Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
29,232
总 Skills
220.2M
总安装量
2,808
贡献者
# Skill 仓库 描述 安装量
1701 writing-unit-tests riekelt/principal-engineer
Writing unit tests REQUIRED BACKGROUND: the principal-engineering skill. testing-changes governs which tests a change owes; this skill is the craft of the tests themselves. Overview A unit test is a behavioral claim with a name, read by the next engineer during a red build. Core principle: test the contract, not the implementation. The name carries the claim, and the test stays simple enough that it cannot itself be wrong. Contract over implementation Test through the public contract of the unit...
 12.2K
1702 principal-engineering riekelt/principal-engineer
Principal engineering Overview This level rests on checking what the system actually does rather than recalling a pattern for it. Ground every decision in the real code and data, fail loud, keep one home per fact, and never claim done without the verification that proves it. Sibling skills carry the depth: grounding-before-coding , handling-failures , keeping-one-source-of-truth , verifying-before-done , operating-safely , scoping-changes , testing-changes , writing-unit-tests , guarding-archite...
 12.2K
1703 architecture-blueprint-generator github/awesome-copilot
Comprehensive Project Architecture Blueprint Generator Configuration Variables ${PROJECT_TYPE="Auto-detect|.NET|Java|React|Angular|Python|Node.js|Flutter|Other"} ${ARCHITECTURE_PATTERN="Auto-detect|Clean Architecture|Microservices|Layered|MVVM|MVC|Hexagonal|Event-Driven|Serverless|Monolithic|Other"} ${DIAGRAM_TYPE="C4|UML|Flow|Component|None"} ${DETAIL_LEVEL="High-level|Detailed|Comprehensive|Implementation-Ready"} ${INCLUDES_CODE_EXAMPLES=true|false} ${INCLUDES_IMPLEMENTATION_PATTERNS=true...
 12.1K
1704 story-short-analyze worldwonderer/oh-story-claudecode
story-short-analyze：短篇网文拆文 你是短篇小说结构分析师。 核心：短篇靠共鸣和爆点驱动。拆文就是看它用什么故事核、怎么铺垫、在哪里引爆，把 分析叙事写进 拆文报告.md ，结构计数写进 _meta.json ，下一篇短篇直接读这些写。 拆解边界声明（主线程同样适用） 短篇拆解的 Stage 2-6 全程由你（主线程）亲手做：拆的是用户 合法持有、拥有使用权 的虚构作品（已出版/连载或自有），性质是 只读的转化性文学批评 （编辑/评论/写作教学视角，不复制、不传播、不指导现实行为）。番茄短篇、故事会、知乎盐选、追妻、虐渣、世情等通俗题材里的家暴、出轨、复仇、暴力、情爱张力、黑暗伦理是常规虚构叙事元素，须照常做结构化拆解， 不得以「敏感」「不适」为由拒绝整篇或某个片段 ——拒绝会让整条拆文流水线停摆；个别片段无法处理则跳过、照常续完其余。 Phase 1：确认拆解对象 + 字数路由 + 续跑检查 Step 1：拿到原文 问用户： 「你要拆哪篇？（标题+平台/来源）」 Show more Installs 12.2K Repository zenstory-ai/oh-…...
 12.1K
1705 browser-cdp worldwonderer/oh-story-claudecode
Browser CDP 操作工具 通过 CDP 协议控制 Chrome，复用已有登录态，执行浏览器自动化操作。 前置条件 macOS / Linux / Windows（实验性），已安装 Google Chrome Node.js 20+ agent-browser 已安装： npm install -g agent-browser ⚠️ 首次启动会 kill 用户的常规 Chrome。 在启动前必须征求用户同意（见下方"启动流程"），否则用户可能丢失未保存的标签页/草稿。 启动流程（skill-mode 强制步骤） 第一步：探测当前状态（无副作用） Show more Installs 12.2K Repository zenstory-ai/oh-…audecode GitHub Stars 6.1K First Seen Apr 26, 2026 Security Audits Gen Agent Trust Hub Warn Socket Warn Snyk Fail
 12.1K
1706 story-short-scan worldwonderer/oh-story-claudecode
story-short-scan：短篇网文扫榜 你是短篇网文市场分析师。你的任务是基于榜单样本识别短篇市场格局，并输出可执行的情绪方向、题材候选、风险阈值和验证动作。 核心信念：短篇市场变化快，题材信号有效期短。 扫榜报告必须标注样本日期、趋势可信度和下次重新扫榜的时间。 核心哲学 原则 1：短篇市场是情绪市场 短篇网文的核心是情绪交付。读者在短时间内完成一次情绪体验；扫榜要提取高频情绪、触发场景、情绪爆发点和读者愿意转发的点，而不是只记录题材名。 原则 2：短篇的生命力在传播 短篇不像长篇靠追读赚钱。短篇靠的是单篇完读率和传播（分享、收藏、点赞）。完读率高 = 情绪拉扯到位；传播率高 = 有共鸣或反转让人想转发。 原则 3：短篇风口来得快去得快 Show more Installs 12.2K Repository zenstory-ai/oh-…audecode GitHub Stars 6.1K First Seen Apr 24, 2026 Security Audits Gen Agent Trust Hub Pass Socket Warn Snyk Warn
 12.1K
1707 cloudbase tencentcloudbase/cloudbase-skills
CloudBase Development Guidelines 📁 Reference Files Location All reference documentation files are located in the references/ directory relative to this file. File Structure: cloudbase/ ├── SKILL.md This file (main entry) └── references/ All reference documentation ├── auth-web/ Web authentication guide ├── auth-wechat/ WeChat authentication guide ├── no-sql-web-sdk/ NoSQL database for Web ├── ui-design/ UI design guidelines └── ... ...
 12.1K
1708 llm-evaluation wshobson/agents
LLM Evaluation Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing. When to Use This Skill Measuring LLM application performance systematically Comparing different models or prompts Detecting performance regressions before deployment Validating improvements from prompt changes Building confidence in production systems Establishing baselines and tracking progress over time Debugging unexpected model behavior Core Evaluation T...
 12.1K
1709 frontend-slides affaan-m/ecc
Frontend Slides Create zero-dependency, animation-rich HTML presentations that run entirely in the browser. Inspired by the visual exploration approach showcased in work by zarazhangrui (credit: @zarazhangrui). When to Activate Creating a talk deck, pitch deck, workshop deck, or internal presentation Converting .ppt or .pptx slides into an HTML presentation Improving an existing HTML presentation's layout, motion, or typography Exploring presentation styles with a user who does not know their de...
 12.1K
1710 python-patterns affaan-m/ecc
Python Development Patterns Idiomatic Python patterns and best practices for building robust, efficient, and maintainable applications. When to Activate Writing new Python code Reviewing Python code Refactoring existing Python code Designing Python packages/modules Core Principles 1. Readability Counts Python prioritizes readability. Code should be obvious and easy to understand. Show more Installs 1.8K Repository affaan-m/ecc GitHub Stars 239.2K First Seen May 19, 2026 Security Audits Gen Agent...
 12.1K
1711 tanstack-query-best-practices deckardger/tanstack-agent-skills
TanStack Query Best Practices Comprehensive guidelines for implementing TanStack Query (React Query) patterns in React applications. These rules optimize data fetching, caching, mutations, and server state synchronization. When to Apply Creating new data fetching logic Setting up query configurations Implementing mutations and optimistic updates Configuring caching strategies Integrating with SSR/SSG Refactoring existing data fetching code Rule Categories by Priority Priority Category Rules Im...
 12.1K
1712 alloydb-basics google/skills
AlloyDB Basics AlloyDB for PostgreSQL is a managed, PostgreSQL-compatible database service designed for enterprise-grade performance and availability. It utilizes a disaggregated compute and storage architecture to scale resources independently. It also provides AlloyDB AI, a collection of features that includes AI-powered search (vector, hybrid search, and AI functions), natural language capabilities, conversational analytics, and inference features like forecasting and model endpoint managemen...
 12.1K
1713 expo-design-system expo/skills
Expo Design Systems Make every screen in an app draw from one visual source of truth: a token theme and a small set of reusable components. This skill defines where tokens live, what they cover, how reusable components are shaped, and when a repeated view earns promotion into the system. Sibling skills own the layers around this one: expo-native-ui - platform styling rules (HIG, semantic colors, controls, shadows syntax). Follow it for what values look native ; follow this skill for where values...
 12.1K
1714 nature-reviewer yuan1z0825/nature-skills
Nature Reviewer Assessment Skill Use this skill to simulate a Nature -style reviewer assessment package from the referee side. This skill is for reviewer-style manuscript evaluation, not for drafting the authors' response. If the user wants rebuttal writing, route to nature-response . Default stance Ground the review only in the local source basis plus manuscript facts supplied by the user. Evaluate the manuscript against source-grounded axes: originality , scientific importance , interdisciplin...
 12.1K
1715 documenting-legacy-codebases riekelt/technical-writer
Documenting legacy codebases REQUIRED BACKGROUND: the technical-writing skill (hard rules, kind classification, truth rules, style). Overview A legacy codebase has one reliable witness: the code at HEAD. Everything else that speaks about it (names, comments, old documents, diagrams, the memory of whoever is left) is testimony. Core principle: describe how the system works and what to look out for, verified against the code; the code stays the authority on how it is implemented. The deliverable i...
 12.1K
1716 verifying-before-done riekelt/principal-engineer
Verifying before done REQUIRED BACKGROUND: the principal-engineering skill. Overview Done means verified, and verified names what was checked. Careful work is not a check: the defects that ship in "obviously fine" changes are the ones caught by the verification that almost got skipped, because "obviously fine" is the feeling that skips it. The discipline Drive the change at its surface, capture what it did. Run the smallest path that executes the changed code in the running system; "Verify at th...
 12.1K
1717 guarding-architecture riekelt/principal-engineer
Guarding architecture REQUIRED BACKGROUND: the principal-engineering skill. Overview Structural invariants are load-bearing contracts: violating one surfaces as a class of bugs, not a single defect. Core principle: an invariant that matters gets a name, a written rationale, and a mechanical guard; an invariant without a guard is a wish. The pattern Name the invariants. Numbered and citable ("Law 3"), each with a Statement (technology-neutral, meant to outlast any framework), a Rationale, and Imp...
 12.1K
1718 grounding-before-coding riekelt/principal-engineer
Grounding before coding REQUIRED BACKGROUND: the principal-engineering skill. Overview Before writing a spec, a fix, or a first line: map the real code and data. Quote file:line and run the query behind every number you rely on. The cost of grounding is minutes; the cost of building on a wrong belief is the whole change plus the incident it causes. The discipline Read the implementations, not the names. A method called validate that does not validate is common enough to be the default assumption...
 12.1K
1719 testing-changes riekelt/principal-engineer
Testing changes REQUIRED BACKGROUND: the principal-engineering skill. The craft of the tests themselves lives in writing-unit-tests ; this skill governs which tests a change owes. Overview A test is the executable form of a claim about behavior. A change that alters behavior without touching tests is a claim nobody wrote down. Two failure modes follow: the green suite over code that could not work, and the test or gate that turned out never to run. Tests a change owes Tests change with behavior,...
 12.1K
1720 keeping-one-source-of-truth riekelt/principal-engineer
Keeping one source of truth REQUIRED BACKGROUND: the principal-engineering skill. Overview Every fact about the system lives in exactly one place, and every other part of the system reads it from there. This outranks convenience: a second copy is a future contradiction, and the copy that drifts is always the one nobody remembers exists. When two places can hold the same truth they will eventually disagree, and the system then looks healthy while serving wrong data. The doctrine Before adding dat...
 12.1K
1721 scoping-changes riekelt/principal-engineer
Scoping changes REQUIRED BACKGROUND: the principal-engineering skill. Overview Scope fails in both directions: gold-plating grows a fix past its trigger, and silent descoping shrinks an approved task below what was agreed. Both are the same defect: the delivered change no longer matches its cause. Core principle: size fixes to their trigger, and when reality forces a cut, decompose visibly instead of trimming quietly. Sizing to the trigger The trigger is the defect or need itself, not the ticket...
 12.1K
1722 operating-safely riekelt/principal-engineer
Operating safely REQUIRED BACKGROUND: the principal-engineering skill. Overview Operational damage is asymmetric: the command takes a second, the recovery takes the weekend, and some things (production data, secret exposure, a colleague's uncommitted work) do not come back at all. Destructive operations Look at the target first. Before deleting or overwriting, read what is there; before dropping, count what would drop. Targeted over bulk. Name the specific service, volume, file, or row set; neve...
 12.1K
1723 handling-failures riekelt/principal-engineer
Handling failures REQUIRED BACKGROUND: the principal-engineering skill. Overview A swallowed error is a bug with its evidence destroyed. Core contract: every failure path does exactly one of three things, and all three are loud. The system that looks healthy while serving wrong data is worse than the one that crashes, because the crash gets fixed today and the silent wrong output gets discovered in an audit. The contract Every catch and failure path either: Logs at WARN or ERROR and rethrows , o...
 12.1K
1724 adding-dependencies riekelt/principal-engineer
Adding dependencies REQUIRED BACKGROUND: the principal-engineering skill. Overview A dependency is a hire, not a snippet: with the feature come its defects, its release rhythm, its transitive tree, and its maintainer's attention span. Core principle: exhaust what you already have, vet what you take, pin what you took, and record why. Exhaust what you already have Work down the list and stop at the first level that holds; good answers often compose two levels, an existing dependency for the hard ...
 12.1K
1725 typescript-mcp-server-generator github/awesome-copilot
Generate TypeScript MCP Server Create a complete Model Context Protocol (MCP) server in TypeScript with the following specifications: Requirements Project Structure : Create a new TypeScript/Node.js project with proper directory structure NPM Packages : Include @modelcontextprotocol/sdk, zod@3, and either express (for HTTP) or stdio support TypeScript Configuration : Proper tsconfig.json with ES modules support Server Type : Choose between HTTP (with Streamable HTTP transport) or stdio-based ser...
 12K
1726 python-type-safety wshobson/agents
Python Type Safety Leverage Python's type system to catch errors at static analysis time. Type annotations serve as enforced documentation that tooling validates automatically. When to Use This Skill Adding type hints to existing code Creating generic, reusable classes Defining structural interfaces with protocols Configuring mypy or pyright for strict checking Understanding type narrowing and guards Building type-safe APIs and libraries Core Concepts 1. Type Annotations Declare expected types f...
 12K
1727 expo-module expo/skills
Writing Expo Modules Complete reference for building native modules and views using the Expo Modules API. Covers Swift (iOS), Kotlin (Android), and TypeScript. When to Use Creating a new Expo native module or native view Adding native functionality (camera, sensors, system APIs) to an Expo app Wrapping platform SDKs for React Native consumption Building config plugins that modify native project files References Consult these resources as needed: references/ native-module.md Module defi...
 12K
1728 clean-code sickn33/agentic-awesome-skills
Clean Code Skill This skill embodies the principles of "Clean Code" by Robert C. Martin (Uncle Bob). Use it to transform "code that works" into "code that is clean." 🧠 Core Philosophy "Code is clean if it can be read, and enhanced by a developer other than its original author." — Grady Booch When to Use Use this skill when: Writing new code : To ensure high quality from the start. Reviewing Pull Requests : To provide constructive, principle-based feedback. Refactoring legacy code : To identify a...
 12K
1729 tavily-dynamic-search tavily-ai/skills
Tavily Dynamic Search Search the web, filter results, and extract content so that raw search data never enters your context window . Only your curated print() output comes back. Why this matters A typical tvly search --include-raw-content returns 8 results × 30-50K chars each = ~300K characters of raw page content. If this enters your context window, you burn tokens reading navigation bars, cookie banners, and boilerplate — and your reasoning quality degrades under the noise. By processing resul...
 12K
1730 wcag-audit-patterns wshobson/agents
WCAG Audit Patterns Comprehensive guide to auditing web content against WCAG 2.2 guidelines with actionable remediation strategies. When to Use This Skill Conducting accessibility audits Fixing WCAG violations Implementing accessible components Preparing for accessibility lawsuits Meeting ADA/Section 508 requirements Achieving VPAT compliance Core Concepts 1. WCAG Conformance Levels Level Description Required For A Minimum accessibility Legal baseline AA Standard conformance Most regulations AAA...
 12K
1731 startup-financial-modeling wshobson/agents
Startup Financial Modeling Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups. Overview Financial modeling provides the quantitative foundation for startup strategy, fundraising, and operational planning. Create realistic projections using cohort-based revenue modeling, detailed cost structures, and scenario analysis to support decision-making and investor presentations. Core Components Reven...
 12K
1732 diagramming-processes riekelt/technical-writer
Diagramming processes REQUIRED BACKGROUND: the technical-writing skill (hard rules, truth rules, style). Overview A diagram is a set of claims drawn instead of written, and every box and arrow is bound by the same truth rules as a sentence. Core principle: diagram the behavior (processes, lifecycles, interactions), keep the source in version control, and treat every render as derived. The prose owns the reasoning; the diagram carries the structure that prose serializes badly, which is branching,...
 12K
1733 search tavily-ai/skills
Search Skill Search the web and get relevant results optimized for LLM consumption. Authentication The script uses OAuth via the Tavily MCP server. No manual setup required - on first run, it will: Check for existing tokens in ~/.mcp-auth/ If none found, automatically open your browser for OAuth authentication Note: You must have an existing Tavily account. The OAuth flow only supports login — account creation is not available through this flow. Sign up at tavily.com first if you don't have an a...
 11.9K
1734 protocol-reverse-engineering wshobson/agents
Protocol Reverse Engineering Comprehensive techniques for capturing, analyzing, and documenting network protocols for security research, interoperability, and debugging. Traffic Capture Wireshark Capture Capture on specific interface wireshark -i eth0 -k Capture with filter wireshark -i eth0 -k -f "port 443" Capture to file tshark -i eth0 -w capture.pcap Ring buffer capture (rotate files) tshark -i eth0 -b filesize:100000 -b files:10 -w capture.pcap tcpdump Capture Basic capture tcpdu...
 11.9K
1735 code-refactoring supercent-io/skills-template
Code Refactoring When to use this skill Code review : Discovering complex or duplicated code Before adding new features : Cleaning up existing code After bug fixes : Removing root causes Resolving technical debt : Regular refactoring Instructions Step 1: Extract Method Before (long function) : function processOrder ( order : Order ) { // Validation if ( ! order . items || order . items . length === 0 ) { throw new Error ( 'Order must have items' ) ; } if ( ! order . customerId ) { throw new Erro...
 11.9K
1736 grimoire-polymarket franalgaba/grimoire
Grimoire Polymarket Skill Use this skill for Polymarket market discovery, CLOB market data, and order-management operations through the polymarket venue adapter. Preferred invocations: grimoire venue polymarket ... npx -y @grimoirelabs/cli venue polymarket ... (no-install) bun run packages/cli/src/index.ts venue polymarket ... (repo-local) grimoire-polymarket ... (direct binary from @grimoirelabs/venues ) Recommended preflight: grimoire venue doctor --adapter polymarket --json grimoire venue pol...
 11.9K
1737 seedance2-api hexiaochun/seedance2-api
Seedance 2.0 Storyboard & Video Generation End-to-end workflow from concept to final video: Storyboard → Reference images → Submit video task → Get results. Step 0: Determine Execution Mode (MCP or Script) Check MCP availability first: Check xskill-ai MCP service status (read mcps/user-xskill-ai/STATUS.md ) If MCP is available → use submit_task / get_task and other MCP tools If MCP is unavailable or returns errors → switch to Script Mode Script mode prerequisites: Verify XSKILL_API_KEY environme...
 11.9K
1738 stock-analysis gracefullight/stock-checker
Stock Analysis (v5.0) Analyze US stocks and cryptocurrencies using Yahoo Finance data. Includes portfolio management, crypto support, and periodic analysis. Quick Start IMPORTANT: Pass ONLY the stock ticker symbol(s) as arguments. Do NOT add extra text, headers, or formatting in the command. Analyze a single ticker: uv run { baseDir } /scripts/analyze_stock.py AAPL uv run { baseDir } /scripts/analyze_stock.py MSFT --output json Compare multiple tickers: uv run { baseDir } /scripts/analyze_stock....
 11.9K
1739 api-design affaan-m/ecc
API Design Patterns Conventions and best practices for designing consistent, developer-friendly REST APIs. When to Activate Designing new API endpoints Reviewing existing API contracts Adding pagination, filtering, or sorting Implementing error handling for APIs Planning API versioning strategy Building public or partner-facing APIs Resource Design URL Structure Show more Installs 3.9K Repository affaan-m/ecc GitHub Stars 265.4K First Seen May 19, 2026 Security Audits Gen Agent Trust Hub Pass So...
 11.9K
1740 django-patterns affaan-m/ecc
Django Development Patterns Production-grade Django architecture patterns for scalable, maintainable applications. When to Activate Building Django web applications Designing Django REST Framework APIs Working with Django ORM and models Setting up Django project structure Implementing caching, signals, middleware Project Structure Recommended Layout Show more Installs 1.6K Repository affaan-m/ecc GitHub Stars 239.2K First Seen May 19, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Sny...
 11.9K
1741 clickhouse-best-practices clickhouse/agent-skills
ClickHouse Best Practices Comprehensive guidance for ClickHouse covering schema design, query optimization, and data ingestion. Contains 28 rules across 3 main categories (schema, query, insert), prioritized by impact. Official docs: ClickHouse Best Practices IMPORTANT: How to Apply This Skill Before answering ClickHouse questions, follow this priority order: Check for applicable rules in the rules/ directory If rules exist: Apply them and cite them in your response using "Per rule-name ..." If ...
 11.9K
1742 byted-mediakit-audio volcengine/mediakit-cli
audio MediaKit Skill 使用规则 先读取 ../byted-mediakit-shared/SKILL.md ，执行统一前置检查；该 Skill 缺失时停止并提示安装。 只从下表选择 audio 域工具；相似能力按各工具“能力描述”和参数边界区分。 执行前按需读取对应 reference；参数与结果说明来自同一份已审核文案，完整机器合同以当前 CLI --schema 为准。 缺少必填参数、鉴权环境变量或真实输入资源时，向用户索取；通用可选字段只能透传用户明确提供的值，其他可选字段可由明确意图准确确定，但不得伪造。 执行时设置 MEDIAKIT_SURFACE=skill ，指定调用来源是 Skill。 执行时把 MEDIAKIT_RUNTIME 设置为当前 Agent 宿主，避免 CLI 无法可靠识别父级 Agent。 澄清与跨域路由 若只说有音频而未说明业务目标，应先澄清。音频裁剪、拼接、调速、淡入淡出、混音、从视频抽取音轨或音视频合流等编辑合成诉求应路由到 editing；字幕生成、提取字幕、语音转字幕、视频理解、视频增强等应路由到 video。 工具列表 Sh...
 11.9K
1743 byted-mediakit-video volcengine/mediakit-cli
video MediaKit Skill 使用规则 先读取 ../byted-mediakit-shared/SKILL.md ，执行统一前置检查；该 Skill 缺失时停止并提示安装。 只从下表选择 video 域工具；相似能力按各工具“能力描述”和参数边界区分。 执行前按需读取对应 reference；参数与结果说明来自同一份已审核文案，完整机器合同以当前 CLI --schema 为准。 缺少必填参数、鉴权环境变量或真实输入资源时，向用户索取；通用可选字段只能透传用户明确提供的值，其他可选字段可由明确意图准确确定，但不得伪造。 执行时设置 MEDIAKIT_SURFACE=skill ，指定调用来源是 Skill。 执行时把 MEDIAKIT_RUNTIME 设置为当前 Agent 宿主，避免 CLI 无法可靠识别父级 Agent。 澄清与跨域路由 若只说有视频而未说明业务目标，应先澄清。明确要把字幕或图片叠加压制到成片、或做裁剪、拼接、混音、合流、调速、转场、画面旋转翻转、视频滤镜或多视频拼画面的成片编辑诉求应路由到 editing；单张图片处理应路由到 image；音频转码、...
 11.9K
1744 byted-mediakit-image volcengine/mediakit-cli
image MediaKit Skill 使用规则 先读取 ../byted-mediakit-shared/SKILL.md ，执行统一前置检查；该 Skill 缺失时停止并提示安装。 只从下表选择 image 域工具；相似能力按各工具“能力描述”和参数边界区分。 执行前按需读取对应 reference；参数与结果说明来自同一份已审核文案，完整机器合同以当前 CLI --schema 为准。 缺少必填参数、鉴权环境变量或真实输入资源时，向用户索取；通用可选字段只能透传用户明确提供的值，其他可选字段可由明确意图准确确定，但不得伪造。 执行时设置 MEDIAKIT_SURFACE=skill ，指定调用来源是 Skill。 执行时把 MEDIAKIT_RUNTIME 设置为当前 Agent 宿主，避免 CLI 无法可靠识别父级 Agent。 图片体积治理与跨域路由 用户强调“尽量不掉画质”“质量优先”“高质量缩小体积”，且没有给出精确体积上限、质量值或格式转换要求时，先读取 reference/families/image-size-reduction.md ，优先选择 slim-ima...
 11.9K
1745 byted-mediakit-editing volcengine/mediakit-cli
editing MediaKit Skill 使用规则 先读取 ../byted-mediakit-shared/SKILL.md ，执行统一前置检查；该 Skill 缺失时停止并提示安装。 只从下表选择 editing 域工具；相似能力按各工具“能力描述”和参数边界区分。 执行前按需读取对应 reference；参数与结果说明来自同一份已审核文案，完整机器合同以当前 CLI --schema 为准。 缺少必填参数、鉴权环境变量或真实输入资源时，向用户索取；通用可选字段只能透传用户明确提供的值，其他可选字段可由明确意图准确确定，但不得伪造。 执行时设置 MEDIAKIT_SURFACE=skill ，指定调用来源是 Skill。 执行时把 MEDIAKIT_RUNTIME 设置为当前 Agent 宿主，避免 CLI 无法可靠识别父级 Agent。 澄清与跨域路由 若只给出媒体类型而未说明要剪、合、叠、调、加滤镜还是分析，应先澄清。纯图像增强、抠图、OCR、图片水印或图片尺寸优化应路由到 image；视频画质增强、内容理解、从视频提取字幕、语音转字幕、字幕擦除、暗水印、人像或绿幕抠像等视...
 11.9K
1746 byted-mediakit-shared volcengine/mediakit-cli
MediaKit 专业媒体处理入口 MediaKit 是面向音视频与图像处理的专业工具集。它将常见的媒体加工、内容理解和 智能增强能力统一到 mediakit-cli ，适合从素材处理到成片制作的完整工作流。 使用规则 通过本 Skill 或领域 Skill 实际执行 mediakit-cli 业务命令时，必须在同一次 调用中注入来源与宿主，避免 CLI 无法识别调用来源： MEDIAKIT_SURFACE=skill （本 Skill / 领域 Skill 调用固定为 skill ） MEDIAKIT_RUNTIME=<当前 Agent 宿主> （无法判断时用 unknown ） 注入方式：在命令前设置环境变量（推荐），不要把这两个值当成 CLI flag 或业务参数。 --help / --schema / --domains / --version 等只读发现命令可不注入；一旦发起 真实处理或 shared query-task ，必须注入。 示例（每次真实调用都带上）： Show more Installs 1.1K Repository volcengine/mediakit...
 11.9K
1747 hypit hypit-ai/hypit
Hypit You are the director and producer entrusted with making the video the user is asking for. Understand their request and supplied material, and develop a creative answer you can stand behind. Keep the intended result clear in Brief as the work develops; let it guide what you create, adapt and reuse. Locate this production through the supplied material and its project notes. The Skill and executable installation locate tools; project files identify the work being commissioned and the material...
 11.9K
1748 documenting-contracts riekelt/technical-writer
Documenting contracts REQUIRED BACKGROUND: the technical-writing skill (hard rules, truth rules, style). Overview A contract document is read by a stranger who cannot see the code and is about to depend on it. Core principle: document the wire, exhaustively, with each detail at its own level; the caller's language is the wire format and domain terms, never the implementation's types. Contract surfaces are reference kind, so the core Reference rule applies: every endpoint, every field, every erro...
 11.9K
1749 postgres-patterns affaan-m/ecc
PostgreSQL Patterns Quick reference for PostgreSQL best practices. For detailed guidance, use the database-reviewer agent. When to Activate Writing SQL queries or migrations Designing database schemas Troubleshooting slow queries Implementing Row Level Security Setting up connection pooling Quick Reference Index Cheat Sheet Show more Installs 1.7K Repository affaan-m/ecc GitHub Stars 239.2K First Seen May 19, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 11.8K
1750 backend-testing supercent-io/skills-template
Backend Testing When to use this skill Specific situations that should trigger this skill: New feature development : Write tests first using TDD (Test-Driven Development) Adding API endpoints : Test success and failure cases for REST APIs Bug fixes : Add tests to prevent regressions Before refactoring : Write tests that guarantee existing behavior CI/CD setup : Build automated test pipelines Input Format Format and required/optional information to collect from the user: Required information Fram...
 11.8K