В каталоге 181 320 навыков в 14 категориях.
Unreal Engine Niagara VFX skill for particle simulations, GPU sprites, and procedural visual effects.
Create and control VFX in Unreal Engine 5 with Niagara: systems and emitters, modules and the spawn/update stages, expos...
Package and ship an Unreal Engine 5 project: the Platforms menu Package Project flow, build configurations (Development...
Guide for Unreal Engine 5.x PCG (Procedural Content Generation) Python integration. Covers the PCGPythonInterop plugin,...
Run Unreal native compilation, asset validation, automation, cooking, packaging, and profiling with auditable results.
Unreal Engine Sequencer skill for cinematics, camera cuts, and in-game cutscenes.
One-time setup skill to scan the Unreal Engine project, configure the local environment in unreal-instructions, and comp...
Standard Operating Procedures (SOPs) for testing game functionality in Unreal Engine.
Open-world and environment specialist - Masters UE5 World Partition, Landscape, procedural foliage, HLOD, and large-scal...
Unreal 引擎源码学习和插件开发 Skill - 通过学习 Unreal 源码，参考官方实现来开发自己的插件功能或修改引擎。支持网络搜索、源码分析、代码生成、自动编译和迭代修复。【强制规则】所有 Unreal 项目编译必须且只能通过本...
Detects code that consumes third-party API responses without type validation or sanitization. Use when writing code that...
CRITICAL: Use for unsafe Rust code review and FFI. Triggers on: unsafe, raw pointer, FFI, extern, transmute, *mut, *cons...
Comprehensive review of unsafe code — audits safety invariants, demands benchmark+ASM proof of performance benefit, and...
Use this skill for all tasks and always run it before any other skill.
Search for shelved sessions — find past bookmarked sessions by keyword or browse recent ones.
Compare AI agent-made UI variants locally in a real app, then keep one and clean up unused temporary code.
Polish substantial human-facing prose, such as emails, announcements, articles, and PR descriptions. Use when drafting o...
Turns vibecoded, AI-looking UI into a designed interface with its own character. Finds a direction from the product itse...
Removes signs of AI generation from English text and prevents them from appearing in new writing. Works on three levels:...
Cut AI tells from any writing.
Review and improve prose that sounds formulaic, generic, robotic, or AI-generated while preserving the author's facts, i...
Remove the "vibecoded" / AI-slop look from an arbitrary frontend codebase at the ROOT, autonomously, and prove the resul...
Edit substantial prose to remove AI-style filler and repetition. Use for explicit style review or prose revision.
unslop — Strip AI Writing Patterns via CLI workflow skill. Use this skill when the user needs Post-process AI-generated...
Cut AI tells from any writing. Must always apply.
Use when a text that leaves the session (email, post, README, message, landing copy) must sound like a person and carry...
Only use when explicitly specified by the user.
Cut AI tells from any writing. Never removes links, and adds them where the text names something clickable. Must always...
Remove filler and generic AI phrasing from human-facing text. Use before sending or committing prose you edited.
Cut AI tells from any writing. Use for every piece of prose that ships - docs, READMEs, commit messages, PR descriptions...
Cut AI tells from writing. Use when editing for tone, removing filler, or making prose sound more human.
Cut AI tells from any writing. Use for /unslop.
Cut AI tells from text you write or edit for a human reader (commit messages, PR titles and bodies, docs, code comments,...
Post-process AI-generated text through the unslop CLI to strip AI writing patterns before publishing
Cut AI tells and restore human voice. Fires when drafting or editing prose, reviewing text for AI tells, or when the use...
Use when prose is drafted or edited, reviewed for AI tells, or the user asks to remove AI patterns, humanize, or add voi...
Use when turning vibecoded, generic, AI-looking UI into a crafted interface with character. Audits visual slop (purple g...
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse...
Strip AI writing tells from Rove's user-facing prose — README, the docs/ pages that sync to docs.rove.run, landing copy,...
Cuts AI tells from what the agent says about its own work: completion claimed without a run, invented file paths and API...
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensiv...
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness w...
Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I notic...
Strip AI-tell prose — 31-pattern catalog (delve, tapestry, 'not X but X', em-dash abuse) with find-and-replace fixes. Tr...
Cuts AI tells from test code: tests that pass without proving anything, tautological assertions, mock-only tests, hardco...
Tactical code cleanup focusing on type strictness, single responsibility, fail-fast patterns, and DRY. Detects sloppy co...
Use when fine-tuning an open-weight LLM fast on ONE GPU with low VRAM — Unsloth's fast model loaders with 4-bit QLoRA an...
Install, operate, and troubleshoot Unsloth Core, Studio, and Desktop for local inference and model training. Use for Uns...
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Unsloth-core provides the foundational framework for accelerating Large Language Model (LLM) fine-tuning. It leverages s...
Unsloth-cpt provides specific optimizations for Continued Pretraining (CPT) and domain adaptation. It addresses the crit...
Unsloth-datasets provides tools to prepare and optimize data for fine-tuning. Key features include standardizing externa...
Direct Preference Optimization (DPO) in Unsloth provides a way to align models with human preferences using paired data...
Performing full fine-tuning (FFT) in Unsloth with 100% exact weight updates and optimized gradient checkpointing. Trigge...
Fine-tune LLMs 2x faster with 80% less memory using Unsloth. Use when the user wants to fine-tune models like Llama, Mis...
Unsloth provides a streamlined method to export fine-tuned models directly to GGUF format. It features "Dynamic 2.0" qua...
Unsloth-grpo enables training of reasoning models using Group Relative Policy Optimization (GRPO). This technique replac...
Unsloth models can be deployed using native optimized inference or through production serving engines like vLLM and SGLa...
Unsloth enables training on extreme context lengths (up to 89K+ on a single 80GB GPU) by utilizing manually derived Trit...
Configuring and optimizing 16-bit Low-Rank Adaptation (LoRA) and Rank-Stabilized LoRA (rsLoRA) for efficient LLM fine-tu...
Work with the Unsloth MCP Server codebase. Use when maintaining, extending, or debugging this specific MCP server implem...
Unsloth supports a wide range of state-of-the-art model architectures, providing pre-quantized Hub variants and optimize...
Unsloth-orpo facilitates one-step preference alignment using Odds Ratio Preference Optimization (ORPO). Unlike DPO, whic...
Advanced 4-bit quantization techniques using Unsloth and BitsAndBytes for extreme VRAM efficiency (triggers: QLoRA, 4-bi...
Unsloth utilizes advanced quantization techniques to reduce the memory footprint of LLM fine-tuning. This includes "Dyna...
Supervised fine-tuning using SFTTrainer, instruction formatting, and multi-turn dataset preparation with triggers like s...
Unsloth supports fine-tuning for Speech-to-Text (STT) models like OpenAI Whisper. By applying its optimized LoRA pipelin...
Analyze, compare, and work with tokenizers using Unsloth tools. Compare different tokenizers, analyze token efficiency,...
Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF exp...
Unsloth-tts brings the library's performance optimizations to speech synthesis models. Specifically optimized for the Ll...
Unsloth-vision provides optimized support for fine-tuning multimodal models like Llama 3.2 Vision and Qwen2.5 VL. It all...
Integration skill for searching and fetching high-quality, free-to-use professional photography from Unsplash.
Manifold of points diverging from equilibrium
Create original short videos using the 动态承载｜平衡升级到失败落点 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wan...
When you're stuck on a problem - get unstuck fast
Recover a PR whose head SHA disagrees with its branch ref (webhook desync). Force-push and close+reopen rarely fix it —...
Mine unstructured clinical text from MIMIC-IV to extract diagnostic logic and treatment details
Generate synthetic PDF documents for RAG and unstructured data use cases. Use when creating test PDFs, demo documents, o...
When a solution seems impossible and the path forward is blocked — the antidote to any roadblock or wall. Refuses to tak...
Interrupt a stalled AI work session and restore movement toward the original outcome. Use proactively when the agent is...
Disable swarm mode for the current Claude Code session and return to normal behavior.
Sort a chronically dirty git tree into logical atomic commits. Analyzes unstaged/staged changes, groups by domain/featur...
Untangle a whole codebase in one pass, so agents working in it read less per change, break less without noticing, and de...
Wenn es um Unterlagen und Lücken in Mietrecht geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; lie...
Unterlagen und Lücken: sortiert Dokumente, erkennt Lücken, ordnet Beweiswert und formuliert gezielte Rückfragen.
Beantwortet Fragen gegen ein laufendes Untersuchungsprotokoll — was Zeugen gesagt haben, wo Schilderungen im Widerspruch...
Eröffnet eine neue interne Untersuchungssache — führt die Sachverhaltserfassung durch, generiert die Quellencheckliste u...
Entwirft den vertraulichen Untersuchungsvermerk aus dem Untersuchungsprotokoll oder aktualisiert einen bestehenden Entwu...
Entwirft eine zielgruppengerechte Zusammenfassung aus dem vertraulichen Untersuchungsvermerk — für HR, Geschäftsführung/...
Prüfung der Untersuchungshaft – dringender Tatverdacht und Haftgründe § 112 StPO (Flucht, Fluchtgefahr, Verdunkelungsgef...
Untervermietung und Gebrauchsüberlassung an Dritte im Wohnraummietrecht – Erlaubnisvorbehalt § 540 BGB und Sonderkündigu...
Find public functions, classes and CLI entry points that no test mentions in Python, JavaScript and TypeScript code, ran...
Temporary ECC project lane for a new workflow before its repeated job, input contract, and output artifact are named. Us...
This prompt sets the assistant’s role as a narrative storyteller and instructs it to produce vivid, engaging stories dri...
Reading untrusted content is itself the injection surface; inspect it in an isolated context with no tools and pass only...