slash-IT

    2

    Convert chat messages into reusable, optimized, and parameterized slash commands for your terminal or IDE.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    slash-IT

    Example session with this skill installed

    That last prompt was great for fixing CSS bugs. Save it as a global command called css-fix but optimize the wording first so it is more concise.

    • Read your context and instructions
    • Compiled the slash-it

    I have optimized your previous CSS debugging prompt and saved it as a global command. You can now trigger this exact logic anywhere by typing /css-fix.

    Command Details

    PropertyValue
    Command Name/css-fix
    ScopeGlobal (~/.claude/commands/css-fix.md)
    ActionOptimised previous message
    StatusActive and Ready

    Saved Content

    Analyze the provided CSS snippet for layout shifts, z-index conflicts, or overflow issues. Provide a corrected version of the code and a brief explanation of the fix, ensuring compatibility with modern evergreen browsers.
    

    Next steps

    1. Test the new command by typing /css-fix followed by a snippet of CSS code.
    2. Use list-cmds to see this alongside your other global shortcuts.
    3. If you need to add variables, run create-cmd-args css-fix to update it with $ARGUMENTS.

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

    About this skill

    Writing complex prompts manually every time you need to reuse them is a waste of cycles. This skill converts your previous chat messages into persistent, reusable slash commands that live in your global or project-specific configuration.

    What it does

    • Instant Persistence saves your last message exactly as written to a named slash command.
    • Prompt Optimization refines your previous message for clarity and grammar before saving.
    • Dynamic Parameterization transforms static prompts into templates using $ARGUMENTS or positional variables like $1.
    • Instructional Reshaping modifies the intent of a previous prompt based on new specific constraints.
    • Command Management provides a searchable list of all active global and repository-specific commands.

    How it works

    1. Send a prompt to the agent that you want to reuse later.
    2. Run create-cmd <name> to save it verbatim or use create-cmd-optimise to let the skill clean it up first.
    3. Use create-cmd-args if you want to leave placeholders for future inputs.
    4. Specify --global to use the command in any project or --project to keep it scoped to your current directory.

    Frameworks & tools

    The skill manages files within ~/.claude/commands/ or local .claude/commands/ directories. It is designed for environment-aware prompt management.

    Why this beats prompting it yourself

    Manually copying prompts into a notepad or system file breaks flow. This skill automates the extraction and formatting of successful prompts into executable commands without leaving the terminal or chat interface.

    Use cases

    • Save a complex code review checklist as /review-pr.
    • Create a parameterized /refactor $1 command for specific languages.
    • Build a project-specific /tech-stack command that injects your local architecture details.
    • List all available custom shortcuts when onboarding a new developer to a repo.

    Known limitations

    Requires specific directory permissions to write to ~/.claude/commands/. Parameters must be manually mapped if using advanced logic beyond simple variable substitution.

    Requires write permissions for ~/.claude/commands/. Parameters are limited to standard shell-style $ARGUMENTS and $1, $2 variables.

    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 any payment.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed1 month ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    This skill solves 'prompt fatigue' by letting you instantly turn any successful chat message into a permanent, executable slash command, eliminating the need to manually copy-paste or rewrite complex prompts.

    slash-IT is designed for CLI-based AI environments like Claude Code and terminal-integrated agents that support custom slash commands via directory-based configurations.

    Yes, you can use the `--global` flag to save commands to your home directory for use anywhere, or the `--project` flag to scope commands to a specific repository's `.claude/` folder.

    The skill includes an 'optimise' mode that automatically refines your previous chat messages for clarity and grammar, ensuring your saved commands are high-quality and reliable for future use.

    You will receive the full skill package, including the command management logic, installation instructions for your local environment, and documentation for setting up dynamic parameters.

    The skill requires write permissions for the `~/.claude/commands/` directory on your machine to successfully store and retrieve your custom global commands.

    New in Prompt & Skill Engineering