aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Back-of-envelope calculations for system design. Use when estimating QPS, storage, bandwidth, or latency for capacity planning. Includes latency numbers every programmer should know and common estimation patterns.
Create custom React Native native modules for iOS and Android. Use when integrating native SDKs, optimizing performance-critical code, or accessing platform-specific APIs. Trigger words include "native module", "bridge", "native code", "iOS bridge", "Android bridge", "Turbo Module".
Use when designing data platforms, choosing between data lakes/lakehouses/warehouses, or implementing data mesh patterns. Covers modern data architecture approaches.
Central authority for Gemini CLI sandboxing and isolation. Covers Docker, Podman, macOS Seatbelt profiles, and security boundaries. Use when enabling sandboxing, choosing sandbox methods, configuring Seatbelt profiles, or troubleshooting sandbox issues. Delegates 100% to gemini-cli-docs for official documentation.
Design ETL/ELT pipelines with proper orchestration, error handling, and monitoring. Use when building data pipelines, designing data workflows, or implementing data transformations.
Design performance test strategies including load profiles, capacity planning, SLA validation, and .NET performance testing with NBomber and k6.
DevSecOps methodology guidance covering shift-left security, SAST/DAST/IAST integration, security gates in CI/CD pipelines, vulnerability management workflows, and security champions programs.
OCaml 5 algebraic effects design patterns. Use when Claude needs to: (1) Design APIs that interact with effect-based schedulers, (2) Decide between effects vs exceptions, (3) Integrate libraries with Eio or affect, (4) Handle suspension vs error cases in streaming code, (5) Understand the layered effect design principle
Eio concurrency patterns for OCaml applications. Use when Claude needs to: (1) Write concurrent OCaml code with Eio, (2) Handle network operations with cohttp-eio, (3) Manage resource lifecycles with switches, (4) Implement rate limiting or synchronization, (5) Create parallel operations with fibers, (6) Test async code with Eio_mock, (7) Integrate with bytesrw for streaming, or any other Eio-based concurrency tasks
Implement data quality checks, validation rules, and monitoring. Use when ensuring data quality, validating data pipelines, or implementing data governance.
Choose optimal Next.js rendering strategy (SSR, SSG, ISR, CSR) based on content type, update frequency, and performance requirements. Use when deciding how to render pages, optimizing performance, or implementing data fetching. Trigger words include "rendering", "SSR", "SSG", "ISR", "static", "server-side".
Guide technical communication for software developers. Covers email structure, team messaging etiquette, meeting agendas, and adapting messages for technical vs non-technical audiences. Use when drafting professional messages, preparing meeting communications, or improving written communication.
Designing and implementing robust command-line interfaces using OCaml's cmdliner library, following Daniel Bünzli's design principles. Use when Claude needs to: (1) Design a new CLI or subcommand layout, (2) Implement cmdliner terms and combinators, (3) Enforce clear, predictable, orthogonal options, (4) Produce high-quality --help output and error messages, (5) Integrate cmdliner CLIs into dune-based OCaml projects.
Set up task-based multi-agent systems with shared task files. Use when setting up parallel agent execution, designing worktree isolation patterns, or implementing task file coordination.
Comprehensive authorization guidance covering RBAC, ABAC, ACL, ReBAC, and policy-as-code patterns. Use when designing permission systems, implementing access control, or choosing authorization strategies.
Adaptive Python development guide with tiered complexity levels (Minimal/Standard/Full). Automatically selects appropriate guidance based on project context - from simple scripts (just clean Python code) to full production systems (complete tooling ecosystem). Covers modern conventions, testing, tooling, security, and best practices. Use when writing Python code, converting scripts, setting up projects, or building production systems. Keywords: PEP-8, Ruff, pytest, mypy, simple scripts, project structure, PyPI, packaging, type hints, clean code
Use when implementing design token systems, CSS variable architectures, or Style Dictionary pipelines. Covers token schemas, naming conventions, token transformations, and multi-platform token delivery for design systems.
Use when implementing responsive images, format conversion, focal point cropping, or image processing pipelines. Covers srcset generation, WebP/AVIF conversion, lazy loading, and image transformation APIs for headless CMS.
Optimize GitHub Actions matrix strategies for testing across multiple versions, platforms, and configurations. Use when configuring matrix builds, testing multiple versions, cross-platform testing, or optimizing CI resource usage. Trigger words include "matrix strategy", "test matrix", "multiple versions", "cross-platform".
Use when designing category hierarchies, tag systems, faceted classification, or vocabulary management for content organization. Covers flat vs hierarchical taxonomies, term relationships, multi-taxonomy content, and taxonomy APIs for headless CMS.
Set up monitoring, logging, and alerting for infrastructure and applications. Use when implementing observability, creating dashboards, or configuring alerts.
Frameworks for effective mentoring and knowledge transfer. Use for 1:1 meetings, pair programming, onboarding, teaching technical concepts, and developing junior engineers.
Requirements prioritization techniques including MoSCoW, Kano Model, WSJF (SAFe), and Wiegers' Value/Cost/Risk matrix. Provides scoring frameworks, trade-off analysis, and priority visualization. Use when ranking requirements by business value, customer impact, or implementation efficiency.
Create Level 6 template meta-prompts that generate other prompts. Use when building prompt generators, designing high-leverage meta-prompts, or creating templates that scaffold other prompts.