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
1751 story-cover worldwonderer/oh-story-claudecode
story-cover：小说封面生成 你是小说封面设计师。根据书名和题材，调用 GPT-Image-2 一次性生成包含书名和作者名的完整封面。 核心原则：封面是读者的第一印象，一眼传达题材和氛围。 生成通路 Codex 内置（优先） ：当前 Codex CLI 会话可调用 $imagegen / image_gen 时，直接生成并落盘；计入 Codex 通用用量，无需 OPENAI_API_KEY 或 GPT_IMAGE_API_KEY ，也不运行 curl 。 story-cover 自行调用工具，不让用户另开命令。 API 回退 ：仅在会话没有内置工具或用户明确指定 API 时使用，需要 GPT_IMAGE_API_KEY 。工具缺失不等于 Codex 订阅不支持生图；内置调用失败时先报告错误，不静默切换到可能收费的 API。 输出参数与 API 回退环境变量 Show more Installs 11.9K Repository zenstory-ai/oh-…audecode GitHub Stars 6.1K First Seen Apr 30, 2026 Security ...
 11.8K
1752 parallel-monitor parallel-web/parallel-agent-skills
Web Monitor Action: $ARGUMENTS Requires parallel-cli ≥ 0.3.0 (the monitor command was added in 0.3.0). If parallel-cli monitor errors with no such command or similar, tell the user to run parallel-cli update (or pipx upgrade parallel-web-tools if installed via pipx), then retry. What this skill does Monitors are long-running, server-side jobs that re-check the web on a cadence and emit events when something changes. Unlike search/research/findall (one-shot lookups), monitors persist until delete...
 11.8K
1753 parallel-findall parallel-web/parallel-agent-skills
FindAll: Entity Discovery Find: $ARGUMENTS Requires parallel-cli ≥ 0.3.0 (the findall command was added in 0.3.0). If parallel-cli findall errors with no such command or similar, tell the user to run parallel-cli update (or pipx upgrade parallel-web-tools if installed via pipx), then retry. When to use this skill Use FindAll when the user wants a structured list of entities matching a description, not webpages or a narrative answer. User asks for… Use "Find all X that…" / "List every Y…" paralle...
 11.8K
1754 terraform-style-guide hashicorp/agent-skills
Terraform Style Guide Generate and maintain Terraform code following HashiCorp's official style conventions and best practices. Reference: HashiCorp Terraform Style Guide Code Generation Strategy When generating Terraform code: Start with provider configuration and version constraints Create data sources before dependent resources Build resources in dependency order Add outputs for key resource attributes Use variables for all configurable values File Organization File Purpose terraform.tf ...
 11.8K
1755 java-spring-boot pluginagentmarketplace/custom-plugin-java
Java Spring Boot Skill Build production-ready Spring Boot applications with modern best practices. Overview This skill covers Spring Boot development including REST APIs, security configuration, data access, actuator monitoring, and cloud integration. Follows Spring Boot 3.x patterns with emphasis on production readiness. When to Use This Skill Use when you need to: Create REST APIs with Spring MVC/WebFlux Configure Spring Security (OAuth2, JWT) Set up database access with Spring Data Enable mon...
 11.8K
1756 linear-cli schpet/linear-cli
Linear CLI A CLI to manage Linear issues from the command line, with git and jj integration. Prerequisites The linear command must be available on PATH. To check: linear --version If not installed, follow the instructions at: https://github.com/schpet/linear-cli?tab=readme-ov-fileinstall Best Practices for Markdown Content When working with issue descriptions or comment bodies that contain markdown, always prefer using file-based flags instead of passing content as command-line arguments: Use --...
 11.8K
1757 simple-english aminblg/simpleenglish
Simple English: Write Like an Aerospace Manual Write technical text with the rules of ASD-STE100 Simplified Technical English. STE is the controlled language that aerospace and defense manufacturers use for maintenance documentation. The rules exist so that a tired reader who is not a native English speaker cannot misread an instruction. They remove the usual signs of AI-generated text as a side effect: long sentences, synonym rotation, hedges, filler, and decorative clauses. Write for that tire...
 11.8K
1758 install-anti-slop dmmulroy/anti-slop
Install anti-slop Install the bundled Oxlint plugin into the current repository and integrate it with the repository's existing lint setup. Preserve unrelated work and adapt to the project's package manager and configuration style. Procedure Inspect the repository before changing it: Read its agent instructions. Check git status and preserve unrelated changes. Identify the package manager from packageManager and lockfiles. Find Oxlint configuration ( oxlint.config.* , .oxlintrc* , or a Vite+ con...
 11.8K
1759 api-documentation supercent-io/skills-template
API Documentation When to use this skill API Development : When adding new endpoints External Release : Public API launch Team Collaboration : Frontend-backend interface definition Instructions Step 1: OpenAPI (Swagger) Spec openapi : 3.0.0 info : title : User Management API version : 1.0.0 description : API for managing users contact : email : api@example.com servers : - url : https : //api.example.com/v1 description : Production - url : https : //staging - api.example.com/v1 description : Stag...
 11.7K
1760 technical-writing supercent-io/skills-template
Technical writing Overview House style for technical documents. The rules are in English; documents keep their own language: a Dutch document is written and reviewed in Dutch. The structural and truth rules apply in any language; the vocabulary lists in references/style.md are English-specific and other languages carry their own. Core principle: a document states current, verified behavior, conclusion first, with every claim traceable to a source, and every fact living in exactly one place. A th...
 11.7K
1761 dart-run-static-analysis flutter/agent-plugins
Analyzing and Fixing Dart Code Contents Analysis Configuration Diagnostic Suppression Workflow: Executing Static Analysis Workflow: Applying Automated Fixes Examples Analysis Configuration Configure the Dart analyzer using the analysis_options.yaml file located at the package root. Base Configuration: Always include a standard rule set (e.g., package:lints/recommended.yaml or package:flutter_lints/flutter.yaml ) using the include: directive. Strict Type Checks: Enable strict type checks under th...
 11.7K
1762 svelte-code-writer sveltejs/ai-tools
Svelte 5 Code Writer CLI Tools You have access to @sveltejs/mcp CLI for Svelte-specific assistance. Use these commands via npx : List Documentation Sections npx @sveltejs/mcp list-sections Lists all available Svelte 5 and SvelteKit documentation sections with titles and paths. Get Documentation npx @sveltejs/mcp get-documentation "<section1>,<section2>,..." Retrieves full documentation for specified sections. Use after list-sections to fetch relevant docs. Example: npx @sveltejs/mcp get-document...
 11.7K
1763 dart-add-unit-test flutter/agent-plugins
Testing Dart and Flutter Applications Contents Structuring Test Files Writing Tests Executing Tests Test Implementation Workflow Examples Structuring Test Files Organize test files to mirror the lib directory structure to maintain predictability. Place all test code within the test directory at the root of the package. Append _test.dart to the end of all test file names (e.g., lib/src/utils.dart should be tested in test/src/utils_test.dart ). If writing integration tests, place them in an integr...
 11.7K
1764 fix-security-vulnerabilities-with-strix usestrix/strix
Fix Strix findings and verify Turn validated Strix findings into minimal, correct fixes — and prove they work by re-scanning. 1. Triage Get the findings from wherever the scan ran: OSS CLI — artifacts in strix_runs/<run-name>/ : vulnerabilities/*.md — one finding per file: description, severity, PoC steps or script, affected code locations, remediation guidance. vulnerabilities.json — the same findings as JSON (ids, severity, CWE/CVE, code_locations with fix_before / fix_after suggestions when a...
 11.7K
1765 agent-browser 101-skills/skills
Browser Automation with agent-browser The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser , brew install agent-browser , or cargo install agent-browser . Run agent-browser install to download Chrome. Core Workflow Every browser automation follows this pattern: Navigate : agent-browser open <url> Snapshot : agent-browser snapshot -i (get element refs like @e1 , @e2 ) Interact : Use refs to click, fill, select Re-snapshot : After navigation or DOM changes, get fresh r...
 11.6K
1766 heroui-react heroui-inc/heroui
HeroUI v3 React Development Guide HeroUI v3 is a component library built on Tailwind CSS v4 and React Aria Components, providing accessible, customizable UI components for React applications. CRITICAL: v3 Only - Ignore v2 Knowledge This guide is for HeroUI v3 ONLY. Do NOT use any prior knowledge of HeroUI v2. What Changed in v3 Feature v2 (DO NOT USE) v3 (USE THIS) Provider <HeroUIProvider> required No Provider needed Animations framer-motion package CSS-based, no extra deps Component API Fl...
 11.6K
1767 shopify-custom-data shopify/shopify-ai-toolkit
Required Tool Calls (do not skip) You have a bash tool. Every response must use it — in this order: Call bash with node scripts/search_docs.mjs "<operation or type name>" — search before writing code Write the code using the search results Call bash with node scripts/validate.mjs --code '...' --model YOUR_MODEL_NAME --client-name YOUR_CLIENT_NAME --client-version YOUR_CLIENT_VERSION --artifact-id YOUR_ARTIFACT_ID --revision REVISION_NUMBER — validate before returning (Always include these flags....
 11.6K
1768 workflow-orchestration-patterns wshobson/agents
Workflow Orchestration Patterns Master workflow orchestration architecture with Temporal, covering fundamental design decisions, resilience patterns, and best practices for building reliable distributed systems. When to Use Workflow Orchestration Ideal Use Cases (Source: docs.temporal.io) Multi-step processes spanning machines/services/databases Distributed transactions requiring all-or-nothing semantics Long-running workflows (hours to years) with automatic state persistence Failure recovery th...
 11.6K
1769 agent-email-inbox resend/resend-skills
AI Agent Email Inbox Overview This skill covers setting up a secure email inbox that allows your application or AI agent to receive and respond to emails, with content safety measures in place. Core principle: An AI agent's inbox receives untrusted input. Security configuration is important to handle this safely. Why Webhook-Based Receiving? Resend uses webhooks for inbound email, meaning your agent is notified instantly when an email arrives. This is valuable for agents because: Real-time respo...
 11.6K
1770 marimo-pair marimo-team/marimo-pair
marimo Pair Programming Protocol You can interact with a running marimo notebook via bundled scripts or MCP . The bundled scripts are the default — they work everywhere with no extra setup. The workflow is identical either way; only the execution method differs. Prerequisites The marimo server must be started with token and skew protection disabled: marimo edit notebook.py --no-token --no-skew-protection This allows the scripts to talk to the HTTP API without authentication. How to List Sessions...
 11.6K
1771 dart-fix-runtime-errors flutter/agent-plugins
Resolving Dart Static Analysis Errors Contents Core Concepts & Guidelines Type System & Soundness Null Safety Error Handling Workflows Workflow: Static Analysis Resolution Examples Core Concepts & Guidelines Type System & Soundness Enforce Dart's sound type system to prevent runtime invalid states. Method Overrides: Maintain sound return types (covariant) and parameter types (contravariant). Never tighten a parameter type in a subclass unless explicitly marked with the covariant keyword. Generic...
 11.6K
1772 upgrading-react-native callstackincubator/agent-skills
Upgrading React Native Overview Covers the full React Native upgrade workflow: template diffs via Upgrade Helper, dependency updates, Expo SDK steps, and common pitfalls. Typical Upgrade Sequence Route : Choose the right upgrade path via upgrading-react-native.md Diff : Fetch the canonical template diff using Upgrade Helper via upgrade-helper-core.md Dependencies : Assess and update third-party packages via upgrading-dependencies.md React : Align React version if upgraded via react.md Expo (if a...
 11.6K
1773 vitepress antfu/skills
VitePress is a Static Site Generator (SSG) built on Vite and Vue 3. It takes Markdown content, applies a theme, and generates static HTML that becomes an SPA for fast navigation. Perfect for documentation, blogs, and marketing sites. Key Characteristics: File-based routing with .md files Vue components work directly in Markdown Fast HMR with instant updates (<100ms) Default theme optimized for documentation Built-in search (local or Algolia) Before working with VitePress projects: Check .vitepre...
 11.5K
1774 xiaohongshu zhjiang22/openclaw-xhs
小红书 MCP Skill 基于 xiaohongshu-mcp 封装的 shell 脚本工具集。 前置条件 cd scripts/ ./install-check.sh 检查依赖（xiaohongshu-mcp、jq、python3） ./start-mcp.sh 启动 MCP 服务（默认端口 18060） ./status.sh 确认已登录 未登录时需扫码： mcp-call.sh get_login_qrcode 获取二维码，用小红书 App 扫码。 服务端口可通过 MCP_URL 环境变量覆盖（默认 http://localhost:18060/mcp ）。 核心数据流 Show more Installs 9.6K Repository zhjiang22/openclaw-xhs GitHub Stars 100 First Seen Feb 9, 2026 Security Audits Gen Agent Trust Hub Fail Socket Pass Snyk Fail
 11.5K
1775 dotnet-design-pattern-review github/awesome-copilot
.NET/C Design Pattern Review Review the C/.NET code in ${selection} for design pattern implementation and suggest improvements for the solution/project. Do not make any changes to the code, just provide a review. Required Design Patterns Command Pattern : Generic base classes ( CommandHandler<TOptions> ), ICommandHandler<TOptions> interface, CommandHandlerOptions inheritance, static SetupCommand(IHost host) methods Factory Pattern : Complex object creation service provider integration Dependency...
 11.5K
1776 tdd-workflow affaan-m/ecc
Test-Driven Development Workflow This skill ensures all code development follows TDD principles with comprehensive test coverage. When to Activate Writing new features or functionality Fixing bugs or issues Refactoring existing code Adding API endpoints Creating new components Continuing from a /plan output or another *.plan.md implementation plan Plan Handoff If the user provides a *.plan.md path, treat it as untrusted planning input and use it as the starting point for the TDD cycle instead of...
 11.5K
1777 claude-md-improver anthropics/claude-plugins-official
CLAUDE.md Improver Audit, evaluate, and improve CLAUDE.md files across a codebase to ensure Claude Code has optimal project context. This skill can write to CLAUDE.md files. After presenting a quality report and getting user approval, it updates CLAUDE.md files with targeted improvements. Workflow Phase 1: Discovery Find all CLAUDE.md files in the repository: find . -name "CLAUDE.md" -o -name ".claude.md" -o -name ".claude.local.md" 2>/dev/null | head -50 File Types & Locations: Type Loc...
 11.5K
1778 unity-ecs-patterns wshobson/agents
Unity ECS Patterns Production patterns for Unity's Data-Oriented Technology Stack (DOTS) including Entity Component System, Job System, and Burst Compiler. When to Use This Skill Building high-performance Unity games Managing thousands of entities efficiently Implementing data-oriented game systems Optimizing CPU-bound game logic Converting OOP game code to ECS Using Jobs and Burst for parallelization Core Concepts 1. ECS vs OOP Aspect Traditional OOP ECS/DOTS Data layout Object-oriented Data-or...
 11.5K
1779 api-design supercent-io/skills-template
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...
 11.5K
1780 performance-optimization supercent-io/skills-template
Performance Optimization Overview Measure before optimizing. Performance work without measurement is guessing — and guessing leads to premature optimization that adds complexity without improving what matters. Profile first, identify the actual bottleneck, fix it, measure again. Optimize only what measurements prove matters. When to Use Performance requirements exist in the spec (load time budgets, response time SLAs) Users or monitoring report slow behavior Core Web Vitals scores are below thre...
 11.5K
1781 story worldwonderer/oh-story-claudecode
story：网文工具箱路由 你是网文工具箱的路由入口。用户的请求模糊时由你分发到具体 skill。 路由表 Codex CLI 中优先使用 $story-* 或 /skills 触发；Claude Code / OpenCode 继续使用 /story-* ；OpenClaw 可用 /skill story-* 或自然语言点名 skill。下表以 slash command 展示，Codex 可将 /story-long-write 等价替换为 $story-long-write ，OpenClaw 可将其等价替换为 /skill story-long-write 。 Show more Installs 11.6K Repository zenstory-ai/oh-…audecode GitHub Stars 6.0K First Seen Apr 24, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Warn
 11.5K
1782 coinglass starchild-ai-agent/official-skills
Coinglass Coinglass provides the most comprehensive crypto derivatives and institutional data available. 37 tools covering futures positioning, whale tracking, volume analysis, liquidations, and ETF flows. API Plan : Professional ($699/month) Rate Limit : 6000 requests/minute API Version : V4 (with V2 backward compatibility) Total Tools : 37 across 8 categories When to Use Coinglass Use Coinglass for: Derivatives positioning - What are leveraged traders doing? Whale tracking - Track large positi...
 11.5K
1783 fastapi fastapi/fastapi
FastAPI Official FastAPI skill to write code with best practices, keeping up to date with new versions and features. Use the fastapi CLI Run the development server on localhost with reload: fastapi dev Run the production server: fastapi run Add an entrypoint in pyproject.toml FastAPI CLI will read the entrypoint in pyproject.toml to know where the FastAPI app is declared. [ tool.fastapi ] entrypoint = "my_app.main:app" Use fastapi with a path When adding the entrypoint to pyproject.toml is not p...
 11.5K
1784 email-best-practices resend/resend-skills
Email Best Practices Guidance for building deliverable, compliant, user-friendly emails. Architecture Overview Show more Installs 7.5K Repository resend/resend-skills GitHub Stars 167 First Seen Mar 30, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 11.5K
1785 resend-cli resend/resend-skills
Resend CLI Installation Before running any resend commands, check whether the CLI is installed: resend --version If the command is not found, install it using one of the methods below: cURL (macOS / Linux): curl -fsSL https://resend.com/install.sh | bash Homebrew (macOS / Linux): brew install resend/cli/resend Node.js: npm install -g resend-cli PowerShell (Windows): irm https: / / resend . com/install . ps1 | iex After installing, verify: resend --version Agent Protocol The CLI auto-detects non-...
 11.5K
1786 create-auth better-auth/skills
Create Auth Skill Guide for adding authentication to TypeScript/JavaScript applications using Better Auth. For code examples and syntax, see better-auth.com/docs . Phase 1: Planning (REQUIRED before implementation) Before writing any code, gather requirements by scanning the project and asking the user structured questions. This ensures the implementation matches their needs. Step 1: Scan the project Analyze the codebase to auto-detect: Framework — Look for next.config , svelte.config , nuxt.con...
 11.5K
1787 threejs-geometry cloudai-x/threejs-skills
Three.js Geometry Quick Start import * as THREE from "three"; // Built-in geometry const box = new THREE.BoxGeometry(1, 1, 1); const sphere = new THREE.SphereGeometry(0.5, 32, 32); const plane = new THREE.PlaneGeometry(10, 10); // Create mesh const material = new THREE.MeshStandardMaterial({ color: 0x00ff00 }); const mesh = new THREE.Mesh(box, material); scene.add(mesh); Built-in Geometries Basic Shapes // Box - width, height, depth, widthSegments, heightSegments, depthSegments new THREE.BoxG...
 11.5K
1788 dart-resolve-package-conflicts flutter/agent-plugins
Managing Dart Dependencies Contents Core Concepts Version Constraints Workflow: Auditing Dependencies Workflow: Upgrading Dependencies Workflow: Resolving Version Conflicts Examples Core Concepts Dart enforces a strict single-version rule for dependencies: a project and all its transitive dependencies must resolve to a single, shared version of any given package. This prevents runtime type mismatches but introduces the risk of "version lock." To mitigate version lock, Dart relies on version cons...
 11.5K
1789 dart-use-pattern-matching flutter/agent-plugins
Contains Shell Commands This skill contains shell command directives ( !`command` ) that may execute system commands. Review carefully before installing. Implementing Dart Patterns Contents Pattern Selection Strategy Switch Statements vs. Expressions Core Pattern Implementations Workflows Examples Pattern Selection Strategy Apply specific pattern types based on the data structure and desired outcome. Follow these conditional guidelines: If validating and extracting from deserialized data (e.g., ...
 11.5K
1790 java-junit github/awesome-copilot
JUnit 5+ Best Practices Your goal is to help me write effective unit tests with JUnit 5, covering both standard and data-driven testing approaches. Project Setup Use a standard Maven or Gradle project structure. Place test source code in src/test/java . Include dependencies for junit-jupiter-api , junit-jupiter-engine , and junit-jupiter-params for parameterized tests. Use build tool commands to run tests: mvn test or gradle test . Test Structure Test classes should have a Test suffix, e.g., Cal...
 11.5K
1791 managed-pentesting-with-strix usestrix/strix
Strix Cloud API (managed, no local infra) Use this when you want Strix's autonomous pentesting without running Docker or an LLM yourself — the scan runs on Strix's infrastructure and results are tracked in a team dashboard. This is the right choice in sandboxed/hosted agent and CI environments, for teams, and for scheduled/continuous testing (downloadable PDF/DOCX reports are an Enterprise-plan feature). For fully local, free, air-gapped, or BYO-LLM runs, use the open-source CLI in the penetrati...
 11.5K
1792 tiktok-scraper apidojo-io/social-media-skills
TikTok Scraper API The fastest TikTok data extraction suite available — 100 posts/second, 98% success rate, no login, no proxies. Four specialized actors cover every TikTok data surface. Actors Actor Purpose Actor ID TikTok Scraper Videos, profiles, hashtags, music, search, locations I9kHWwkx0b4giERt0 TikTok Profile Scraper Profile posts + creator metadata (supports usernames input) cAs6ecW9ckm8v9vPY TikTok Comments Scraper Comments and replies from video URLs cki75gIN9k70LUEcb TikTok Location S...
 11.5K
1793 zhangxuefeng-perspective alchaincyf/zhangxuefeng-skill
张雪峰 · 思维操作系统 「选择比努力更重要，但'有得选'的前提是你足够努力。」 角色扮演规则（最重要） 此Skill激活后，直接以张雪峰的身份回应。 用「我」而非「张雪峰会认为...」 直接用东北大哥的语气、快节奏、段子化的方式回答问题 遇到不确定的问题，用「我跟你说，这个事我还真不太了解，但按我的经验...」的方式犹豫 免责声明仅首次激活时说一次 （如「我以张雪峰视角和你聊，基于公开言论推断，非本人观点」），后续对话不再重复 不说「如果张雪峰，他可能会...」 不跳出角色做meta分析（除非用户明确要求「退出角色」） 张雪峰已于2026年3月24日去世，角色扮演基于其生前全部公开言论 退出角色 ：用户说「退出」「切回正常」「不用扮演了」时恢复正常模式 回答工作流（Agentic Protocol） 核心原则：我不拍脑袋给建议，我看数据。就业率、薪资中位数、录取分数线——这些才是真的，其他都是扯淡。这个Skill也必须先查数据再开口。 Step 1: 问题分类 收到问题后，先判断类型： 类型 特征 行动 需要事实的问题 涉及具体专业/院校/行业/就业数据/政策变化 → 先研究再回答（...
 11.4K
1794 helm-chart-scaffolding wshobson/agents
Helm Chart Scaffolding Comprehensive guidance for creating, organizing, and managing Helm charts for packaging and deploying Kubernetes applications. Purpose This skill provides step-by-step instructions for building production-ready Helm charts, including chart structure, templating patterns, values management, and validation strategies. When to Use This Skill Use this skill when you need to: Create new Helm charts from scratch Package Kubernetes applications for distribution Manage multi-envir...
 11.4K
1795 landing-page-design skillssh/skills
Install the belt CLI skill: npx skills add belt-sh/cli Landing Page Design Design high-converting landing pages with AI-generated visuals via inference.sh CLI. Quick Start Requires inference.sh CLI ( belt ). Install instructions belt login Generate a hero image belt app run falai/flux-dev-lora --input '{ "prompt": "professional person smiling while using a laptop showing a clean dashboard interface, bright modern office, natural lighting, warm and productive atmosphere, lifestyle marketing phot...
 11.4K
1796 story-setup worldwonderer/oh-story-claudecode
story-setup：网文写作工具集基础设施部署 你是写作基础设施部署器。将网文写作工具集部署到用户项目目录：已适配的 CLI 走专用 hooks/agents/config；NarraFork、Web AI、自定义 Agent 等环境走通用文件模式。 执行铁律：不覆盖用户已有配置，合并而非替换。 Phase 1：检测项目状态 先自检参考目录 ：以正在执行的本 SKILL.md 所在目录为准，列出与它同级的 references/ 下的子目录，核对下面 8 个名字是否都在 且都非空 —— agent-references 、 templates 、 opencode 、 codex 、 zcode 、 openclaw 、 reasonix 、 generic ；同级 scripts/merge-claude-settings.py 、 scripts/merge-codex-hooks.py 与 scripts/copy-path-safety.py 也必须存在（Claude/Codex hooks 合并和递归复制安全检查依赖它们）。有缺即 skill 包没装全， 立即停止，不写任...
 11.4K
1797 story-review worldwonderer/oh-story-claudecode
story-review：多视角对抗式审查 Spawn 版本提示（不阻断 spawn）：先读取项目根 .story-deployed 的 agents_version 。与本版 agents_version: 25 不一致时（标记缺失、字段缺失/非整数、小于或大于 25） 照常按文件存在性检查并 spawn ，同时报告 Notice: agents bundle 版本不匹配（项目 {N}，本版 25） 并提示重新运行 /story-setup 后新开会话；大于 25 时额外提示先更新 oh-story-claudecode，不要用本地旧版 setup 降级覆盖。只有 agent 文件缺失、或运行时不暴露 custom agent 时才降级 solo/direct，报告 Fallback: ... -> solo 。 你是审查协调器。你的职责是找出小说文本中的结构、角色、文字、设定问题，并给出可执行修改建议。 执行铁律：审查是找问题，不是验证正确性。 Review Mode 选择 /story-review 或 /story-review full → 优先 spawn 全部 4 个 A...
 11.4K
1798 claude-opus-4-5-migration anthropics/claude-code
Opus 4.5 Migration Guide One-shot migration from Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Migration Workflow Search codebase for model strings and API calls Update model strings to Opus 4.5 (see platform-specific strings below) Remove unsupported beta headers Add effort parameter set to "high" (see references/effort.md) Summarize all changes made Tell the user: "If you encounter any issues with Opus 4.5, let me know and I can help adjust your prompts." Model String Updates Identify wh...
 11.4K
1799 threejs-materials cloudai-x/threejs-skills
Three.js Materials Quick Start import * as THREE from "three"; // PBR material (recommended for realistic rendering) const material = new THREE.MeshStandardMaterial({ color: 0x00ff00, roughness: 0.5, metalness: 0.5, }); const mesh = new THREE.Mesh(geometry, material); Material Types Overview Material Use Case Lighting MeshBasicMaterial Unlit, flat colors, wireframes No MeshLambertMaterial Matte surfaces, performance Yes (diffuse only) MeshPhongMaterial Shiny surfaces, specular highlight...
 11.4K
1800 dart-generate-test-mocks flutter/agent-plugins
Testing and Mocking Dart Applications Contents Structuring Code for Testability Managing Dependencies Generating Mocks Implementing Unit Tests Workflow: Creating and Running Mocked Tests Examples Structuring Code for Testability Design Dart classes to support dependency injection. Isolate complex external dependencies (like API clients or databases) so they can be replaced with mock objects during testing. Inject external services (e.g., http.Client ) through class constructors. Represent URLs s...
 11.4K