Loading...
Loading...
Found 973 Skills
Use ONLY when creating NEW registrable components in ML projects that require Factory/Registry patterns. ✅ USE when: - Creating a new Dataset class (needs @register_dataset) - Creating a new Model class (needs @register_model) - Creating a new module directory with __init__.py factory - Initializing a new ML project structure from scratch - Adding new component types (Augmentation, CollateFunction, Metrics) ❌ DO NOT USE when: - Modifying existing functions or methods - Fixing bugs in existing code - Adding helper functions or utilities - Refactoring without adding new registrable components - Simple code changes to a single file - Modifying configuration files - Reading or understanding existing code Key indicator: Does the task require @register_* decorator or Factory pattern? If no, skip this skill.
Industry-standard Terraform patterns, modular structure, and security validation. Use when reviewing, refactoring, or authoring Terraform code (.tf files) to ensure maintainability and security.
Python design patterns for CLI scripts and utilities — type-first development, deep modules, complexity management, and red flags. Use when reading, writing, reviewing, or refactoring Python files, especially in .trellis/scripts/ or any CLI/scripting context. Also activate when planning module structure, deciding where to put new code, or doing code review.
Statistical rule discovery through measurement of Go codebases: Count patterns, derive confidence-scored rules, produce Style Vector fingerprint. Use when analyzing codebase conventions, extracting implicit coding rules, profiling a repo before onboarding or PR automation. Use for "analyze codebase", "find coding patterns", "what conventions does this repo use", "extract rules", or "codebase DNA". Do NOT use for code review, bug fixes, refactoring, or performance optimization.
RED-GREEN-REFACTOR cycle with strict phase gates. Write failing test first, implement minimum code to pass, then refactor while keeping tests green. Use when implementing new features, fixing bugs with test-first approach, improving test coverage, or when user mentions TDD. Use for "TDD", "test first", "red green refactor", "write tests", or "implement with tests". Do NOT use for debugging existing failures (use systematic-debugging) or for refactoring without new tests (use systematic-refactoring).
Evidence-based 4-phase root cause analysis: Reproduce, Isolate, Identify, Verify. Use when user reports a bug, tests are failing, code introduced regressions, or production issues need investigation. Use for "debug", "fix bug", "why is this failing", "root cause", or "tests broken". Do NOT use for feature requests, refactoring, or performance optimization without a specific bug symptom.
OpenAI Codex Rust coding patterns distilled from the codex-rs workspace. Use this skill whenever writing, reviewing, or refactoring Rust code — especially for async agents, CLI tools, sandboxing, Ratatui TUIs, JSON-RPC protocols, tokio-based services, or any codebase that needs defensive panic discipline. Trigger even when the user does not explicitly mention Codex, because the patterns generalize to any production Rust workspace. Covers async cancellation, error enum design, process sandboxing, Cargo workspace architecture, wiremock-based fakes, insta snapshot testing, OpenTelemetry tracing, and Ratatui rendering.
Post-implementation quality check via fresh-eyes review. Chain: Implement → Review (independent agent) → Resolve (if issues). Max 2 rounds. Auto-triggers for security-sensitive and data-mutation code. Not for code refactoring (use code-cleanup). Not for decision analysis (use agent-room). For post-deploy verification, see deploy-verify. For shipping and PRs, see ship.
Guides systematic PyTorch recommender-system model development across compact data facts, existing source code, configs, focused tests, and training loops without overloading context from broad research archives. Use when building, debugging, or refactoring torch/nn.Module RecSys models with Transformer/HSTU/attention blocks, sparse/dense/list feature fusion, pCVR/CTR heads, ablation axes, or competition codebases where many model ideas exist but bugs and interface drift must be controlled. 用来指导推荐系统 PyTorch 模型开发、Transformer/HSTU 建模、关键数据事实、特征交互、shape/debug、训练闭环和已有模型结构的系统化推进。
Use when creating a plan using Plan model and enhancing structured design plans in Cursor Plan mode for Java implementations. Use when the user wants to create a plan, design an implementation, structure a development plan, or use plan mode for outside-in TDD, feature implementation, or refactoring work. This should trigger for requests such as Create a plan with Cursor Plan mode; Write a plan with Claude Plan mode; Design an implementation plan; Structure a development plan. Part of cursor-rules-java project
Comprehensive React and Next.js performance optimization guide with 40+ rules for eliminating waterfalls, optimizing bundles, and improving rendering. Use when optimizing React apps, reviewing performance, or refactoring components.
Tailwind CSS v4 performance optimization and best practices guidelines (formerly tailwindcss-v4-style). This skill should be used when writing, reviewing, or refactoring Tailwind CSS v4 code to ensure optimal build performance, minimal CSS output, and correct usage of v4 features. Triggers on tasks involving Tailwind configuration, @theme directive, utility classes, responsive design, dark mode, container queries, or CSS generation optimization.