AgentObservability

Search ACE playbook before implementing, building, fixing, debugging, or refactoring code. Capture patterns after completing substantial coding work.

Comprehensive Android device control via ADB (Android Debug Bridge). Use when user asks about: Android device management, app installation/uninstallation, APK operations, package management, file transfer (push/pull), screenshots, screen recording, input simulation (tap/swipe/text/keyevents), shell commands, logcat viewing, device info (battery/memory/storage), automation scripts, wireless ADB connection, scrcpy mirroring. Keywords: adb, android, phone, tablet, device, apk, install app, uninstall app, screenshot, screen record, tap, swipe, type text, keyevent, logcat, push file, pull file, shell, package, activity, intent, broadcast, dumpsys, getprop, settings, input, sendevent, monkey, am start, pm list, device info, battery status, wireless adb, connect device.

>-

Advanced Git - interactive rebase, cherry-pick, bisect, reflog, and power user operations

Cloudflare Workers and Pages deployment for Adynato projects. Covers wrangler CLI, reading logs for debugging, KV/D1/R2 storage, environment variables, and common errors. Use when deploying to Cloudflare, debugging workers, or configuring edge functions.

Send messages to other Claude Code sessions via tmux. Hand off complex debugging context, get second opinions, share detailed technical findings across sessions.

Systematic debugging approaches for isolating and fixing software defects. Use when something isn't working and the cause is unclear.

Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool routing) for LLM systems. Use when building or debugging agent workflows, tool-use loops, or multi-step task delegation; triggers: agentic, multi-agent, orchestration, ReAct, evaluator-optimizer, tool-use, handoff.

AgentsKB - Knowledge Base API for AI Agents with 32K+ technical Q&As

Instructions for debugging agentstack-server during development

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.

Debug AILANG code errors. Use when you encounter type errors, parse errors, or runtime failures in AILANG programs.

Deploying and debugging Toygres on AKS (Azure Kubernetes Service). Use when deploying, debugging pods, viewing logs, troubleshooting SSL, or managing Kubernetes resources.

Investigate codebase, debug issues, or analyze patterns

This skill provides automated assistance for log analysis tool tasks.

Use when starting work after context compaction, switching features, or gathering context without re-reading entire files - searches anchor tags to find relevant architecture/pattern documentation

Automate ADB commands for device management, app installation, and log analysis. Use when listing devices, installing APKs, viewing logs, debugging app issues, or capturing screenshots.

Start real-time log streaming from connected Android device using adb logcat. Shows only app's log messages. Use when monitoring app behavior, debugging, or viewing Android logs.

Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders. This skill covers transactional email that works, marketing automation that converts, deliverability that reaches inboxes, and the infrastructure decisions that scale. Use when: keywords, file_patterns, code_patterns.

Search logs and codebases for error patterns, stack traces, and

Comprehensive JavaScript reference covering 33+ essential concepts every developer should know. From fundamentals like primitives and closures to advanced patterns like async/await and functional programming. Use when explaining JS concepts, debugging JavaScript issues, or teaching JavaScript fundamentals.

Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power

>

Debug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant loading failures, or runtime errors from aot_compile, aot_load, aoti_compile_and_package, or aoti_load_package.

Create or modify API endpoints in IdeaForge backend. Triggers: new route, controller, service, repository, CRUD operation, Zod validation, API debugging. Pattern: Routes → Controller → Service → Repository.

Implement comprehensive API error handling with standardized error responses, logging, monitoring, and user-friendly messages. Use when building resilient APIs, debugging issues, or improving error reporting.

Instrument API requests with spans and distributed tracing. Use when tracking request latency or debugging API issues.

Expert lifecycle decisions for iOS/tvOS: when SwiftUI lifecycle vs SceneDelegate, background task strategies, state restoration trade-offs, and launch optimization. Use when managing app state transitions, handling background work, or debugging lifecycle issues. Trigger keywords: lifecycle, scenePhase, SceneDelegate, AppDelegate, background task, state restoration, launch time, didFinishLaunching, applicationWillTerminate, sceneDidBecomeActive

Implement structured logging across applications with log aggregation and centralized analysis. Use when setting up application logging, implementing ELK stack, or analyzing application behavior.

Comprehensive assistance with ar-io-build

Expert guidance for GabeDA v2.1 architecture (34 modules) - implementing models, features, debugging 4-case logic, and maintaining the /src codebase.

Build and debug ARKit features for visionOS, including ARKitSession setup, authorization, data providers (world tracking, plane detection, scene reconstruction, hand tracking), anchor processing, and RealityKit integration. Use when implementing ARKit workflows in immersive spaces or troubleshooting ARKit data access and provider behavior on visionOS.

Asks Claude CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.

Asks Codex CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.

This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claude analysis needs deeper reasoning or extended context windows.

Creates assessments with varied question types (MCQ, code-completion, debugging, projects) aligned to learning objectives. Use when educators design quizzes/exams, need questions at appropriate Bloom's cognitive levels, want balanced cognitive distribution (60%+ non-recall), or require rubrics for open-ended questions.

Use `astro:assets` for all images. This enables automatic optimization (resizing, WebP/AVIF conversion, lazy loading).

Set up observers for debugging and monitoring. Covers implementing actionObservers for dispatch logging, stateObserver for state change tracking, combining observers with globalWrapError, and using observers for analytics.

Establish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies, tracing effects, or building causal models.

Automatically helps debug Web Audio API issues, audio playback problems, pitch preservation, and caching issues in the VSSK-shadecn music practice app

Analyze the WaveCap-SDR audio stream to assess tuning quality, detect silence, noise, proper audio, or distortion. Use when checking if SDR channels are properly configured or debugging audio issues.

Run a single-session engineering productivity audit on the codebase

Comprehensive audit logging for compliance and security. Track user actions, data changes, and system events with tamper-proof storage.

Comprehensive guide to implementing audit trails and logging for AI agents including tracing, observability, compliance, and debugging

Implementing comprehensive logging, tracking, and audit trails for AI systems to ensure compliance and enable debugging.

name: auto-debug

How the devbox automatically updates llm-agents (claude-code) via GitHub Actions and systemd timers. Use when debugging update failures or understanding the update flow.