Simulate a dependency outage on a live host (upstream DNS, an API endpoint, a backup target, a peer) to prove a watcher, failover or alert actually works, without paging anyone…
Use when investigating codebase, debugging deep errors, or auditing dependencies — evidence-first, file:line mandatory
Use when planning architecture refactoring, understanding cross-module dependencies, discovering hidden dependencies, finding shotgun surgery patterns, or identifying files that…
Use when monitoring code quality over time, measuring refactoring impact, tracking if complexity is improving or worsening, or validating technical debt work - tracks complexity…
Expert in data forensics, anomaly detection, audit trail analysis, fraud detection, and breach investigation
Use when team reorganization planning, identifying coordination inefficiencies, validating Conway's Law, assessing team-architecture fit, or planning service splits - analyzes…
Use when planning refactoring sprints, prioritizing technical debt backlog, justifying refactoring investment to executives, or creating data-driven roadmaps - calculates return…
Deep forensic debugging that never stops until root cause is found or visibility limit is proven. Use when user wants to understand exactly why something is broken, not work…
Use when investigating test suite issues, reducing CI/CD time, identifying brittle tests, finding test duplication, or analyzing test maintenance burden - reveals test code…
Forest Admin integration. Manage data, records, and automate workflows. Use when the user wants to interact with Forest Admin data.
Use when a task needs the judgment of a Forest and Conservation Technician — running a prism (BAF) timber cruise plot and resolving borderline tree calls, relocating and…
Use when a task needs the judgment of a Forest and Conservation Worker — planning or executing a seedling-planting contract, diagnosing a failed reforestation stocking survey,…
Use when targeting Forest Ecology and Management or deciding whether a forest-science manuscript fits this venue.
Use when a task needs the judgment of a Forest Fire Inspector/Prevention Specialist — setting or interpreting an industrial fire precaution level for logging/timber operations,…
Analyze data with `forest-plot-styler` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.
Analyse the current project and generate project-customised forge-kit agents, skills, and commands tailored to its stack, domain, and architecture.
Create or update an Architecture Decision Record for a durable technical decision. Use when the user asks to record a decision, alternatives matter, reversal is costly, or future…
Analyze vague user ideas and recommend architecture based on actual needs, not predefined categories.
Forge playbook for contract-first APIs. Use for API, REST, GraphQL, gRPC, OpenAPI, endpoint, auth, JWT, versioning, rate limit, idempotency, contract test, backend.
REST and RPC discipline for backend APIs. Resource naming, canonical error shape, cursor pagination implementation, idempotency keys, status code decision logic, versioning.
Guides building, deploying, troubleshooting, and installing Atlassian Forge apps — custom extensions built with the Forge CLI (forge create, forge deploy, forge install).
Add alpha blending, alpha testing, or additive blending to an SDL GPU project. Configure blend state, sort transparent objects, and set up clip/discard for cutout transparency.
Reviewing pull requests well. What to look at first, what to skip, severity prefixes, when to block vs approve, frame feedback as questions, never rewrite-as-review, reviewing…
Optimizes Atlassian Forge apps to reduce platform consumption and avoid unnecessary costs using Atlassian's "Optimise Forge platform costs" guidance.
Forge systematic-debugging playbook. Use for ANY bug, crash, stack trace, failing test, or regression — debug, root cause, bisect, flaky test — before proposing a fix.
Production-grade Dockerfiles. Multi-stage builds, non-root execution, deterministic dependencies, sub-200MB final image, signal-handling exec-form CMD, build-time secret mounts,…
Next.js 16 with React Server Components and Tailwind 4. Server-first by default, streaming with Suspense, server actions over API routes, app router conventions, async page…
Forge playbook for full-stack apps — frontend + backend + database + auth. Use for full-stack, SaaS, CRUD app, Postgres, Supabase, JWT, session, signup, dashboard.
GraphQL schema design. Nullable defaults, connections (cursor pagination via Relay spec), errors as data not throws, DataLoader for N+1, persisted queries for caching, schema…
Build production-grade infrastructure as code for a service or project. Use when asked to "set up infra", "provision infrastructure", "create cloud resources", "IaC for this…
Production-grade Kubernetes manifests. Pinned images, resource requests + memory limits (no CPU limits), securityContext (non-root, read-only root, drop all caps, RuntimeDefault…
Safe Postgres and MySQL migrations. Lock-free patterns, batched backfills, the NOT VALID + VALIDATE dance, reversibility, zero-downtime deploys, separating index DDL from…
Generates a mind map (nodes+edges) to visualize a plan or architecture. Use when a plan has enough branching that a graph reads clearer than prose — mind map, visualize the plan.
Forge playbook for production ML systems (opt-in Python) — training-to-serving lifecycle. Use for MLOps, model registry, MLflow, drift monitoring, A/B test, canary, rollback.
When to spawn subagents vs do work inline. Patterns - fan-out, sequential, orchestrator/worker, judge/critic, retry-with-fallback, pipeline.
Prompt design for LLM-powered applications. System prompts, structured outputs, tool descriptions, few-shot examples, anti-injection defenses, output validation, versioning,…
Rate-limiting discipline for HTTP and queue handlers. Token bucket as the default, sliding window for per-second precision, fixed window only for low-volume.
Rules-of-Hooks discipline for React. Hooks must be called unconditionally at the top of a component or another hook - never inside an if/else, loop, ternary, short-circuit (&& /…
Structured report formats for Claude — card-based, human-readable, no ASCII frame noise. Use when finishing a multi-step task (≥5 tool calls, ≥3 files modified, multi-task…
Standard test protocol for a new/changed Forge skill: activation-test (trigger vs near-miss phrases, target >=95%) + opt-in fresh-session A/B benchmark.
Define the requirements for a clear feature, refactor, workflow, or significant change before planning or implementation.
Merge feature branch to baseBranch for staging deployment. Triggered when an issue reaches pass status — merges the ISS-* branch to the project's baseBranch and sets status to…
Unit + integration + e2e discipline. Real DB over mocks, deterministic data, no shared state, descriptive failure messages, no skipped tests committed, no sleeps, parallel-safe.
TypeScript discipline. No `any`, narrow types via `unknown`, exhaustive unions with `assertNever`, branded primitives, Result types, schema-validated boundaries with zod.
Fork management lifecycle for Azure OSDU SPI service forks — three-branch strategy, upstream sync, cascade integration, conflict resolution, template propagation, and multi-repo…
To manage form state, validation, and submission efficiently without causing excessive re-renders, unlike controlled components.
Architectural patterns beyond fat models — form objects for multi-model form binding, query objects for complex AR querying, presenters / decorators for view logic.
Test WordPress form submissions and email delivery. Validates contact forms, checks WP Mail SMTP configuration, and sends test emails.
End-to-end form handling with react-hook-form, Zod schemas, validation patterns, error messaging, field arrays, and multi-step wizards.
Exhaustive testing of form validation logic including boundary values, injection payloads, encoding edge cases, and client-server validation bypass techniques
Expert guide for mathematical formal verification, SMT solver constraints (Z3, Dafny, TLA+), invariant theorem proving for FinTech billing state machines, RBAC/ABAC authorization,…
数据格式转换专业版面向需要在大规模数据与多源系统间进行格式转换的专业开发者与数据工程师,提供完整的批量、流式、自动化转换能力。核心能力: - 涵盖免费版全部能力,无文件大小与数量限制 - 批量转换:目录级批量处理,支持通配符与递归 - 流式转换:大文件分块读取与流式输出,支持 GB 级 - 自定义字段映射:重命名、过滤、合并、拆分字段 -…
Guide SwiftLint and SwiftFormat integration across CLI, Xcode build phases, Xcode source-editor workflows, Swift Package plugins, AppleScript, Git hooks, and GitHub Actions,…
i18n cho React apps — react-intl, FormatJS. Dùng khi implement đa ngôn ngữ, format số/ngày/tiền tệ chuẩn theo locale.
Use when the task is to apply SwiftUI formatting conventions, MARK comment organization, modifier-chain readability, preview style, or safe editing/improvement/optimization of…
Formats WPF XAML and C# code using XamlStyler and dotnet format. Generates Settings.XamlStyler and .editorconfig files automatically.
Read a multi-service OpenProse program directory, analyze all service contracts, and generate the Forme wiring manifest for inspection and debugging
Forms knowledge base - react-hook-form, Zod validation, Server Actions, file upload, multi-step forms.
ACTIVATE when the user works on authentication in Laravel. This includes login, registration, password reset, email verification, two-factor authentication (2FA/TOTP/QR…
Set up the @main App struct for FOSMVVM SwiftUI apps. Configures MVVMEnvironment, deployment URLs, and test infrastructure.