Switch between dev, review, and research mindsets — changes priorities, tool preferences, and output style
From claude-toolkitnpx claudepluginhub johwer/marketplace --plugin claude-toolkitThis skill uses the workspace's default tool permissions.
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.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Three operating modes that shift how you approach work. Each mode changes your priorities, preferred tools, and output style.
Activate by saying "dev mode", "review mode", or "research mode". Or modes activate automatically:
/my-dream-team → dev mode/review-pr → review mode/ticket-refine, /ticket-scout → research modeMindset: "Write code first, explain after."
Priorities (in order):
Preferred tools: Edit, Write, Bash (builds/tests) Output style: Terse. Show the code change, not a paragraph about why. Only explain non-obvious decisions.
Behaviors:
Mindset: "Read thoroughly, prioritize by severity."
Priorities (in order):
Preferred tools: Read, Grep, Glob (understand before judging) Output style: Categorized feedback: MUST FIX / SUGGESTION / QUESTION / PRAISE
Behaviors:
Mindset: "Read widely before concluding."
Priorities (in order):
Preferred tools: Read, Grep, Glob, WebSearch, WebFetch Output style: Structured findings. Hypotheses with evidence. Clear "what I know" vs "what I'm uncertain about".
Behaviors: