Намерете инструкция, прочетете оригиналния файл и подгответе команда за своя инструмент.
31 301 skills в каталога
Как подбирам и измервамДанните имат нужда от нова проверка.Последна успешна проверка: 23.09.2026 г.
Проверката на източника не означава, че всяка инструкция е изпробвана от Level8. Каталогът не обхваща непременно всички публични хранилища.
Търсене в целия индекс. Метаданните показват посоченото от източника; липсващите стойности остават означени.
Датата в GitHub е отделна от първата поява в моя индекс. Филтърът по дата изключва записите без посочено обновяване.
Страница 35: 24 записа в 6 групи по репозиторий. Всички записи от страницата са показани. Номерът пази позицията от избраната подредба.
8 skills от този източник на тази страница
Operate Claude Code CLI (v2.1+) via the terminal only when the user explicitly requests Claude Code or names this skill. Covers print mode (-p), interactive tmux sessions, and background (--bg) orchestration.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when you have a spec or requirements for a multi-step task, before touching code
Deep research on any topic using parallel sub-agents and built-in tools only (WebSearch/WebFetch + free APIs, no keys). Use when the user asks for a thorough multi-source investigation with a cited report — "深度调研X"、"deep research"、"帮我全面研究一下"、"多方求证"、"写一份调研报告". NOT for simple lookups (single WebSearch suffices) and NOT for academic literature surveys (use auto-research skill instead).
Use when you want to modify ANY aspect of yourself — your capabilities (new/overridden tools), your behavior (hooks that intercept every tool call, LLM request, session and subagent lifecycle), your knowledge (skills that persist across sessions), your orchestration (workflow scripts), or even your UI (TUI panels, commands, dialogs). Nothing about you is fixed: every layer from what tools you expose, to how you react to events, to what the user sees on screen is rewritable through files in .mimo
Use whenever the user asks about MiMoCode itself: features, TUI or CLI commands, keybindings, terminal compatibility, rendering glitches, TUI lag, SSH or remote rendering, agent modes (build / plan / compose) and how to switch between them, configuration, file locations, providers, models, authentication, or custom OpenAI-compatible or Anthropic-compatible API endpoints. Especially trigger when a prompt supplies or asks to configure a base URL/baseURL, API key/apiKey, model name or ID, provider,
Autonomous research skill for open-ended, high-volume research work — an agent left running for a while (minutes to overnight) that produces honest, comparable, auditable evidence instead of a single one-shot answer. Covers eight modes selected by the request: (1) experiment loop — iteratively edit code, run, measure a metric, keep or revert (baseline → hypothesize → run → keep/revert loop; use for "optimize X", "tune hyperparameters", "run experiments overnight", "autonomously improve this mode
Recreate an authorized live website or app URL as a faithful, runnable, frontend-only local implementation.
3 skills от този източник на тази страница
Strict JSON:API v1.1 specification compliance. Trigger: When creating or modifying API endpoints, reviewing API responses, or validating JSON:API compliance.
Main entry point for Prowler development - quick reference for all components. Trigger: General Prowler development questions, project overview, component navigation (NOT PR CI gates or GitHub Actions workflows).
Zustand 5 state management patterns. Trigger: When implementing client-side state with Zustand (stores, selectors, persist middleware, slices).
9 skills от този източник на тази страница
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experimen
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
1 skill от този източник на тази страница
把用户提供的素材（网页 URL / PDF / DOCX / Markdown / 纯文本 / 截图 / 粘贴材料）编辑、设计成一篇美丽的、可离线打开和分享的**单文件 HTML 网页文章**。基于 reacticle 组件协议：不手写裸 HTML/CSS，而用语义组件 + 受主题约束的 Raw 自由层；按 source→规划→双确认→生成→终审→修复的小型 harness 流程推进，默认 100% 信息保留的长文。触发场景：把 URL/PDF/DOCX/文章做成网页文章 / 长文 / briefing / 解释文 / 视觉文章 / 教程 / 审阅复盘 / 方案分析，'render this as a beautiful web article / 把这篇做成网页文章 / 生成一篇可分享的 HTML 长文 / reacticle 文章'。只生成文章，不生成后台、表单、dashboard、产品原型或通用 Web App。
2 skills от този източник на тази страница
评估和处理 OpenCreator GitHub PR，先审查实际功能与风险，对不能合入的 PR 用英文反馈，并将满足门禁的 PR 合并到 develop。用于查看、评审或处理 https://github.com/krillinai/OpenCreator/pulls；不用于合并 master 或发布。
验证 OpenCreator develop 分支的增量功能、共享集成和进入 master 前的源码门禁。用于“验证 develop”“检查合并后功能”“确认能否进 master”等请求；普通局部开发修改和实际 Desktop 打包发布不使用。
1 skill от този източник на тази страница
Use this skill when the user sends a slash command or asks to run a MoviePilot system or plugin command in natural language. Discover the live command catalog, resolve the exact command, and dispatch it through the structured API gateway.
Пазя съществуващия каталог и добавям намерени SKILL.md файлове след прочит на метаданните. Наличният индекс остава използваем, когато проверката е частична.
Платформата и нивото описват записаното в източника. Те не са гаранция за съвместимост. Български текст се показва само когато в каталога има отделен превод; иначе виждате оригинала с означен език.
Общите звезди показват натрупана популярност. За „Набират интерес“ се сравнява измереният темп при достатъчен интервал. ≥ означава непълна извадка. Под един час не изчислявам дневен темп; методът и изминалият период се показват до записа.
Проверете файла, лиценза и нужния достъп преди употреба. Нито каталогът, нито четенето на SKILL.md изпълняват външни инструкции.
Темата Agent Skills в GitHub