███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 20251 | piper-tts-training | sammcj/agentic-coding |
Piper TTS Voice Training Train custom text-to-speech voices compatible with Piper's lightweight ONNX runtime. Overview Piper produces fast, offline TTS suitable for embedded devices. Training involves: Corpus preparation (text covering phonetic range) Audio generation or recording Quality validation via Whisper transcription Fine-tuning from existing checkpoint (recommended) or training from scratch ONNX export for deployment Fine-tuning vs from-scratch: Fine-tuning: ~1,300 phrases + 1,000 epoch...
|
43 |
| 20252 | authoring-claude-md | sammcj/agentic-coding |
CLAUDE.md Authoring Create effective CLAUDE.md files that serve as project-specific memory for AI coding agents. Purpose CLAUDE.md files provide AI agents with: Non-obvious conventions, architectural patterns and gotchas Confirmed solutions to recurring issues Project-specific context not found in standard documentation Not for : Obvious patterns, duplicating documentation, or generic coding advice. Core Principles Signal over noise : Every sentence must add non-obvious value. If an AI agent cou...
|
43 |
| 20253 | laravel:documentation-best-practices | jpcaparas/superpowers-laravel |
Keep documentation minimal and meaningful. Well-written code with descriptive names often eliminates the need for comments. Document the "why" not the "what", and focus on complex business logic, not obvious code. When NOT to Document ``` // BAD: Redundant comments that add no value class UserController { // This is the constructor public function __construct( // Inject user repository private UserRepository $repository ) { // Set the repository $th...
|
43 |
| 20254 | resume-design-generation | eachlabs/skills |
Resume Design Generation Generate visually stunning and professionally designed resumes and CVs using each::sense. This skill creates resume layouts and designs optimized for different industries, career levels, and personal branding styles. Features Modern Professional : Clean, contemporary designs for corporate environments Creative Designer : Bold, artistic layouts for creative industries Minimalist : Simple, elegant designs with focus on content Executive/Corporate : Sophisticated designs fo...
|
43 |
| 20255 | context-manager | jackspace/claudeskillz |
Use this skill when Working on context manager tasks or workflows Needing guidance, best practices, or checklists for context manager Do not use this skill when The task is unrelated to context manager You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implementation-playbook.md . You ar...
|
43 |
| 20256 | godot-genre-survival | thedivergentai/gd-agentic-skills |
Genre: Survival Resource scarcity, needs management, and progression through crafting define survival games. Available Scripts inventory_slot_resource.gd Expert inventory slot pattern using Resources for save compatibility. Core Loop Harvest : Gather resources (Wood, Stone, Food) Craft : Convert resources into tools/items Build : Construct shelter/base Survive : Manage needs (Hunger, Thirst, Environmental threats) Thrive : Automation and tech to transcend early struggles NEVER Do in Survival Gam...
|
43 |
| 20257 | fix-flaky-tests | tuist/tuist |
Fix Flaky Test Quick Start You'll typically receive a Tuist test case URL or identifier. Follow these steps to investigate and fix it: Run tuist test case show <id-or-identifier> --json to get reliability metrics for the test. Run tuist test case run list Module/Suite/TestCase --flaky --json to see flaky run patterns. Run tuist test case run show <run-id> --json on failing flaky runs to get failure messages and file paths. Read the test source at the reported path and line, identify the flaky pa...
|
43 |
| 20258 | erpnext-errors-permissions | openaec-foundation/erpnext_anthropic_claude_development_skill_package |
ERPNext Permissions - Error Handling This skill covers error handling patterns for the Frappe permission system. For permission syntax, see erpnext-permissions . For hooks, see erpnext-syntax-hooks . Version : v14/v15/v16 compatible Permission Error Handling Overview ┌─────────────────────────────────────────────────────────────────────┐ │ PERMISSION ERRORS REQUIRE SPECIAL HANDLING │ ├─────────────────────────────────────────────────────────────────────┤ │ ...
|
43 |
| 20259 | azure-resource-manager-durabletask-dotnet | sickn33/antigravity-awesome-skills |
Azure.ResourceManager.DurableTask (.NET) Management plane SDK for provisioning and managing Azure Durable Task Scheduler resources via Azure Resource Manager. ⚠️ Management vs Data Plane This SDK (Azure.ResourceManager.DurableTask) : Create schedulers, task hubs, configure retention policies Data Plane SDK (Microsoft.DurableTask.Client.AzureManaged) : Start orchestrations, query instances, send events Installation dotnet add package Azure.ResourceManager.DurableTask dotnet add package Azure.Iden...
|
43 |
| 20260 | altinity-expert-clickhouse-overview | altinity/skills |
System Health and Routing Overview Quick health check and routing entry point for ClickHouse diagnostics. Run this first, then chain to other skills based on findings. Timeframe Handling Use the timeframe specified by the user. If none is provided, default to the last 24 hours. Use it consistently for system.errors and for scanning all system.*_log tables. Routing Rules (Chain to Other Skills) High memory usage or OOMs → altinity-expert-clickhouse-memory Disk usage > 80% or poor compression ...
|
43 |
| 20261 | argocdreview | julianobarbosa/claude-code-skills |
ArgoCDReview - ArgoCD CLI Review & Troubleshooting Comprehensive ArgoCD CLI commands for reviewing applications, diagnosing issues, and managing deployments. This skill provides structured commands for inspecting ArgoCD application state, comparing live manifests against Git, reviewing deployment history, and troubleshooting sync failures. Prerequisites ArgoCD CLI installed (argocd) Logged into ArgoCD server: argocd login <server> Context set if using multiple clusters Verify connection argo...
|
43 |
| 20262 | read-bin-docs | ypares/agent-skills |
Need to extract text from a PDF? Use this Python snippet: ``` from pypdf import PdfReader reader = PdfReader("document.pdf") text = "".join(page.extract_text() for page in reader.pages) print(text) ``` Or from the command line: ``` uvx --with pypdf python /path/to/extract_pdf_text.py document.pdf ``` PDF Text Extraction Basic Usage ``` from pypdf import PdfReader Read all pages reader = PdfReader("file.pdf") for page in reader.pages: text = page.extract_text() print(text) `...
|
43 |
| 20263 | skill-creator | volcengine/openviking |
Skill Creator A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes like this: Decide what you want the skill to do and roughly how it should do it Write a draft of the skill Create a few test prompts and run claude-with-access-to-the-skill on them Help the user evaluate the results both qualitatively and quantitatively While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you...
|
43 |
| 20264 | skill-tester | borghei/claude-skills |
Skill Tester Name : skill-tester Tier : POWERFUL Category : Engineering Quality Assurance Dependencies : None (Python Standard Library Only) Author : Claude Skills Engineering Team Version : 1.0.0 Last Updated : 2026-02-16 Description The Skill Tester is a comprehensive meta-skill designed to validate, test, and score the quality of skills within the claude-skills ecosystem. This powerful quality assurance tool ensures that all skills meet the rigorous standards required for BASIC, STANDARD, and...
|
43 |
| 20265 | api-gateway-patterns | nickcrew/claude-ctx-plugin |
API Gateway Patterns A comprehensive skill for implementing production-grade API gateways using Kong and industry best practices. This skill covers advanced routing, authentication, rate limiting, load balancing, traffic management, and observability patterns for microservices architectures. When to Use This Skill Use this skill when: Implementing an API gateway for microservices architectures Managing traffic routing, load balancing, and service discovery Implementing authentication and aut...
|
43 |
| 20266 | sentry-integration | blogic-cz/blogic-marketplace |
Sentry Integration Patterns Overview Implement error tracking and performance monitoring using Sentry following the project's established patterns for both client and server. When to Use This Skill Configuring Sentry SDK Adding error tracking to TRPC procedures Implementing custom spans/traces Setting up user context Working with Sentry API SDK Configuration Server-side // apps/web-app/src/server.ts import * as Sentry from "@sentry/tanstackstart-react" ; Sentry . init ( { ... ( env . SENTRY_DSN ...
|
43 |
| 20267 | godot-adapt-3d-to-2d | thedivergentai/gd-agentic-skills |
Adapt: 3D to 2D Expert guidance for simplifying 3D games into 2D (or 2.5D). NEVER Do NEVER remove Z-axis without gameplay compensation — Blindly flattening 3D to 2D removes spatial strategy. Add other depth mechanics (layers, jump height variations). NEVER keep 3D collision shapes — Use simpler 2D shapes (CapsuleShape2D, RectangleShape2D). 3D shapes don't convert automatically. NEVER use orthographic Camera3D as "2D mode" — Use actual Camera2D for proper 2D rendering pipeline and performance. NE...
|
43 |
| 20268 | debugging-code | almogbaku/debug-skill |
Interactive Debugger Use when a program crashes, produces wrong output, or you need to understand exactly how execution reached a particular state — and running it again with more print statements won't give you the answer fast enough. You can pause a running program at any point, read live variable values and the call stack at that exact moment, step forward line by line or jump to the next breakpoint, and evaluate arbitrary expressions against the live process — all without restarting. Setup T...
|
43 |
| 20269 | e2e-tester | redpanda-data/console |
E2E Testing with Playwright & Testcontainers Write end-to-end tests using Playwright against a full Redpanda Console stack running in Docker containers via testcontainers. When to Use This Skill Testing 2+ step user journeys (login -> action -> verify) Multi-page workflows Browser automation with Playwright NOT for: Component unit tests -> use testing Critical Rules ALWAYS: Run bun run build before running E2E tests (frontend assets required) Use testcontainers API for container management (neve...
|
43 |
| 20270 | jscpd | knoopx/pi |
jscpd Duplicate code detector supporting 150+ languages. Usage Analyze directory npx jscpd /path/to/source With pattern filter npx jscpd --pattern "src//*.js" . Ignore directories npx jscpd --ignore "/node_modules/,/dist/" . Minimum tokens to match (default: 50) npx jscpd --min-tokens 30 . Output formats npx jscpd --reporters json --output report.json . npx jscpd --reporters html --output ./report/ . Common Options Option Description --min-tokens N Minimum tokens for duplicate detect...
|
43 |
| 20271 | r-package-development | posit-dev/skills |
R package development Key commands Run code in the package Rscript -e "devtools::load_all(); code" Run all tests Rscript -e "devtools::test()" Run all tests for files starting with {name} Rscript -e "devtools::test(filter = '^{name}')" Run all tests for R/{name}.R Rscript -e "devtools::test_active_file('R/{name}.R')" Run a single test "blah" for R/{name}.R Rscript -e "devtools::test_active_file('R/{name}.R', desc = 'blah')" Redocument the package Rscript -e "devtools::document()" Check pk...
|
43 |
| 20272 | data-model-creation | tencentcloudbase/cloudbase-mcp |
When to use this skill This is an OPTIONAL advanced modeling tool for complex database design. Most simple table creation should use relational-database-tool directly with SQL statements. ONLY use this skill when you specifically need: Complex multi-table relationships with automatic foreign key management Visual ER diagram generation for documentation Automated field type mapping and constraint generation Enterprise-level data model documentation For most cases, use relational-database-tool ski...
|
43 |
| 20273 | shopify-app-api-patterns | tamiror6/shopify-app-skills |
Shopify App API Patterns Use this skill when building frontend features that communicate with your app's backend in a Shopify Remix app. When to Use Adding new pages that fetch data from Shopify or your database Creating forms that submit data (mutations) Using useFetcher for client-side data operations Handling authenticated sessions in routes Building APIs for app extensions or external services Architecture Overview ┌─────────────────────────────────────────────────────────────┐ │ ...
|
43 |
| 20274 | tanstack-form | oakoss/agent-skills |
Overview TanStack Form is a headless form library with deep TypeScript integration. It provides field-level and form-level validation (sync/async), array fields, linked/dependent fields, fine-grained reactivity, and schema validation adapter support (Zod, Valibot, Yup). Package: @tanstack/react-form Adapters: @tanstack/zod-form-adapter , @tanstack/valibot-form-adapter Status: Stable (v1) Installation npm install @tanstack/react-form Optional schema adapters: npm install @tanstack/zod-form-adapt...
|
43 |
| 20275 | deploying-contracts-on-base | base/base-skills |
Deploying Contracts on Base Prerequisites Configure RPC endpoint (testnet: sepolia.base.org , mainnet: mainnet.base.org ) Store private keys in Foundry's encrypted keystore — never commit keys Obtain testnet ETH from CDP faucet (testnet only) Get a BaseScan API key for contract verification Security Never commit private keys to version control — use Foundry's encrypted keystore ( cast wallet import ) Never hardcode API keys in source files — use environment variables or foundry.toml with ${ENV_V...
|
43 |
| 20276 | motion-v-skilld | harlan-zw/vue-ecosystem-skills |
motiondivision/motion-vue motion-v Version: 2.0.1 (Mar 2026) Deps: framer-motion@^12.29.2, hey-listen@^1.0.8, motion-dom@^12.29.2, motion-utils@^12.29.2 Tags: latest: 2.0.1 (Mar 2026) References: Docs — API reference, guides API Changes This section documents version-specific API changes — prioritize recent major/minor releases. BREAKING: focus , hover , press , inView shorthand props — removed in v2.0.0-beta.1. Use whileFocus , whileHover , whilePress , and whileInView for animations, and full ...
|
43 |
| 20277 | supabase | dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations |
Supabase Core Principles 1. Supabase changes frequently — verify against current docs before implementing. Do not rely on training data for Supabase features. Function signatures, config.toml settings, and API conventions change between versions. Before implementing, look up the relevant topic using the documentation access methods below. 2. Verify your work. After implementing any fix, run a test query to confirm the change works. A fix without verification is incomplete. 3. Recover from errors...
|
43 |
| 20278 | swift-accessibility-skill | pasqualevittoriosi/swift-accessibility-skill |
Platform Accessibility Overview Apply accessibility for SwiftUI, UIKit, and AppKit across all supported platforms. Covers all 9 App Store Accessibility Nutrition Label categories — VoiceOver, Voice Control, Larger Text, Dark Interface, Differentiate Without Color, Sufficient Contrast, Reduced Motion, Captions, and Audio Descriptions. This skill prioritizes native platform APIs (which provide free automatic support) and fact-based guidance without architecture opinions. First-Draft Rules Include ...
|
43 |
| 20279 | anvil | simota/agent-skills |
You are "Anvil" - a command-line craftsman who forges powerful terminal experiences. Your mission is to build ONE polished CLI command, TUI component, or development tool integration that provides an excellent developer experience. CLI/TUI Coverage Area Scope Terminal UI Progress bars, spinners, tables, selection menus, prompts CLI Design Command structure, argument parsing, help generation, output formatting Tool Integration Linter/Formatter setup, test runner config, build tool integration En...
|
43 |
| 20280 | terraform-state-manager | dengineproblem/agents-monorepo |
Terraform State Manager Эксперт по управлению Terraform state файлами, remote backends, state operations и troubleshooting. Core Principles State File Security state_security_principles : - principle : "Never commit state to version control" reason : "State files contain sensitive information including secrets" - principle : "Use remote backends for team environments" reason : "Enables collaboration and prevents state corruption" - principle : "Enable encryption at rest and in transit" reason : ...
|
43 |
| 20281 | web-browser | tkersey/dotfiles |
Web Browser Skill Minimal CDP tools for collaborative site exploration. Start Chrome ./scripts/start.js Fresh profile ./scripts/start.js --profile Copy your profile (cookies, logins) Start Chrome on :9222 with remote debugging. Navigate ./scripts/nav.js https://example.com ./scripts/nav.js https://example.com --new Navigate current tab or open new tab. Evaluate JavaScript ./scripts/eval.js 'document.title' ./scripts/eval.js 'document.querySelectorAll("a").length' ./scri...
|
43 |
| 20282 | vercel-react-native-skills | vercel-labs/vercel-skills |
React Native Skills Comprehensive best practices for React Native and Expo applications. Contains rules across multiple categories covering performance, animations, UI patterns, and platform-specific optimizations. When to Apply Reference these guidelines when: Building React Native or Expo apps Optimizing list and scroll performance Implementing animations with Reanimated Working with images and media Configuring native modules or fonts Structuring monorepo projects with native dependencies Rul...
|
43 |
| 20283 | nx-monorepo | panaversity/agentfactory |
Nx Monorepo Overview Provides comprehensive guidance for working with Nx monorepos in TypeScript/JavaScript projects. Nx is a smart build system with advanced caching, affected command execution, and powerful generators for React, Next.js, NestJS, and more. This skill covers workspace creation, project generation, task execution, caching strategies, Module Federation, and CI/CD integration. When to Use Use this skill when: Creating a new Nx workspace or initializing Nx in an existing project Gen...
|
43 |
| 20284 | frontend-design | johnlindquist/claude |
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
|
43 |
| 20285 | squash-stretch-mastery | dylantarre/animation-principles |
Squash and stretch is considered the most important of Disney's 12 principles because it solves animation's fundamental problem: making rigid objects feel alive. Developed in the 1930s at Disney, it emerged from observing how real flesh and rubber deform under force while maintaining constant volume. Core Theory Volume Preservation: When an object squashes, it must widen. When it stretches, it must narrow. This constraint creates believability—violate it and objects appear to grow or shrink r...
|
43 |
| 20286 | eisenhower-matrix | guia-matthieu/clawfu-skills |
Eisenhower Matrix "What is important is seldom urgent and what is urgent is seldom important." Master Dwight D. Eisenhower's prioritization framework to focus on what truly matters. When to Use This Skill Feeling overwhelmed by too many tasks and not enough time Weekly planning to set priorities for the week ahead Daily triage when everything seems urgent Delegation decisions to identify what others should handle Saying no by recognizing tasks that shouldn't be done at all Breaking reactive cycl...
|
43 |
| 20287 | vue3-best-practices | eva813/vue3-skills |
Vue 3 Best Practices Comprehensive performance optimization and development guide for Vue 3 applications. Contains 45 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Writing new Vue 3 components or composables Implementing reactive data and computed properties Reviewing code for performance issues Refactoring from Vue 2 to Vue 3 Optimizing bundle size or load times Working with state management (P...
|
43 |
| 20288 | write-agent | inkeep/team-skills |
Write Agent Skill Design agents that are focused, safe, and reliable without over-constraining them. Key principle: treat tokens and attention as a shared budget . Prefer small, high-signal prompts plus strong output contracts over long prose. How this skill uses supporting files This skill includes optional supporting material in references/ and templates/ . When a workflow step says Load: path/to/file.md , open that file before continuing. If you feel uncertain about a decision point, jump to ...
|
43 |
| 20289 | pr-reviewer | spillwavesolutions/pr-reviewer-skill |
PR Reviewer Skill Conduct comprehensive, professional code reviews for GitHub Pull Requests using industry-standard criteria and automated tooling. Table of Contents Purpose When to Use Review Process Workflow Reference Documentation Scripts Reference Best Practices Quick Reference Commands Tips for Effective Reviews Resources Purpose This skill performs code reviews by: Automating data collection - Fetching all PR-related information (metadata, diff, comments, commits, issues) Organizing review...
|
43 |
| 20290 | large-500-800ms | dylantarre/animation-principles |
Large Animations (500-800ms) At 500-800ms, animations become events. Users stop and watch. Reserve this duration for significant moments that deserve attention and communicate importance. Disney Principles at Large Scale Full Expression of All Principles Squash & Stretch: Dramatic deformation - 20-30% stretch visible and characterful. Objects feel elastic and alive. Anticipation: Extended wind-up - 150-200ms anticipation sells the action. Clear "about to happen" signal. Staging: Sophisticat...
|
43 |
| 20291 | ipsw | blacktop/ipsw-skill |
IPSW - Apple Reverse Engineering Toolkit Install: brew install blacktop/tap/ipsw Choose Your Workflow Goal Start Here Download/extract firmware Firmware Acquisition Reverse engineer userspace Userspace RE Analyze kernel/KEXTs Kernel Analysis Research entitlements Entitlements Dump private API headers Class Dump Analyze standalone binary Mach-O Analysis Firmware Acquisition Download latest IPSW for device ipsw download ipsw --device iPhone16,1 --latest Download with automatic kernel/DSC extr...
|
43 |
| 20292 | direnv | julianobarbosa/claude-code-skills |
direnv Skill This skill provides comprehensive guidance for working with direnv, covering installation, configuration, stdlib functions, and best practices for per-project environment management. When to Use This Skill Use this skill when: Installing and configuring direnv on macOS or Linux Creating or modifying .envrc files for projects Setting up per-project environment variables Configuring language-specific layouts (Python, Node.js, Ruby, Go, Perl) Integrating direnv with Nix or Nix Flak...
|
43 |
| 20293 | gin | teachingai/full-stack-skills |
When to use this skill Use this skill whenever the user wants to: [待完善:根据具体工具添加使用场景] How to use this skill [待完善:根据具体工具添加使用指南] Best Practices [待完善:根据具体工具添加最佳实践] Keywords [待完善:根据具体工具添加关键词]
|
43 |
| 20294 | azure-ai-translation-document-py | sickn33/antigravity-awesome-skills |
Azure AI Document Translation SDK for Python Client library for Azure AI Translator document translation service for batch document translation with format preservation. Installation pip install azure-ai-translation-document Environment Variables AZURE_DOCUMENT_TRANSLATION_ENDPOINT = https:// < resource > .cognitiveservices.azure.com AZURE_DOCUMENT_TRANSLATION_KEY = < your-api-key > If using API key Storage for source and target documents AZURE_SOURCE_CONTAINER_URL = https:// < storage > .blob...
|
43 |
| 20295 | thesys-generative-ui | ovachiever/droid-tings |
Thesys Generative UI Last Updated : 2025-11-10 Quick Start import { generateUI } from 'thesys' ; const ui = await generateUI ( { prompt : 'Create a user profile card with avatar, name, and email' , schema : { type : 'component' , props : [ 'name' , 'email' , 'avatar' ] } } ) ; export default function Profile ( ) { return < div > { ui } < / div > ; } Core Features Natural Language : Describe UI in plain English Schema-Driven : Type-safe component generation React Components : Generate production-...
|
43 |
| 20296 | agent-estimation | zhanghandong/agent-estimation |
Agent Work Estimation Skill Problem AI coding agents systematically overestimate task duration because they anchor to human developer timelines absorbed from training data. A task an agent can complete in 30 minutes gets estimated as "2-3 days" because that's what a human developer forum post would say. Solution Force the agent to estimate from its own operational units — tool-call rounds — and only convert to human wallclock time at the very end. Core Units Unit Definition Scale Round One tool-...
|
43 |
| 20297 | nx-ci-monitor | tech-leads-club/agent-skills |
CI Monitor Command You are the orchestrator for monitoring Nx Cloud CI pipeline executions and handling self-healing fixes. You spawn the ci-watcher subagent to poll CI status and make decisions based on the results. Context Current Branch: ! git branch --show-current Current Commit: ! git rev-parse --short HEAD Remote Status: ! git status -sb | head -1 User Instructions $ARGUMENTS Important: If user provides specific instructions, respect them over default behaviors described below. Configurati...
|
43 |
| 20298 | wechat-ai-publisher | bbwdadfg/wechat-ai-publisher |
微信公众号 AI 热点自动发布工具 完整链路 1. 询问用户配置(主题、风格、配图数量) ↓ 2. Exa/Tavily 搜索采集 AI 热点资料 ↓ 3. 撰写文章(Markdown 格式) ↓ 4. 调用 nanobanana API 生成配图 ↓ 5. 上传图片到微信服务器(获取 mmbiz URL) ↓ 6. 转换为 HTML 并发布到公众号草稿箱 ↓ 7. 提示用户去微信公众号后台检查文章 配置信息 微信公众号 API AppID : WECHAT_APPID (通过环境变量配置) AppSecret : WECHAT_SECRET (通过环境变量配置) 图片生成 API 模型 : google/nano-banana-pro (通过 Replicate) 脚本 : ~/.codex/skills/article-illustrator/scripts/generate_image.py (也可能是 ~/.claude/skills/... 或 ~/.gemini/skills/... ,以你的工具为准) 配置方法见 README.md (本仓库已移除所有硬编码密钥/Toke...
|
43 |
| 20299 | social-media-strategist | sorabhv/social-media-strategist |
Social Media Strategist You are a social media strategist agent for small businesses. You discover what's trending right now across TikTok and Google Trends, then generate ready-to-film Reel concepts and a weekly posting calendar tailored to the user's business type. Memory (Business Profile) Before doing anything else , read the saved business profile: cat memory/business_profile.json If a profile exists (fields are not all null ): Present the saved profile to the user in a friendly summary, e....
|
43 |
| 20300 | nix-rebuild | edmundmiller/dotfiles |
Nix System Rebuild After changing any Nix-managed config in ~/.config/dotfiles , the system must be rebuilt for changes to take effect. Nix store symlinks are read-only — you cannot edit them in place. Quick Rebuild cd ~/.config/dotfiles sudo darwin-rebuild switch --flake . darwin-rebuild has a NOPASSWD sudoers rule, so this works non-interactively. Using hey The hey command wraps rebuilds: hey rebuild or: hey re hey test build + activate without boot entry hey rollback roll back to previous ...
|
43 |