table has gone stale, so a changed flag is noticed.

    The skill is optimized for CLI help layouts generated by argparse, Click, and standard GNU-style formats, making it compatible with most Python and system-level command-line tools.

    Yes, the skill includes a CI validation mode that checks if the existing README matches the current CLI output, allowing you to fail builds if a developer adds a flag without updating the docs.

    Only the text between the two markers it writes: <!-- cli-usage:start --> and <!-- cli-usage:end -->. If the markers are not in your README yet, --write appends them at the end; if they are, it replaces only what sits between them.

    The Python script (scripts/cli_help_to_readme.py), a sample CLI with its help text, tests, an instruction file for Claude Code (SKILL.md) and the README.

    No, the skill only extracts information that is explicitly printed in the help output; it cannot "reach into" your source code to find defaults that aren't displayed to the user.

    New in Technical Documentation