Help us improve
Share bugs, ideas, or general feedback.
From mimirs
Answers hard open-ended questions about how a project works by synthesizing code, structure, git history, decisions, and discussion across multiple areas.
npx claudepluginhub thewinci/mimirs --plugin mimirsHow this skill is triggered — by the user, by Claude, or both
Slash command
/mimirs:researchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Goal: a thorough, cited answer to a specific question — pulled from across the whole project memory, not one file or one area. Where `explore` maps an area's structure, `research` answers a question by combining code, history, decisions, and discussion.
Builds a mental model of unfamiliar codebases by searching, reading dependencies, and checking git history. Use when onboarding or before editing unknown code.
Spawns parallel sub-agents to research codebase areas and synthesize findings into a structured document. Use for deep technical questions or codebase understanding.
Explores codebase topics with multi-angle analysis, injecting prior knowledge and producing structured research documents. Invoked via /research.
Share bugs, ideas, or general feedback.
Goal: a thorough, cited answer to a specific question — pulled from across the whole project memory, not one file or one area. Where explore maps an area's structure, research answers a question by combining code, history, decisions, and discussion.
search "<sub-question>" for the relevant files, then read_relevant "<behavior>" for the actual functions/sections with line ranges. Use the extensions/dirs/excludeDirs filters to scope. search_symbols <name> for named things you already know.project_map(focus: <file>), depends_on/dependents <file>, impact <symbol> (transitive callers), trace from=<a> to=<b> (how one reaches another).search_commits "<topic>" for why and when it changed; file_history <file> for how a file evolved.search_checkpoints "<topic>" for recorded decisions and direction changes; search_conversation "<topic>" for the back-and-forth and alternatives considered.get_annotations (search across notes) for known bugs, constraints, and fragile spots that qualify the answer.Finish: answer each sub-question in plain language with a file:line, commit, or checkpoint citation; separate what the source proves from what is inferred; list what stayed unresolved instead of guessing.