Review maintainability like a principal engineer. Use when the user asks what a senior/staff/principal maintainer would notice, whether code looks vibe-coded, what is gross, what should be fundamentally different, or which architecture smells matter beyond ordinary deduplication.
Optimize performance scientifically with current scip-query evidence. Use for benchmarking, profiling, cold or warm indexing, command latency, memory and computational cost, or comparing current-pipeline tuning with alternative designs.
Compress systems with SCIP evidence. Use to zoom out, simplify architecture, eliminate layers, consolidate commands/scripts/helpers, find deeper roles, reason about same-in-principle repetition, build a compression atlas, or execute ordered simplification.
Apply TypeScript performance and safety rules. Use for tsc speed, tsconfig, type errors, async patterns, module organization, import hygiene, type definitions, memory issues, or .ts/.tsx/.d.ts work. Not for TypeScript basics or framework-specific testing.
Instructions for PlunderStruck/scip-query, a project described as: Evidence and verification for AI coding agents: map code, reuse concepts, finish migrations, and gate diffs.
Understand a repository system end to end before explaining, planning, changing, or reviewing it. Use when the task depends on how behavior enters the system, branches, transforms data, crosses runtimes, changes state, reaches consumers, or recovers from failure across multiple symbols or files. Apply scip-query as…
Audit whether implementations are real with scip-query. Use for suspected faked or half-implemented features, decorative checkers or verifiers that never fail, dead code paths hidden behind graceful fallbacks, metrics that may be lying, or a "does any of this actually work" interrogation of a system.
Write a concise, code-grounded implementation plan for a non-trivial feature, fix, refactor, migration, or retirement. Use scip-query as the primary repository exploration surface and cite exact owners, relationships, behavior, and consumers.
Use FIRST for codebase work when compiler-resolved identity, runtime boundaries, callers, dependencies, consumers, architecture, change impact, or cleanup relationships can affect the answer. It exposes exact referents, explicit typed-graph projections, and source evidence; it does not infer task relevance. Pair it…
Install, diagnose, index, watch, repair, or clean up scip-query for a repository. Use for setup, freshness, cache ownership, worktrees, watcher behavior, and operational failures—not ordinary code exploration.