AI Agent Workflow Collection

Expert agent for the Apple Store Connect API. Use when the user asks questions about the App Store Connect API or needs to automate tasks involving TestFlight, In-App Purchases, Provisioning, App Metadata, Reporting, or Game Center.

Run chaos engineering experiments using Chaos Monkey, Litmus, or…

Generate a complete, production-ready CLI in Bun from a SPEC (OpenAPI, JSON Schema, markdown contract, or natural-language description). Outputs a runnable binary with commander-style arg parsing, shell autocomplete, --help generation, man page, and token-aware output formatting. Use when you need to turn an API spec or feature description into a working CLI in minutes.

Comprehensive code review expertise. Use when reviewing code, evaluating architecture, or assessing quality. Triggers on review, evaluate, assess, audit, code quality, best practices.

Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for agents.

Database index optimization advisor for PostgreSQL, MySQL, and SQLite. Analyzes slow queries, missing indexes, unused indexes, and over-indexed tables. Generates CREATE INDEX statements with EXPLAIN ANALYZE estimates. Use when queries are slow, p99 DB latency spikes, or when reviewing a new schema.

Feature flag implementation, management, and cleanup. Handles flag creation, gradual rollout strategies, A/B testing wiring, stale flag detection, and safe flag removal. Supports LaunchDarkly, Unleash, GrowthBook, Statsig, custom env-var flags, and database-backed toggles. Use when adding gated features, rolling out gradually, or cleaning up old flags.

Expert GitHub CLI plugin containing multiple skills for PR management, issue tracking, and GitHub workflows automation.

Search GitHub for code examples and patterns. Use when user asks to "search GitHub", "find examples on GitHub", "how do people implement X", or needs real-world code patterns.

Executes autonomous Loop Engineering cycles (Autoresearch) for continuous code and metric optimization.

Applies Karpathy's "A Recipe for Training Neural Networks" adapted to software engineering. Forces a minimum runnable baseline before optimizing, one knob at a time, with verifiable eval at the beginning. Use when implementing a new feature, doing a non-trivial refactor, integrating an external service, or when the user says "implement X from scratch", "how to start feature Y", "recipe", "incremental approach", "baseline first".

Maintains docs/ in the Karpathy-style LLM-wiki standard. Generates docs/llms.txt (flat machine-readable index conforming to llmstxt.org), validates broken links, enforces a minimum front-matter in new .md files (title, status, updated, related), groups orphan docs. Use when the user says "update docs index", "generate llms.txt", "audit docs", "organize wiki", "cure documentation", or after adding/renaming a file in docs/.

Generate OpenAPI 3.1 specs from existing code (routes, controllers, types, Zod/Joi schemas), or generate code from an existing spec. Produces valid openapi.yaml, typed client SDKs, mock servers, and Postman collections. Use when documenting an API, onboarding clients, generating typed SDKs, or migrating to spec-first development.

Generate complete Postman collections and environments from OpenAPI/Swagger specs or code routing files. Includes rich JS tests validating RESTful compliance (status codes, body schema, response headers) and automates Newman setup/execution.

Meta-skill gatekeeper that runs FIRST on every task to decide which other skill(s) — if any — should activate. Analyzes the user request, matches it against a ranked catalog (frontend-design, ui-ux-pro-max, superpowers/planning, git-, mcp-builder, smart-dispatch, claude-api, etc.), and emits a tight SELECTION plan so other skills are loaded on-demand only. Minimizes token/context consumption by refusing to activate heavy skills unless clearly justified. Triggers on ANY user instruction that could plausibly benefit from a specialized skill — i.e. essentially every turn that starts new work. Keywords: "plan", "design", "ui", "ux", "implement", "build", "create", "fix", "refactor", "commit", "pr", "review", "test", "debug", "deploy", "mobile", "video", "mcp", "skill", "architecture", "api", "ci", "docs", "copy", "social", "setup", "doctor".

Automatically routes tasks to the optimal AI agent, model, or provider based on complexity, cost, and capability. Use when implementing features, fixing bugs, or any multi-step development work. Triggers on "implement", "build", "create", "fix", "add feature", "develop", or when the user asks to do any coding task.

代码追溯专家 - 查找代码修改者、关联PR、获取改动背景。 触发词: 谁改的, 谁写的, blame, 追溯, 找作者, 这行代码, 提交记录, 谁提交的, PR,…

Bilingual content synchronization validator for young-personal-site. Ensures perfect zh-TW/en translation consistency.

Cria um Manager e QuerySet customizado Django para um model do SurveyHub, com métodos em português seguindo o padrão do projeto (ativos, naodeletados, dousuario, comcontagens, otimizado). Adiciona anotações com Count/Prefetch, filtros de domínio e busca textual. Segue .claude/rules/architecture/django-orm.md e naming-conventions.md. Use quando o usuário disser "criar manager", "adicionar manager customizado", "filtro de ORM", "queryset customizado", "método no manager", "adicionar ativos()", "filtro no banco", "otimizar queries", "prefetch", "selectrelated", "anotação com Count". DO NOT USE para criar o model inteiro — use /novo-modelo. DO NOT USE para lógica envolvendo múltiplos models — use /nova-service.

Interrogatório implacável para planos e designs. Estressa planos antes de implementar. Baseado em grill-me/grilling de Matt Pocock.