f8-features-obfuz-workflow
Use when implementing or troubleshooting Obfuz feature workflows — code obfuscation and protection in F8Framework.
Find the perfect capability for your agent.
Use when implementing or troubleshooting Obfuz feature workflows — code obfuscation and protection in F8Framework.
Use when executing builds, generating update packages, or verifying build artifacts with F5 build tool in F8Framework.
Use when working with ComponentBind editor tools — auto-generating component reference code from UI hierarchies in F8Framework.
Use when working with AssetManager editor tools — F8 shortcut, AB name management, asset index generation, and asset status inspector in F8Framework.
Use when working with GameObjectPool editor tools — preload pool Inspector, PoolsPreset ScriptableObject creation in F8Framework.
Use when working with PlayModePlus editor tools — editor play mode enhancements and development convenience features in F8Framework.
Use when working with UI editor tools — sprite slicing, atlas tools, safe area setup, BaseView template creation, and UI utility components in F8Framework.
Search and install skills from skills.sh and GitHub repos. Use when users ask to find skills, install skills, download skills, add skills from GitHub, search for skills, browse skills, get a skill, or want new capabilities. Trigger phrases include "install skill", "find skill", "search skills", "add skill", "download skill", "get skill from github", "skills.sh", "browse skills", "what skills are available", "I need a skill for".
Add a Hugging Face dataset to Marin pipelines. Use when asked to add, register, or inspect a new dataset for training.
Start, monitor, and babysit Zephyr pipeline jobs on Iris. Use when launching a zephyr job, watching it run, or restarting after failures.
Fix a bug using test-driven development. Analyze the problem, write a failing test first, fix the code, validate, then commit. Use for in-branch bug fixes where the issue is already understood. For bugs originating from a GitHub issue, prefer fix-issue instead.
Monitor/babysit a job continuously and recover on failure. Use when asked to babysit, monitor, or watch a job, pipeline, workflow, or training run.
Scheduled scrub workflow for maintaining newcomer-friendly TL;DR blocks on experiment issues.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
智能提示词生成器 v2.0 - 支持人像/跨domain/设计三种模式,语义理解、常识推理、一致性检查
Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.