Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
46.092 de skill-uri din 2.198 de depozite · actualizat acum 17 minute
9.543 de skill-uri
- content-enrichchubbyguan/chubbyskills内容加工：给任意采集产物（转录稿 / 文章 / 笔记）自动补「摘要 + 要点 + 标签 + 价值判断」， 写进 frontmatter 并在正文顶部插入摘要块。是「加工层」通用能力，惠及仓库所有采集 skill。AlteleFără avertismente★ 1,3 K↓ —
- x-ingestchubbyguan/chubbyskillsX(Twitter) 推文采集 → 统一 frontmatter Markdown。自动区分图文与视频： 图文下载图片本地嵌入，视频提取直链转成文字稿。无需登录（走官方嵌入端点）。AlteleFără avertismente★ 1,3 K↓ —
- swarmdsebban/skillsFan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.AlteleFără avertismente★ 69↓ —
- zhihu-transcribechubbyguan/chubbyskills知乎视频 → 下载 → 转录 → 存为 Markdown。 支持知乎视频链接、问答内嵌视频和专栏文章，无需登录。AlteleFără avertismente★ 1,3 K↓ —
- using-syncJanYork/llm-wiki-cliUse when an Agent needs to synchronize LWC Wiki stores across SSH hosts, resume or abort an interrupted Sync session, or resolve semantic Sync conflicts safely.AlteleFără avertismente★ 68↓ —Apare și în 3 alte depozite
- capacitor-plugin-upgrade-v7-to-v8Cap-go/capgo-skillsUpgrades a Capacitor plugin library from v7 to v8 using `npx @capacitor/plugin-migration-v7-to-v8@latest`, then the manual checklist - dev deps `^8.0.0` and peer `@capacitor/core` `>=8.0.0`, minSdk 24 and compile/target SDK 36 defaults, AndroidX dependency defaults, AGP 8.13.0, Gradle 8.14.3, Gradle `=` property assignment syntax, Java 21, Kotlin 2.2.20 (`kotlinOptions` to `compilerOptions`, no `kotlin-android-extensions`), google-services 4.4.4, iOS 15 in podspec and `Package.swift`, `capacitor-swift-pm` `from: "8.0.0"`, and the renamed `capacitor_bridge_layout_main` resource. Use when a plugin targets Capacitor 7 and must support 8, or on Kotlin 2 / Gradle space-assignment errors. Points to the v8-to-v9 next step. Do not use for app upgrades, other major versions, or non-Capacitor libraries.AlteleFără avertismente★ 73↓ —Apare și în 1 alt depozit
- using-bookJanYork/llm-wiki-cliUse to import, prepare, read, or synthesize a complete supported book in verified source order. Skip ordinary document lookup.AlteleFără avertismente★ 68↓ —Apare și în 3 alte depozite
- simpo-trainingKalarisLabs/research-agent-skillsSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.AlteleFără avertismente★ 76↓ —
- youtube-transcribechubbyguan/chubbyskillsYouTube 视频 → 下载 → 转录 → 翻译 → 存为 Markdown。 支持中英文，英文内容自动翻译成中文，输出中英对照。AlteleFără avertismente★ 1,3 K↓ —
- xiaohongshu-ingestchubbyguan/chubbyskills小红书笔记采集 → 统一 frontmatter Markdown → 爆款拆解 + 衍生选题。 支持笔记链接和 xhslink 短链；爆款拆解按「人群×场景×痛点×情绪×钩子」生成可复用选题。AlteleFără avertismente★ 1,3 K↓ —
- deepline-quickstartgetaero-io/gtm-eng-skillsRun a quick Deepline demo with a maintained Play.AlteleFără avertismente★ 72↓ —
- simulink-curating-library-kgmatlab/simulink-agentic-toolkitUse this skill when the user wants to curate the SATK library knowledge index for a Simulink project — mark commonly used blocks, correct auto-assigned block categories, or improve block descriptions so the model-building agent picks better blocks from custom libraries. Triggered by phrases like "mark blocks common", "improve block descriptions", "correct block category", "make the agent prefer certain blocks", and from Gate 3 of building-simulink-models.AlteleFără avertismente★ 1,3 K↓ —
- niche-signal-discoverygetaero-io/gtm-eng-skillsDeprecated alias. This skill was renamed to `deepline-scoring`. Use when a user or script still invokes `/niche-signal-discovery`: immediately load and follow the `deepline-scoring` skill instead. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals.AlteleFără avertismente★ 72↓ —
- Blumira MSPWYRE-AI/msp-claude-pluginsBlumira's MSP path group (`/msp/*`): managed-account enumeration, cross-account and per-account finding queries, per-account device, agent-key and user management, and how MSP paths differ from org paths.AlteleFără avertismente★ 52↓ —
- btp-abap-environmentlikweitan/abap-skillsHelp with SAP BTP ABAP Environment setup and development including service instance creation, ADT connectivity, communication arrangements, communication scenarios, inbound/outbound services, destination configuration, identity and access management, software components, and first-project scaffolding. Use when users ask about BTP ABAP Environment, SAP BTP ABAP, Steampunk, ABAP environment service instance, ADT connection to BTP, communication arrangement, communication scenario, communication system, outbound communication, inbound communication, destination service, software component, ABAP system on BTP, or cloud ABAP development setup. Triggers include "set up BTP ABAP", "connect ADT to BTP", "communication arrangement", "communication scenario", "create service instance", "ABAP on BTP", "outbound service", or "first ABAP project on BTP".AlteleFără avertismente★ 72↓ —
- model-pruningKalarisLabs/research-agent-skillsReduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.AlteleFără avertismente★ 76↓ —
- praise-before-worklovstudio/skills落实用户“每次帮我肝活之前先夸夸我”的个人协作偏好。新任务开工前，先明确、具体地赞美用户，再开展工作。显式调用本 Skill 时，即使用户只说“你好”也要给出能明显感受到的夸奖；普通进度更新不重复。AlteleFără avertismente★ 73↓ —
- simulating-simulink-modelsmatlab/simulink-agentic-toolkitConfigures Simulink simulations non-destructively using SimulationInput objects — parameter overrides without modifying the model, batch sweeps via parsim, custom input signals via Dataset, and simulation data retrieval via logsout. Use when running sim()/parsim() with setVariable, setBlockParameter, setExternalInput, or when performing parameter sweeps and multi-run analysis. Not needed for one-shot simulations without configuration.AlteleFără avertismente★ 1,3 K↓ —
- build-tamgetaero-io/gtm-eng-skillsBuild a Total Addressable Market list: size the audience, source companies from ICP filters, then find contacts at those companies at scale.AlteleFără avertismente★ 72↓ —
- configuring-block-policymatlab/simulink-agentic-toolkitGuide users through creating and managing .satk/block-policy.json for controlling which blocks the agent can use, which are excluded, and which block parameters the agent should not modify. Use when setting up block usage policy for a project.AlteleFără avertismente★ 1,3 K↓ —
- lov-media-selectionlovstudio/skills比较媒体候选的剪辑版本、画质、编码、体积、音轨、字幕、活跃度与证据，自动选出最合适版本；适用于“哪个版本最值得下”、"choose the best compact release"。AlteleFără avertismente★ 73↓ —
- simulink-frequency-responsematlab/simulink-agentic-toolkitEstimate frequency response from Simulink models using frestimate. Use when frequency response should be obtained from simulation rather than model linearization.AlteleFără avertismente★ 1,3 K↓ —
- simulink-linearizematlab/simulink-agentic-toolkitLinearize Simulink models. Use when obtaining linear time invariant or linear parameter varying models from Simulink models.AlteleFără avertismente★ 1,3 K↓ —
- faissKalarisLabs/research-agent-skillsFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.AlteleFără avertismente★ 76↓ —
agent-lightning
coco-research/coco
AlteleActualizat acum 12 ore
De la autor
Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore, implementing reward functions, or optimizing prompts with RL/APO algorithms.
Instalare
npx skills add coco-research/coco --skill agent-lightning -a claude-code
Se instalează în .claude/skills/agent-lightning/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Fără descărcare: licența acestui skill (Personalizată sau neclară) nu ne permite să-i redistribuim fișierele. Comenzile de instalare le iau direct de pe GitHub.
La ce are acces
Doar instrucțiuniFolosește rețeauaLicență: Personalizată sau neclară
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 82
Securitate100
Proveniență75
Întreținere100
Licență45
Adopție47
Fișiere (2)
- SKILL.md
- reference.md