concurrency-expert
Swift Concurrency review and remediation for Swift 6.2+. Use when asked to review Swift Concurrency usage, improve concurrency compliance, or fix Swift concurrency compiler errors.
Essential command-line tools and system utilities.
Swift Concurrency review and remediation for Swift 6.2+. Use when asked to review Swift Concurrency usage, improve concurrency compliance, or fix Swift concurrency compiler errors.
Query the code graph for callers, dependencies, and blast radius. Use when you need to understand code relationships, find what calls a function, determine impact of changes, or explore the codebase structure.
This skill should be used when the user asks to "debug notebook", "inspect notebook outputs", "find notebook error", "read traceback from ipynb", "why did notebook fail", or needs to understand runtime errors in executed Jupyter notebooks from any source (marimo, jupytext, papermill).
Precision and type-safety hardening for Phoenix calculation paths. Use when configuring ESLint/TypeScript, replacing parseFloat in P0 files, or validating Decimal.js precision.
Performance optimization playbook (measure → diagnose → fix → verify) for this repo (React + R3F + Three.js + Vite). Use when asked to improve FPS, reduce jank, lower draw calls, optimize loading/bundle size, or investigate CPU/GPU/memory bottlenecks.
[30] ANALYZE. Understand how changes impact the system — what's the core, what's affected, what depends on what. Use when planning changes, analyzing systems, debugging issues, or anytime you need to see the full picture of cause and effect. Triggers on "what's affected", "impact analysis", "dependencies", "scope mapping", or when you need to understand ripple effects.
You are the iOS Simulator runtime debugging specialist.
コード変更の影響範囲分析スキル。変更が引き起こし得る影響を影響面(code/interface/data/external/config/runtime/security/observability)ごとに整理し、「どこをレビューし、何をテストし、何を観測すべきか」を根拠つきで提示する。 トリガー条件: - 「影響範囲を分析して」「この変更の影響は?」「どこまで波及する?」 - PRレビュー依頼時、リファクタ/仕様変更時 - 障害対応で「原因箇所の周辺影響」を確認したい時 注意: 変更の是非の最終判断は行わない。実行時にしか分からない挙動は推定と不確実性を提示する。
SUPERSEDED by persistent-cache-gap-filling (v2.8.0). Cache data during symbol selection for instant repeat runs.
Test Claude Code hooks in isolation and via integration. Use when developing, debugging, or validating hook behavior.
Systematic codebase investigation before addressing issues. Use when you need to build comprehensive understanding of a problem area.
Diagnoses JavaScript errors, asset loading failures, p5.js conflicts, game logic bugs, and performance issues. Use when encountering errors, crashes, console warnings, sprites not loading, enemies stuck, towers not working, or any unexpected behavior.
Use when working on the Miden compiler (`cargo miden`, `cargo-miden`) and its integration test suite, debugging compiler issues or failing tests, or implementing compiler changes and you need to inspect intermediate artifacts. Covers `MIDENC_EMIT` (the environment-variable equivalent of `--emit`) for emitting WAT/HIR/MASM (and related outputs), plus `MIDENC_EMIT_MACRO_EXPAND` for dumping macro-expanded Rust via `cargo expand` for integration-test fixtures.
Chrome拡張機能開発に関する包括的なガイド。ベストプラクティス、アンチパターンの回避、型安全性、Manifest V3への準拠をサポート。Claudeが以下のためにChrome拡張機能を扱う場合に使用:(1) 新規拡張機能の計画・作成、(2) 既存コードのデバッグ・修正、(3) セキュリティレビュー、(4) Manifest V2からV3への移行、(5) TypeScript型の問題解決。
Capture errors with rich context for debugging and alerting
Detect and fix memory leaks in Python and PyTorch code, especially matplotlib figures and unreleased tensors. This skill should be used during Phase 4 performance optimization when memory usage grows over time.
Query the ragsharp code graph for declarations, references, callers, callees, dependencies, and line-number evidence. Triggers: find usages, where defined, callers, callees, dependency path, project deps, type hierarchy, line numbers, evidence.
Systematic debugging methodology that eliminates guessing and speculation. Add instrumentation to gather specific data that fully explains the problem. Evidence before hypothesis. Observation before solution.
Log a bug report. Use when user asks to create, log, file, or report a bug.
This skill should be used when creating token-efficient hook systems and MCP server architectures for web applications. Use for React/FastAPI, Django, Node.js projects that need smart caching, progressive context loading, and 95%+ token reduction. Essential for projects requiring monitoring, debugging, data analysis, and system health tools.
Use this skill BEFORE using writing any Clojure code. It teaches how to use the Clojure REPL (via brepl) so you can test code, check if edited files compile, verify function behavior, or interact with a running REPL session.
Systematically debug issues in PhotoClove by examining code, state, logs, and data flow. Automatically invoked when investigating bugs, errors not working as expected, or tracing problems through the codebase. Uses structured debugging approach to identify root causes.