Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
Write a complete Numerai experiment report in experiment.md (abstract, methods, results tables, decisions, next steps) and generate/link the standard show_experiment plot(s). Use after running any Numerai research experiments, or when a user asks for a “full report”, “write up”, “experiment.md update”, or “generate the standard plot”.
Design and manage Numerai experiments in this repo for any model idea.
Add a new Numerai model type to the agents training pipeline. Use when you need to register a model in `agents/code/modeling/utils/model_factory.py`, handle fit/predict quirks in `agents/code/modeling/utils/numerai_cv.py`, and update configs so the model can run via `python -m agents.code.modeling`.
Create Numerai Tournament model upload pickles (.pkl) with a self-contained predict() function. Use when preparing upload artifacts, debugging numerai_predict import errors, or documenting model-upload requirements and testing steps.
End-to-end Numerai research workflow for trying a new idea: design experiments, implement new model types if needed, run scout→scale experiments, write a full experiment.md report with standard plots, and optionally package/upload a Numerai pickle. Use when a user asks to “try/test a new idea”, “run an experiment”, “sweep configs”, “compare model variants”, or otherwise do new Numerai research.
Golang data structures — slices (internals, capacity growth, preallocation, slices package), maps (internals, hash buckets, maps package), arrays, container/list/heap/ring, strings.Builder vs bytes.Buffer, generic collections, pointers (unsafe.Pointer, weak.Pointer), and copy semantics. Use when choosing or optimizing Go data structures, implementing generic containers, using container/ packages, unsafe or weak pointers, or questioning slice/map internals.
Comprehensive guide for dependency injection (DI) in Golang. Covers why DI matters (testability, loose coupling, separation of concerns, lifecycle management), manual constructor injection, and DI library comparison (google/wire, uber-go/dig, uber-go/fx, samber/do). Use this skill when designing service architecture, setting up dependency injection, refactoring tightly coupled code, managing singletons or service factories, or when the user asks about inversion of control, service containers, or wiring dependencies in Go.
Implements dependency injection in Golang using samber/do. Apply this skill when working with dependency injection, setting up service containers, managing service lifecycles, or when you see code using github.com/samber/do/v2. Also use when refactoring manual dependency injection, implementing health checks, graceful shutdown, or organizing services into scopes/modules.
Provides a guide for setting up Golang project layouts and workspaces. Use this whenever starting a new Go project, organizing an existing codebase, setting up a monorepo with multiple packages, creating CLI tools with multiple main packages, or deciding on directory structure. Apply this for any Go project initialization or restructuring work.
Continuously modernize Golang code to use the latest language features, standard library improvements, and idiomatic patterns. Use this skill whenever writing, reviewing, or refactoring Go code to ensure it leverages modern Go idioms. Also use when the user asks about Go upgrades, migration, modernization, deprecation, or when modernize linter reports issues. Also covers tooling modernization: linters, SAST, AI-powered code review in CI, and modern development practices. Trigger this skill proactively when you notice old-style Go patterns that have modern replacements.
Generating rich inline SVG diagrams to visually explain systems, processes, architectures, and abstract concepts.
Philosophy, decision-making framework, and technical skills for delivering visual, interactive, and educational AI responses.
This skill is for interface design — dashboards, admin panels, apps, tools, and interactive products. NOT for marketing design (landing pages, marketing sites, campaigns).
Leverage OpenAI Codex/GPT models for autonomous code implementation. Triggers: "codex", "use gpt", "gpt-5", "gpt-5.2", "let openai", "full-auto", "用codex", "让gpt实现".
Plan and run a series of training experiments, then compare results
使用 zombie 进行多协议暴力破解。zombie 是 chainreactors 出品的高性能暴力破解工具，支持 SSH/FTP/MySQL/MSSQL/PostgreSQL/Redis/SMB/RDP/SNMP/LDAP/VNC 等 20+ 协议，内置智能字典生成和分布式模式。与 hydra 的区别：zombie 支持更多协议、更快的并发、以及基于规则的字典生成。当需要批量弱口令检测、凭据喷洒时使用此技能
Kubernetes 容器逃逸与集群攻击。当目标运行在 K8s 环境中、发现 6443/10250/2379 端口、获取到 ServiceAccount Token、或已在容器内时使用。覆盖容器逃逸、Pod 提权、API Server 未授权、etcd 泄露、RBAC 滥用、节点接管。任何涉及 Kubernetes、容器编排、云原生安全的场景都应使用此技能
