coding-agent-skills

Expert web accessibility (a11y): WCAG 2.2 AA, semantic HTML, ARIA, keyboard, and screen readers. Trigger keywords: accessibility, a11y, WCAG, ARIA, role, screen reader, keyboard navigation, focus, focus trap, contrast, alt text, semantic HTML, label, axe, tab order. Use to build accessible UI, audit/fix a11y issues, or add accessible behavior to widgets.

Expert API design for REST & GraphQL: resource modeling, status codes, versioning, pagination, idempotency, errors, and contracts. Trigger keywords: API design, REST, RESTful, GraphQL, OpenAPI, endpoint, status code, versioning, pagination, cursor, idempotency, rate limit, contract, schema. Use to design or review HTTP/GraphQL APIs and their contracts.

Expert Bash scripting: robust, safe, portable shell scripts. Trigger keywords: bash, shell script, sh, quoting, word splitting, set -euo pipefail, trap, IFS, getopts, mktemp, shellcheck, POSIX, CLI, automation. Use for writing/debugging shell scripts and automation, or fixing quoting, exit-code, and portability bugs.

Expert modern C++ (17/20/23): safe, performant code, RAII, move semantics, templates/concepts, and UB diagnosis. Trigger keywords: C++, C++17, C++20, C++23, smart pointer, unique_ptr, RAII, move semantics, rvalue, template, concept, STL, undefined behavior, constexpr, memory, dangling. Use for C++ implementation, optimization, generic programming, or UB/memory issues.

Expert systematic debugging and root-cause analysis. Trigger keywords: debug, bug, error, exception, crash, stack trace, reproduce, root cause, works on my machine, intermittent, heisenbug, regression, git bisect, race condition. Use to diagnose failures methodically, find the real cause, and stop guess-and-check fixing.

Expert Docker: Dockerfiles, multi-stage builds, image size/cache optimization, Compose, and container best practices. Trigger keywords: Docker, Dockerfile, container, image, multi-stage, layer cache, docker-compose, .dockerignore, entrypoint, distroless, non-root, healthcheck, build context. Use for writing/optimizing Dockerfiles, shrinking images, faster builds, or Compose setup.

Expert Git & GitHub: workflows, history recovery, pull requests, branch protection, and Actions CI/CD. Trigger keywords: git, GitHub, merge conflict, rebase, cherry-pick, reflog, bisect, force push, pull request, branch protection, GitHub Actions, CI/CD, release, conventional commits. Use for Git troubleshooting, collaboration/automation setup, or recovering lost work.

Expert idiomatic Go: concurrency, interfaces, error handling, and the standard library. Trigger keywords: Go, golang, goroutine, channel, context, select, interface, error wrapping, errors.Is, defer, sync, Mutex, WaitGroup, errgroup, race, pprof. Use for writing/refactoring Go, designing concurrency, or fixing races, leaks, and deadlocks.

Expert Kubernetes: workloads, services, config, probes, resources, and troubleshooting. Trigger keywords: Kubernetes, k8s, Deployment, StatefulSet, Service, Pod, ConfigMap, Secret, Ingress, liveness, readiness, probe, requests, limits, HPA, kubectl, Helm, CrashLoopBackOff, ImagePullBackOff, OOMKilled. Use for writing manifests, configuring workloads, or debugging cluster issues.

Expert Next.js App Router: Server vs Client Components, data fetching, caching, server actions, and rendering strategy. Trigger keywords: Next.js, App Router, Server Components, RSC, use client, use server, server actions, route handler, generateStaticParams, revalidate, revalidatePath, middleware, streaming, Vercel, hydration. Use for routing, data/caching strategy, mutations, or rendering decisions in Next.js.

Expert Node.js backends (Express/Fastify/Hono): routing, middleware, validation, auth, async, and production hardening. Trigger keywords: Node.js, Express, Fastify, Hono, REST, middleware, JWT, session, zod, async, streams, unhandled rejection, graceful shutdown, backend, server. Use for building HTTP services, structuring backends, or fixing async/error/security issues.

Expert performance optimization across CPU, memory, I/O, and rendering. Trigger keywords: performance, slow, profiling, profiler, optimize, latency, throughput, p99, memory leak, allocation, bottleneck, benchmark, flamegraph, N+1, cache. Use to diagnose and fix performance problems with a measure-first methodology.

Expert prompt engineering: prompt structure, few-shot, chain-of-thought, structured output, and iteration. Trigger keywords: prompt, prompt engineering, system prompt, few-shot, chain-of-thought, output format, JSON schema, structured output, instructions, role, examples, eval. Use for writing, debugging, or optimizing prompts for LLMs.

Expert Python: Pythonic code, typing, async, the standard library, and performance. Trigger keywords: Python, PEP 8, type hints, mypy, asyncio, generator, decorator, context manager, dataclass, pytest, pandas, numpy, packaging, uv, GIL, profiling. Use for writing/refactoring Python, fixing bugs, performance, or library/tooling guidance.

Expert Retrieval-Augmented Generation: chunking, embeddings, vector/hybrid search, reranking, and grounded answers. Trigger keywords: RAG, retrieval, embeddings, vector database, chunking, reranking, hybrid search, BM25, grounding, citations, hallucination, context window, recall. Use to build or debug RAG pipelines and improve answer quality/faithfulness.

Expert modern React (18/19): hooks, component design, state, performance, and Server Components. Trigger keywords: React, hooks, useState, useEffect, useMemo, useCallback, useRef, context, re-render, key, Suspense, Server Components, RSC, JSX, stale closure. Use when building/refactoring components or hooks, fixing render/effect bugs, or choosing a state-management approach.

Expert safe, incremental, behavior-preserving refactoring. Trigger keywords: refactor, code smell, cleanup, technical debt, extract function, rename, inline, decouple, simplify, guard clause, legacy code, duplication, god class. Use to restructure code without changing behavior, reduce complexity, or pay down tech debt safely.

Expert Rust: ownership, borrowing, lifetimes, traits, async, and idiomatic error handling. Trigger keywords: Rust, ownership, borrow checker, lifetime, move, clone, trait, generics, async, tokio, Result, Option, ?, thiserror, anyhow, unsafe, Arc, Mutex, cargo, Send, Sync. Use for writing/refactoring Rust, resolving borrow-checker/lifetime errors, or designing safe abstractions.

Expert defensive application security and secure code review (OWASP Top 10). Trigger keywords: security, vulnerability, OWASP, injection, SQL injection, XSS, CSRF, SSRF, authentication, authorization, access control, secrets, JWT, session, dependency, secure coding, sanitization. Use to write secure code, review a diff for vulnerabilities, or harden an app. Defensive use only.

Expert SQL & relational databases: queries, schema design, indexing, query-plan optimization, and transactions (Postgres/MySQL/SQLite). Trigger keywords: SQL, database, Postgres, MySQL, SQLite, JOIN, index, EXPLAIN, query plan, slow query, N+1, normalization, transaction, isolation, deadlock, migration. Use for writing/optimizing queries, designing schemas, or fixing slow/locking queries.

Expert Tailwind CSS: utility-first styling, responsive/dark mode, theming, and design systems. Trigger keywords: Tailwind, CSS, utility classes, responsive, breakpoints, dark mode, design tokens, theme, @apply, cva, clsx, class-variance-authority, arbitrary values, shadcn. Use for styling UIs, responsive layouts, theming, or untangling class soup.

Expert software testing: unit/integration/e2e, TDD, test doubles, fixtures, and flakiness. Trigger keywords: testing, unit test, integration test, e2e, TDD, mock, stub, fake, spy, fixture, coverage, flaky test, assertion, test pyramid, snapshot. Use for writing tests, designing test strategy, or fixing flaky/brittle/slow tests.

Expert TypeScript: type system, generics, narrowing, inference, and strict-mode safety. Trigger keywords: TypeScript, types, generics, type narrowing, tsconfig, strict, discriminated union, conditional/mapped types, utility types, declaration files, type error, satisfies, infer, any vs unknown. Use when writing/refactoring TS, fixing cryptic type errors, designing type-safe/generic APIs, or configuring the compiler.

Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.

Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.

Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.

Three.js lighting - light types, shadows, environment lighting. Use when adding lights, configuring shadows, setting up IBL, or optimizing lighting performance.

Three.js materials - PBR, basic, phong, shader materials, material properties. Use when styling meshes, working with textures, creating custom shaders, or optimizing material performance.

Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.

Use this skill when user needs to solve competitive programming problems. Applicable to LeetCode, Codeforces, AtCoder and similar platforms. Triggers include: algorithm problem, coding challenge, time complexity analysis, data structure implementation, TLE (Time Limit Exceeded), MLE (Memory Limit Exceeded).

Use this skill when user needs to design deep learning models, perform training optimization, interpret papers, or solve engineering practice issues. Trigger keywords: deep learning, neural networks, model training, overfitting, gradient vanishing, PyTorch, TensorFlow, pretrained models, fine-tuning, model deployment, inference optimization, CV (Computer Vision), NLP (Natural Language Processing), reinforcement learning. Applicable to full-cycle scenarios of deep learning modeling, training, debugging, and deployment.

Use this skill when user needs to design LLM evaluation strategies, build test datasets, or ensure model quality. Trigger keywords: LLM testing, model evaluation, prompt engineering, regression testing, red teaming, hallucination detection, RAG testing, Agent testing, A/B testing, LLM-as-a-Judge. Applicable to quality assurance in model development and application deployment.

Use this skill when user needs system architecture design, technology stack selection, or architecture review. Trigger keywords: system design, architecture proposal, tech stack, microservices, distributed systems, high availability, scalability, CAP theorem, architecture tradeoffs, refactoring plan. Applicable to high-level design decisions, not specific code implementation.