Debugging

Code review, security audits, bug detection, alternative implementations, second opinions via OpenAI Codex. Use when user asks for code review, security analysis, implementation advice, bug detection, code patterns, or wants a second opinion on code. Supports uncommitted changes review. Do not use for architecture design or web searches.

A code analyzer skill that helps with code quality and best practices

Go error handling patterns. Routes to specific patterns.

Fast code hygiene validation (lints, formatters, tests, coverage) for quick development loop feedback.

Run failing tests and update expected variables to match actual output from pytest

Produce concise, citation-backed explanations of module behavior, data flow, and important types/APIs.

处理代码审查反馈并修复审查中发现的问题。当用户要求修复审查问题、处理 review 反馈时触发。参数为 task-id。

A comprehensive code review skill that analyzes code for best practices, potential bugs, security issues, and suggests improvements.

Clear Unity console logs via uloop CLI. Use when you need to: (1) Clear the console before running tests, (2) Start a fresh debugging session, (3) Clean up log output for better readability.

Use when synthesizing perf findings into evidence-backed recommendations and decisions.

Checks the internal consistency of a software project, fixes any issues found.

Diagnose planning directory health and optionally repair issues. Use when the user wants to check project integrity or troubleshoot DevFlow state. Triggers on: "is the project healthy?", "check project health", "any issues?", "something seems wrong with planning"

Prompt debugging skills for LLM developers. Convert conversations from OpenAI, Anthropic, Google, and Helicone into .echo format, and integrate .echo export into your apps. Use with EchoSpace — the local-first prompt debugging workspace.

Debug issues by researching errors and proposing minimal fixes. Use when user asks to troubleshoot or debug a failure.

HTTP API testing and debugging

Backend typed error handling and boundary mapping

Review code for architectural fit, dead code, and complexity. Use when asked to review a module, file, or PR.

Find and fix unsafe error handling in Leavn - try! force unwraps, empty catch blocks, silent try? failures

Diagnoses and fixes CI failures and re-runs GitHub Actions jobs. Use when CI is failing, tests break in CI, lint errors block merging, a build fails, or jobs need re-running.

Systematic debugging approach for identifying and fixing issues

Choose a consistent error handling approach: exceptions, Result types, or error callbacks Use when maintaining consistent code style. Style category skill.

To inspect the Flutter widget tree of the running app, retrieve the widget hierarchy after connecting to the Dart Tooling Daemon.

Parse and analyze log files to find errors, exceptions, and failures. Use when debugging build logs, application logs, or any large text file containing system output.

Fetches a GitHub issue, implements the fix, and verifies it. Use when user wants to fix an issue, implement issue changes, or resolve a bug.

Targeted interview for execution-time clarification. Use when you hit an ambiguity or decision point during implementation that needs user input before proceeding.

Repair broken imports automatically across the project

AI-powered codebase security scanner inspired by Claude Code Security. Triggers when the user runs /security-review or asks to scan their code for vulnerabilities, security issues, bugs, exposed secrets, or insecure dependencies. Use this skill whenever the user mentions: security scan, vulnerability check, find bugs, check for SQLi / XSS / injection, exposed API keys, audit dependencies, access control review, or any phrasing like "is my code secure?", "scan this file", "review for security issues", or "check my repo for vulnerabilities". Works across all agentic IDEs: VS Code, Cursor, Windsurf, and any Claude-powered coding environment. Always trigger this skill — even for partial scans on a single file.

Debug web and Node.js applications using console inspection, network analysis, and non-blocking code debugging. Use when the user reports bugs, wants to debug JavaScript (browser or backend), inspect network requests, troubleshoot page/API issues, trace function calls, or monitor exceptions.

Use when handling errors. Use when tempted to catch and swallow exceptions. Use when returning default values to hide failures.

Systematic debugging and problem-solving methodology. Activate when encountering unexpected errors, service failures, regression bugs, deployment issues, or when a fix attempt has failed twice. Also activate when proposing ANY fix to verify it addresses root cause (not a workaround). Prevents patch-chaining, wrong-environment restarts, workaround addiction, and "drunk man" random fixes.

フロントエンドトラブルシューティング。Web Audio/Tailwind/OGP/React/SSE/SNS連携等

Brutally honest code review in the style of Linus Torvalds, focusing on data structures, simplicity, and pragmatism. Use when you want critical, no-nonsense feedback that prioritizes engineering fundamentals over style preferences.

Debug the Lightdash app using PM2 logs, Spotlight traces, and browser automation. Use when investigating issues, tracking down bugs, understanding request flow, or correlating frontend actions with backend behavior.

Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity. Use when finding related code, locating similar implementations, discovering code dependencies, or identifying code that performs similar operations. Outputs ranked file lists with matching code snippets and relevance scores.

Debugging crashes related to custom memory heap implementations, particularly release-only crashes involving static destruction order, use-after-free during program shutdown, and memory lifecycle issues between custom allocators and standard library internals. This skill should be used when debugging segfaults or memory corruption that only occur in release/optimized builds, involve custom memory allocators or heap managers, or manifest during static object destruction after main() returns.

Guide for debugging distributed training issues in AReaL. Use when user encounters hangs, wrong results, OOM, or communication errors.

Static type inference and validation for navigation paths

Diagnose Ingress failures (rules not matching, backend unreachable, TLS errors, no address assigned). Checks Ingress resources, IngressClass, backend Services, and controller health to identify why external traffic is not routed correctly.

Use when asked to review a PR, or when /review is invoked with a PR number or URL. Performs a focused code review checking for bugs, security, performance, and test gaps, then posts findings as a PR comment and formal GitHub review.

Navigate and work with the react-native-navigation (RNN) codebase. Use when fixing bugs, adding features, tracing command flows, understanding options resolution, or working across JS/iOS/Android layers in this repo.

This skill should be used when the user wants to debug or trace where time is spent during query execution in Materialize. Trigger when the user mentions tracing queries, span analysis, query latency breakdown, Tempo traces, trace IDs, or wants to understand where time goes in CREATE TABLE, SELECT, INSERT, DROP, or any other SQL statement execution.

Use when creating, updating, debugging, or reviewing Scout UI tests in Kibana (Playwright + Scout fixtures), including page objects, browser authentication, parallel UI tests (spaceTest/scoutSpace), a11y checks, and flake control.

Bisect a ClickHouse regression using pre-built master binaries from CI. Use when the user wants to find the commit that introduced a bug.

Evaluate first-time user experience (FTUE) and onboarding for roguelike deckbuilders. Use when reviewing tutorials, starter decks, unlock sequences, tooltip design, or information architecture. Triggers on requests to audit new player experience, analyze onboarding flow, or improve teaching/discovery mechanics.

Comprehensive testing reference for running tests in IntelliJ codebase via tests.cmd. Use when running, debugging, or troubleshooting test execution.

Understanding the NetCDF-C library architecture including dispatch tables, format implementations (NetCDF-3, HDF5, Zarr, DAP), I/O layers, and metadata structures. Use when working on NetCDF-C codebase, debugging format issues, adding new features, or understanding how different storage backends interact.

Generate code fixes and patches from bug reports, failing test cases, error messages, and stack traces. Use this skill when debugging code, fixing test failures, addressing GitHub issues, resolving runtime errors, or patching security vulnerabilities. Analyzes the bug context, identifies root causes, and generates precise code patches with explanations and validation steps.

Systematic debugging methodology using evidence-based investigation to identify root causes. Use when encountering bugs, errors, unexpected behavior, failing tests, or intermittent issues. Enforces four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) with the iron law NO FIXES WITHOUT ROOT CAUSE FIRST. Covers runtime errors, logic bugs, integration failures, and performance issues. Useful when debugging, troubleshooting, investigating failures, or when --debug flag is mentioned.

Use when auditing whether tests genuinely catch failures, or when user expresses doubt about test quality. Triggers: 'are these tests real', 'do tests catch bugs', 'tests pass but I don't trust them', 'test quality audit', 'green mirage', 'shallow tests', 'tests always pass suspiciously', 'would this test fail if code was broken'. Forensic analysis of assertions, mock usage, and code path coverage.

Phase 4: Code Review — four lenses on the same diff: clarity, correctness, safety, and CLAUDE.md compliance. Invokes /simplify, /review, /security-review, and code-review:code-review with a commit after each step.