Find the perfect capability for your agent.
Use when symptoms don't reveal the cause. Trace backward through call chains to find where problems originate. Follow: Observe symptom → Find immediate cause → Identify caller → Keep tracing → Locate trigger.
Debug bugs and errors using intel-first approach with systematic root cause analysis. Use proactively when errors occur, tests fail, or unexpected behavior appears. MUST trace from symptom to root cause with CoD^Σ reasoning.
Systematic debugging discipline that enforces root cause investigation BEFORE fixes. Triggers on - bug, error, failing, broken, fix, not working, crash, issue, debug, investigate, diagnose, trace, root cause, why is, undefined, null, 500 error, RLS, timeout, infinite loop, exception, stack trace. Integrates with Zen MCP, TodoWrite, and verification-before-completion. Aligns with fail-fast engineering principle.
遇到任何 bug、测试失败或意外行为时使用，在提出修复方案之前进行系统化调试。Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Follow the four phases: Root Cause Investigation, Pattern Analysis, Hypothesis Testing, Implementation.
Review local codebase for bugs and CLAUDE.md compliance using multi-agent analysis
Use when encountering bugs, test failures, or unexpected behavior - ensures root cause understanding before attempting fixes
Debug WebSocket connection issues between CLI and FigJam plugin. Use when diagrams aren't syncing, connection fails, plugin shows "Connecting..." indefinitely, or patches aren't being applied to canvas.
Detects null pointer dereference vulnerabilities by identifying unchecked pointer usage and missing validation. Use when analyzing pointer operations, input validation, or investigating crash vulnerabilities.
Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications.
How to use the FlowStorm debugger to analyze Clojure/ClojureScript program executions. This skill teaches timeline exploration, value inspection, and debugging patterns using FlowStorm's recording API for runtime analysis.
Check if a Ralph run is active and tail the most recent log.
Tracks untrusted input propagation from sources to sinks in binary code to identify injection vulnerabilities. Use when analyzing data flow, tracing user input to dangerous functions, or detecting command/SQL injection.
Diagnose slow Claude Code startup and guide cleanup. Use /bluera-base:clean to run.
Understand business logic vulnerabilities in AI code including race conditions, integer overflow, and calculation errors that pass functional tests but create security holes. Use this skill when you need to learn about race conditions in AI code, understand integer overflow vulnerabilities, recognize business logic security flaws, or identify calculation errors. Triggers include "race conditions", "business logic vulnerabilities", "integer overflow", "race condition AI", "flash sale security", "concurrent access", "negative totals", "calculation errors".
Use when encountering any bug, test failure, or unexpected behavior in Flutter - requires systematic investigation before proposing fixes
触发并汇总预览结果（Java转发到Node Preview），输出预览链接与渲染耗时/错误快照。用户要预览或验收预览时调用。
Use when analyzing YouTube videos for research, learning, or understanding how content relates to a project - downloads transcripts with yt-dlp, chunks long content, and provides context-aware analysis
Analyses and optimises performance across frontend, backend and database interactions. Identifies bottlenecks and implements solutions to enhance speed and efficiency.
Run and manage performance benchmarks with cargo xtask bench for facet-json, analyzing results with Markdown reports and comparing against serde_json baseline
