Implement email rate limiting and volume controls that protect sender reputation. Use when setting up send throttling, handling ISP deferrals, configuring per-domain limits, or debugging 421 errors and throttled delivery.

Process email delivery webhooks from providers like SendGrid, Postmark, SES, Resend, and Mailgun. Use when building webhook endpoints, handling bounces/complaints/deliveries, debugging missed events, or implementing idempotent event processing.

Set up SPF, DKIM, and DMARC email authentication. Use when configuring a new sending domain, debugging spam/rejection issues, adding email providers, or preparing for Google/Yahoo/Microsoft bulk sender requirements.

Expert guidance for BeepDM development, including IDMEEditor usage, IDataSource implementations, IDataSourceHelper patterns, and ConfigEditor integration.

Detailed guidance for FormsManager mode transitions in BeepDM. Use when working with EnterQueryModeAsync, ExecuteQueryAndEnterCrudModeAsync, EnterCrudModeForNewRecordAsync, and related readiness or validation checks across blocks.

Break the Loop - Deep Bug Analysis

Use when searching GitHub for code examples, documentation, discussions, or solutions related to the user's question. Automatically triggers when context indicates need for implementation patterns, debugging help, technology selection, or best practices.

'Detailed model routing role definitions, decision flowchart, model tier grid, and fallback chain best practices. Load when authoring agents or debugging model routing.'

Publishable Prompt Engineering skill package that compiles a user request into a ready-to-use high-quality Prompt, with support for diagnosis, module injection, debugging, and evaluation.

Use when generating static map images with the Python `staticmap` library — embedding isochrone or drive-time polygon maps in Word (.docx) reports, placing facility or location markers over polygon fills using PIL, sizing maps for page layout, or debugging CircleMarker visibility, `m.transformer` AttributeErrors, or coordinate conversion failures. Triggers on: trade area map, isochrone map, drive-time map, map image too large, legend pushed to next page, markers not appearing, blank page in docx.

Project location and build context for The Maths Habit app. Use this skill whenever working on The Maths Habit codebase — building, debugging, updating, syncing Capacitor, generating AAB/IPA builds, or any development task. Also use when Claude needs to find or access the source code, or when the user says 'update the app', 'build the app', 'sync android', 'generate AAB', 'open the project', or references The Maths Habit source files. If the project folder isn't already mounted, this skill tells you where to find it.

Fix a bug following the Reproduce > Diagnose > Fix > Verify workflow. Use when something is broken, there's an error, or the user reports unexpected behavior.

Guide for using the Sentry CLI to interact with Sentry from the command line. Use when the user asks about viewing issues, events, projects, organizations, making API calls, or authenticating with Sentry via CLI. Primary workflow: given a short issue ID (e.g. PROJECT-123), fetch full bug report with description and stack trace.

Verify AWS infrastructure configuration before deployment. Use when validating VPC endpoints, NAT Gateway capacity, security groups, or debugging network path issues that cause Lambda connection timeouts.

Graph Operations — графы знаний, сущности и связи. ИСПОЛЬЗУЙ когда строишь граф знаний, ищешь по графу (LightRAG/GraphRAG), извлекаешь сущности, настраиваешь entity extraction, выбираешь режим поиска. Триггеры: 'граф знаний', 'сущности', 'связи', 'entities', 'LightRAG', 'GraphRAG', 'graph traversal', 'entity extraction', 'knowledge graph'. НЕ для векторного поиска (→ search-pipeline-debug).

Generate responsive breakpoint tokens: sm through 2xl.

- Extract the most likely root cause from logs.

**Skill Name**: browser-local-chrome-remote-debugging

Structured code debugging through hypothesis formation and falsification planning. Use when diagnosing bugs, unexpected behaviour, or system failures where the root cause is unclear. Produces a hypothesis document for execution by another agent rather than performing the investigation directly. Triggers on requests to debug issues, diagnose problems, investigate failures, or create debugging plans.

learn

Build generate_job_data binary (release or ASAN debug mode)

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

Create responsive web designs that work across all devices and screen sizes. Use when building mobile-first layouts, implementing breakpoints, or optimizing for different viewports. Handles CSS Grid, Flexbox, media queries, viewport units, and responsive images.

Diagnoses and fixes a failing CI run using systematic debugging.

Builds and debugs Interactive Brokers TWS API integration in C++ (twsapi)—connectivity, EReader/EClientSocket, contract builders (STK/OPT/FUT/BAG), market data and snapshot pricing, order CRUD and combo orders, EWrapper execution hooks, Docker/SDK/CMake, env IBKR_HOST/IBKR_PORT/IBKR_CLIENT_ID, tws/ibkr/ and controllers. Use when implementing or changing IBKR trading, pricing, contracts, or gateway wiring in the tws service.

>-

Use when an agent produces wrong output, fails on tools, or breaks in a multi-agent system. Decision tree for diagnosing agent failures.

Use when an agent stops responding mid-thought. Debugging pattern for conflicting rules.

Use when safety controls exist on paper but never fire. Debugging pattern for config-gated orphan resources.

Use when debugging silent Docker container path bugs. The one-liner that fixes container path resolution.

Use when a pipeline runs perfectly but processes nothing. Debugging pattern for enum mismatches.

Use when a system reports success but money never arrives. Debugging pattern for silent redemption failures.

Use when the user works with @hamdymohamedak/openfetch, openFetch, or a fetch-only HTTP client with interceptors, middleware, plugins (retry, timeout, hooks, debug), memory cache (TTL, stale-while-revalidate), fluent chaining (sugar), raw native Response, idempotency keys, or SSR/RSC-safe fetch in Node, browsers, Bun, Deno, or Workers. Use instead of guessing axios or XHR APIs.

Manage AI agent context effectively — what to include, what to exclude, compression strategies, and context hierarchy for optimal performance.

Debug Java and Kotlin JVM services using IDE debuggers, jdb, jstack, and jmap. Use this for exceptions, wrong output, transaction issues, thread problems, heap pressure, framework boundary bugs, and stale callsites.

Debug native C, C++, Rust, and other compiled runtime problems using gdb or lldb. Use this for crashes, corrupted output, dangling pointers, invalid object state, stale callsites, memory errors, and lifetime bugs.

Debug Python runtime and logic bugs using pdb or ipdb. Use this for wrong output, tracebacks, stale callsites, object-shape drift, async issues, import confusion, and runtime state mismatches.

Auto-fix layout issues. Snaps off-grid spacing, adds missing max-width constraints, and normalizes gap usage.

Keep UI professional, consistent, and readable under industrial debug workloads.

Root cause investigation methodology — loaded by agents when debugging failures to enforce evidence-first diagnosis over guess-and-fix approaches

>

/*

REPL-driven Clojure development for writing, editing, and debugging code. Triggers when working with Clojure files (.clj, .cljs, .cljc, .edn), handling namespaces, functions, or tooling. Provides idiomatic functional programming guidance through the REPL workflow.

strategies for agent observability (logging, tracing, metrics). Use this to instrument agents for debugging, performance tracking, and quality assurance.

>-

When debugging DuckLake branching issues, **always add debug logging to trace the operation as it happens**, rather than trying to analyze the result after the fact.

学习不走弯路，[关注公众号](#公众号) 回复「学习路线」，获取mall项目专属学习路线！

CLI tool to convert YouTube videos and playlists into AI-powered Markdown study notes using LLM APIs. Use when helping users run notewise, debug failures, configure providers, or contribute to the project.