Stats
Actions
Tags
From devils-advocate
Bridge between evaluate and iterate. Asks user how to address devil's concerns - user suggestions, auto-apply recommended options, or planning mode. Now integrated into iterate's Step 1 - use /devils-advocate:iterate directly.
How this skill is triggered — by the user, by Claude, or both
Slash command
/devils-advocate:improveThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Integrated into `/devils-advocate:iterate`.**
Integrated into /devils-advocate:iterate.
Iterate handles full cycle: decide improvement (Step 1) -> apply changes + version (Step 2) -> score (Step 3) -> rename with residual (Step 4).
Use /devils-advocate:iterate directly. First step asks same improvement mode (your suggestions / auto-apply / planning mode / you already edited).
User edited externally, wants re-scoring only: /devils-advocate:iterate option 4 ("you already edited") skips straight to scoring.
npx claudepluginhub stellarshenson/claude-code-plugins --plugin devils-advocateProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.