From tabnine
Searches, explores, and investigates remote repositories using Tabnine's Context Engine. Activates for cross-repo questions, service architecture, PR impact analysis, and verifying external API usage in real codebases.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tabnine:codebase-searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When the user asks about remote codebases, always use the `tabnine-context` MCP tools to search and explore. Do not guess or rely on training data — fetch real information from the indexed repositories.
When the user asks about remote codebases, always use the tabnine-context MCP tools to search and explore. Do not guess or rely on training data — fetch real information from the indexed repositories.
The tabnine-context MCP server exposes tools for:
Cast a wide net first using semantic search and files search, then narrow down with symbol tools. If the first search doesn't return useful results, try different queries or filters before giving up. Cross-reference multiple repos when investigating service interactions.
npx claudepluginhub tabnine/skills --plugin tabnineExplores internal code implementations, patterns, and architecture across organization repositories using Glean code search tools.
Provides semantic search, grep, and call graph tracing across CodeAlive-indexed codebases. Use to search code, fetch artifacts, or query data sources.
Retrieves code context summaries, API docs, and examples from GitHub repos, npm/pip libraries, code searches, and clones using isolated agents.