racecraft-plugins-public: Skill for Claude Code

Verify Tasks Run Skill

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Supported arguments: Optional space/comma-separated task IDs to verify only specific tasks. Optional --scope branch|uncommitted|plan-anchored|all (default: all) to control which changes count as evidence.

Display the following advisory immediately before any other work:

⚠️ FRESH SESSION ADVISORY: For maximum reliability, run /speckit.verify-tasks in a separate agent session from the one that performed /speckit.implement. The implementing agent's context biases it toward confirming its own work.

Pre-Execution Checks

Check for extension hooks (before verification):

• Check if .specify/extensions.yml exists in the project root.
• If it exists, read it and look for entries under the hooks.before_verify-tasks key
• If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
• Filter to only hooks where enabled: true
• For each remaining hook, do not attempt to interpret or evaluate hook condition expressions:
  • If the hook has no condition field, or it is null/empty, treat the hook as executable
  • If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementation
• When constructing command invocations from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.
• For each executable hook, output the following based on its optional flag:

  • Optional hook (optional: true):

    ## Extension Hooks
    
    **Optional Pre-Hook**: {extension}
    Command: `/{command}`
    Description: {description}
    
    Prompt: {prompt}
    To execute: `/{command}`
    

  • Mandatory hook (optional: false):

    ## Extension Hooks
    
    **Automatic Pre-Hook**: {extension}
    Executing: `/{command}`
    EXECUTE_COMMAND: {command}
    
    Wait for the result of the hook command before proceeding to the Outline.