Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From probe
Searches indexed project docs and code using probe_search and probe_read before broad greps. Useful for architecture, APIs, design docs, runbooks, and locating behavior definitions.
npx claudepluginhub zeroentropy-ai/probe --plugin probeHow this skill is triggered — by the user, by Claude, or both
Slash command
/probe:use-probeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use probe as the first pass when the user asks about project knowledge that may span files, docs, or code.
Answers codebase questions by tracing flows and researching topics. Two modes: autonomous (structured output for subagents) and interactive (narrative with checkpoints).
Semantic codebase search — use for exploring code, finding implementations, and answering questions about any project. Searches using natural language queries, identifier names, or file paths. Returns ranked results using embedding-based similarity, BM25 keyword matching, symbol matching, import graph analysis, and git recency. Use this as the default exploration tool instead of grep when you don't know the exact text to search for.
Explores codebases with Repowise indexing for architecture understanding, searching, and answering questions without raw source grepping.
Share bugs, ideas, or general feedback.
Use probe as the first pass when the user asks about project knowledge that may span files, docs, or code.
probe_search before broad grep, find, or reading many files.refreshed field in probe_search. If it contains an error, say the search used the last good local index.probe_read(file_path, line_start, line_end, context_lines=...) calls
when search returns line ranges and you need more context.probe_read only when the whole file is genuinely needed.probe_index only when the user asks, search is empty, or freshness looks wrong.Do not use probe for a file the user already named unless repo context or related docs would help.