探索开发、内容、数据与办公效率等 AI 技能。先比较用途和仓库热度，再查看技能说明与来源。
Guide for writing, refactoring, and testing MoonBit projects. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/test/doc/ide), or following MoonBit-speci...
Reproduce a SkiaSharp issue systematically and capture structured reproduction results. Handles bugs (verify reported behavior) and enhancements (confirm feature is missing). Produces schema-validated JSON with...
Implement SkiaSharp GitHub issues with proper context gathering and planning. Use when user provides a GitHub issue URL (github.com/mono/SkiaSharp/issues/NNNN), says "implement issue #NNNN", "work on #NNNN", "f...
Tag and finalize a SkiaSharp release after packages are published. Use when user says "tag X", "finish release X", or "finalize X". This is the FINAL step - after packages are live. Tags cannot be deleted so on...
Create a release branch for SkiaSharp. Use when user says "release X", "start release X", or "create release branch for X". This is the FIRST step of releasing - creates branch and pushes to trigger CI. Uses co...
Write and review XML API documentation for SkiaSharp following .NET guidelines. Use when user asks to document a class, add XML docs, write XML documentation, add triple-slash comments, review documentation qua...
Backport docs/examples changes to a pre-existing ZenML release. Use when changes merged to `develop` need to be reflected in a live release version. Triggers include "backport", "cherry-pick to release", "updat...
Build stateful backends with Rivet Actors: high-performance, long-lived, in-memory, persisted processes. Use when you outgrow HTTP, databases, or queues. Trigger on tasks related to AI agents, multiplayer apps...
Bisect PyTorch commits to find the regression that breaks TorchTitan. Use when the user wants to bisect PyTorch or invokes /torch_bisect.
Guide for benchmarking FlashInfer kernels with CUPTI timing
Tutorial for debugging CUDA crashes using API logging
Step-by-step tutorial for adding new CUDA kernels to FlashInfer
Migrate codebase from try/catch or Promise-based error handling to better-result. Use when adopting Result types, converting thrown exceptions to typed errors, or refactoring existing error handling to railway-...
End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs deterministic placement and navigation in a multi-p...
Test the Expensify App using Playwright browser automation. Use when user requests browser testing, after making frontend changes, or when debugging UI issues
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or meas...
Browser automation with Playwright and real cookies. Use 'grab browser execute ""' to run Playwright code.
Discover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixing bugs, or refactoring code.
Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria...
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structur...
Use when users need to debug, modify, or extend the code-forge application's CLI commands, argument parsing, or CLI behavior. This includes adding new commands, fixing CLI bugs, updating command options, or tro...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends your capabilities with specialized knowledge, workflows, or tool i...
Execute structured task plans with status tracking. Use when the user provides a plan file path in the format `plans/{current-date}-{task-name}-{version}.md` or explicitly asks you to execute a plan file.
Convert natural language questions into SQL queries. Activates when users ask data questions in plain English like "show me users who signed up last week" or "find orders over $100".
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。