Use when you need to make a decision, compare options, or think through a list of items systematically — 'help me decide', 'weigh these options', 'walk me through the tradeoffs'.
From dp-ctonpx claudepluginhub raisedadead/dotplugins --plugin dp-ctoThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Lightweight structured decision skill. Walks through a list of items one at a time, presenting context and options for each. No beads, no spec pipeline, no stage machine.
If the user provided items in args or conversation → use them. Otherwise → ask: "What items do you want to brainstorm? Provide a list, a file path, or describe the topic."
Parse into a numbered list of discrete items to decide on.
For each item:
AskUserQuestion — typically: Keep / Relax / Modify / Remove. Add a recommendation with rationale.One item per message. Do not batch. Do not skip ahead.
After all items are decided, present a decision summary table:
| # | Item | Decision | Notes |
|---|
Then ask: "All items decided. Want to act on these now, or save for later?"