Comprehensive guide for creating, configuring, and troubleshooting codemagic.yaml files for CI/CD workflows. Use when building mobile apps (Flutter, iOS, Android, React Native) with Codemagic, setting up build pipelines, configuring environment variables, implementing code signing, managing artifacts, or debugging workflow issues.

Ask OpenAI Codex questions about code to understand implementations, architecture, patterns, and debugging. Use when the user asks how code works, where something is implemented, what patterns are used, or needs to understand existing code. Requires Codex CLI installed.

Use Codex CLI for sandboxed auditing, debugging, and autonomous prototyping

Interactive REPL workflows with Codex CLI including session management, multimodal conversations, and automated execution. Use for extended development sessions, debugging, or collaborative problem-solving.

Systematic debugging and root cause analysis with Codex (gpt-5.2).

Use OpenAI Codex CLI as a discussion partner to verify ideas, evaluate plans, and improve quality. Automatically triggered during implementation planning, troubleshooting, debugging, or when seeking a second opinion on technical decisions.

Context compression for long coding sessions. Creates checkpoints (state snapshots) and maintains them as you work.

**Role**: Combat Systems Designer

Expert Combine decisions for iOS/tvOS: when Combine vs async/await, Subject selection trade-offs, operator chain design, and memory management patterns. Use when implementing reactive streams, choosing between concurrency models, or debugging Combine memory leaks. Trigger keywords: Combine, Publisher, Subscriber, Subject, PassthroughSubject, CurrentValueSubject, async/await, AnyCancellable, sink, operators, reactive

When setting up commit message validation for a project. When project has commitlint.config.js or .commitlintrc files. When configuring CI/CD to enforce commit format. When extracting commit rules for LLM prompt generation. When debugging commit message rejection errors.

Compare ERB and JavaScript template outputs for the offline scoring SPA. Use when working on ERB-to-JS conversion, debugging template parity issues, or verifying that changes to scoring views work correctly in both ERB and SPA modes.

Multi-step reasoning patterns and frameworks for systematic problem solving. Activate for Chain-of-Thought, Tree-of-Thought, hypothesis-driven debugging, and structured analytical approaches that leverage extended thinking.

Patterns and best practices for developing React 19 components with Shadcn UI, Radix primitives, and Tailwind CSS 4 in Next.js 16. Covers accessibility, composition, variants, and server/client component patterns. Use when creating, modifying, or debugging UI components.

Develop advanced debugging workflows for concurrent rendering, including reproducibility under non-deterministic scheduling.

Comprehensive assistance with conductor

Lightweight ChatGPT consultation for agents (cached, budgeted)

Debug Docker containers and containerized applications. Diagnose deployment issues, container lifecycle problems, and resource constraints.

Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.

>-

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

Expert debugging guide for AI Counsel's convergence detection system. Use when deliberations aren't converging as expected, early stopping fails, semantic similarity seems wrong, or voting vs semantic status conflicts occur.

This skill should be used when users need to save, search, or retrieve Claude Code conversation transcripts. Use this skill when users ask to save the current conversation, search through past conversations for context, or retrieve information from previous sessions. Also use when appropriate to proactively save important conversations at natural breakpoints (e.g., after completing a major feature, fixing a critical bug, or when the user indicates they're done with a session).

Global hooks for logging Claude Code conversation events to markdown files. Tracks prompts, tool usage, and responses across all sessions. Useful for debugging, auditing, and providing conversation context to Claude.

Advanced subagent troubleshooting. Use when subagent calls fail, return bad output, or need voting for critical decisions.

Production-ready CopilotKit pitch deck wizard in main application. Use when enhancing AI conversation features, optimizing Edge Function integration, debugging chat interface, or improving pitch deck generation flow. System is PRODUCTION READY (98/100).

Expert Core Data decisions for iOS/tvOS: when Core Data vs alternatives, context architecture for multi-threading, migration strategy selection, and performance optimization trade-offs. Use when choosing persistence layer, debugging save failures, or optimizing fetch performance. Trigger keywords: Core Data, NSManagedObject, NSPersistentContainer, NSFetchRequest, FetchRequest, migration, lightweight migration, background context, merge policy, faulting

Core Dump Analysis skill for the ikigai project

Optimize CoreML models for iOS and macOS deployment. Covers quantization, palettization, pruning, Neural Engine targeting, compute unit selection, and performance profiling. Use when converting ML models to CoreML, optimizing model size/latency, debugging Neural Engine issues, or benchmarking on-device inference.

Implement distributed tracing with correlation IDs, trace propagation, and span tracking across microservices. Use when debugging distributed systems, monitoring request flows, or implementing observability.

Systematic debugging and root cause analysis with both Codex (GPT-5.2) and Gemini.

Get a help or a second opinion from other agents. Bundle a prompt and a curated file set, then ask other LLMs for advice (debug, refactor, design, ...).

Crash log analysis, symbolication, and debugging workflows for iOS apps. Use when investigating app crashes, analyzing crash reports, symbolicating stack traces, or identifying root causes. Covers crash log retrieval, symbolication with dSYM files, stack trace analysis, and common crash patterns.

Set up crash instrumentation with actionable context. Use when configuring crash capture, error boundaries, or breadcrumb strategies.

Parse and analyze macOS crash logs to identify crash causes and debugging information

Create implementation tickets with proper format and conventions.

This skill creates ephemeral pods cloned from existing deployments for interactive shell access with full application context. Use this when you need Rails console, database access, or debugging with env vars and secrets without affecting production pods.

Under master\CrimsonStainedLands\bin\Debug is a file named skilllevels.xml. This file contains entries for what level different guilds get different skills at.

Coordinate debugging across multiple services. Use when a senior developer needs to trace a distributed issue.

csharp-dotnet-debugging

Debug CSRF token issues and authentication problems including 403 Forbidden errors, cookie issues, JWT tokens, OAuth flows, and session management. Use when troubleshooting CSRF verification failed, 403 errors on POST requests, login not working, or token refresh issues.

Explain CSS layout issues and propose fixes. Use when a junior developer is struggling with alignment or spacing.

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.

Quick reference cheatsheet for libpython-clj Python interop. Includes initialization, module imports, function calls, data conversions, NumPy/Pandas/Transformers patterns, and troubleshooting. Use when calling Python from Clojure, using Python libraries, or debugging interop issues.

Archive completed debug work to ./.gtd/archive/

Execute bug fix plan. Creates ./.gtd/debug/current/FIX_SUMMARY.md

Create execution plan to fix root cause. Creates ./.gtd/debug/current/FIX_PLAN.md

Clarify and document bug symptoms. Creates ./.gtd/debug/current/SYMPTOM.md

Complete D365 Finance & Operations debugging framework. Routes symptoms to correct playbook (Finance, SCM, WMS, Batch, Security, Integration, Performance, Reporting). Activates for D365, Dynamics, AX, voucher, posting, batch job, SSRS, DMF, work order, wave, security, can't post, missing, wrong amount, slow, stuck.

Traces complete execution paths through DAG workflows. Records timing, inputs, outputs, and state transitions for all nodes. Activate on 'execution trace', 'trace execution', 'execution path', 'debug execution', 'execution log'. NOT for performance analysis (use dag-performance-profiler) or failure investigation (use dag-failure-analyzer).

Performs root cause analysis on DAG execution failures. Traces failure propagation, identifies systemic issues, and generates actionable remediation guidance. Activate on 'failure analysis', 'root cause', 'why did it fail', 'debug failure', 'error investigation'. NOT for execution tracing (use dag-execution-tracer) or performance issues (use dag-performance-profiler).