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...
21,493
总 Skills
36.5M
总安装量
2,447
贡献者
# Skill 仓库 描述 安装量
6651 web-browser mitsuhiko/agent-stuff
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...
 317
6652 ocr mr-shaper/opencode-skills-paddle-ocr
OCR Skill Usage To extract text from an image or PDF, run: python3 "/Users/mrshaper/Library/Application Support/com.differentai.openwork/workspaces/starter/.opencode/skills/paddle-ocr/scripts/ocr.py" "/path/to/image.png" Options Option Description --prompt "text" Custom prompt (e.g., "Extract table as markdown") --fast Use faster PaddleOCR instead of DeepSeek-OCR --json Output as JSON format Examples Basic OCR python3 scripts/ocr.py image.png Extract table as markdown python3 scripts/ocr.py ta...
 317
6653 personal-productivity oldwinter/skills
Personal Productivity Help the user manage their time and tasks more effectively using techniques from 2 product leaders. How to Help When the user asks for help with personal productivity: Understand their situation - Ask what's overwhelming them, how they currently manage their time, and what outcomes they're trying to achieve Identify the bottleneck - Determine if the issue is prioritization, focus, energy management, or too many commitments Apply practical techniques - Help them implement ti...
 317
6654 create-docs nuxt-content/docus
Create Docs Generate a complete, production-ready documentation site for any project. Workflow Analyze - Detect package manager, monorepo structure, read context Initialize - Create docs directory with correct setup Generate - Write documentation pages using templates Configure - Set up AI integration (MCP, llms.txt) Finalize - Provide next steps with correct commands Package Manager Reference Detect from lock files, default to npm if none found: Lock File PM Install Run Add pnpm-lock.yaml p...
 317
6655 wcag-accessibility-audit mastepanoski/claude-skills
WCAG Accessibility Audit This skill enables AI agents to perform a comprehensive web accessibility evaluation using the Web Content Accessibility Guidelines (WCAG) 2.1 and 2.2 standards, ensuring digital products are usable by people with disabilities. WCAG is the international standard for web accessibility (ISO/IEC 40500), legally required in many jurisdictions (ADA, Section 508, European Accessibility Act, etc.). Use this skill to identify accessibility barriers, ensure legal compliance, reac...
 317
6656 ml-paper-writing orchestra-research/ai-research-skills
ML Paper Writing for Top AI Conferences Expert-level guidance for writing publication-ready papers targeting NeurIPS, ICML, ICLR, ACL, AAAI, and COLM. This skill combines writing philosophy from top researchers (Nanda, Farquhar, Karpathy, Lipton, Steinhardt) with practical tools: LaTeX templates, citation verification APIs, and conference checklists. Core Philosophy: Collaborative Writing Paper writing is collaborative, but Claude should be proactive in delivering drafts. The typical workflo...
 317
6657 code-review-ai-ai-review sickn33/antigravity-awesome-skills
AI-Powered Code Review Specialist You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, Claude 4.5 Sonnet) with battle-tested platforms (SonarQube, CodeQL, Semgrep) to identify bugs, vulnerabilities, and performance issues. Use this skill when Working on ai-powered code review specialist tasks or workflows Needing guidance, best practices, or checklists...
 317
6658 vite uni-helper/skills
Vite Based on Vite 8 beta (Rolldown-powered). Vite 8 uses Rolldown bundler and Oxc transformer. Vite is a next-generation frontend build tool with fast dev server (native ESM + HMR) and optimized production builds. Preferences Use TypeScript: prefer vite.config.ts Always use ESM, avoid CommonJS Core Topic Description Reference Configuration vite.config.ts , defineConfig , conditional configs, loadEnv core-config Features import.meta.glob , asset queries ( ?raw , ?url ), import.meta.env , HMR API...
 317
6659 spring-boot-project-creator giuseppe-trisciuoglio/developer-kit
Spring Boot Project Creator Overview Generates a fully configured Spring Boot project from scratch using the Spring Initializr API. The skill walks the user through selecting project parameters, choosing an architecture style (DDD or Layered), configuring data stores, and setting up Docker Compose for local development. The result is a build-ready project with standardized structure, dependency management, and configuration. When to Use Bootstrap a new Spring Boot 3.x or 4.x project with a stand...
 317
6660 android-gradle-logic new-silvermoon/awesome-android-agent-skills
No SKILL.md available for this skill. View on GitHub
 317
6661 mmx-cli minimax-ai/skills
MiniMax CLI — Agent Skill Guide Use mmx to generate text, images, video, speech, music, and perform web search via the MiniMax AI platform. Prerequisites Install npm install -g mmx-cli Auth (OAuth persists to ~/.mmx/credentials.json, API key persists to ~/.mmx/config.json) mmx auth login --api-key sk-xxxxx Verify active auth source mmx auth status Or pass per-call mmx text chat --api-key sk-xxxxx --message "Hello" Region is auto-detected. Override with --region global or --region cn . Agent ...
 317
6662 academic-researcher silupanda/academic-researcher
Academic Researcher You are an academic research assistant with expertise across disciplines for literature reviews, paper analysis, and scholarly writing. When to Apply Use this skill when: Conducting literature reviews Summarizing research papers Analyzing research methodologies Structuring academic arguments Formatting citations (APA, MLA, Chicago, etc.) Identifying research gaps Writing research proposals Paper Analysis Framework When reviewing academic papers, address: 1. Research Question ...
 316
6663 research-agent parcadei/continuous-claude-v3
Note: The current year is 2025. When researching best practices, use 2024-2025 as your reference timeframe. Research Agent You are a research agent spawned to gather external documentation, best practices, and library information. You use MCP tools (Nia, Perplexity, Firecrawl) and write a handoff with your findings. What You Receive When spawned, you will receive: Research question - What you need to find out Context - Why this research is needed (e.g., planning a feature) Handoff directory...
 316
6664 agent-context-isolation parcadei/continuous-claude-v3
Agent Context Isolation Prevent agent output from polluting the main context window. Rules 1. Use Background Agents with File-Based Coordination RIGHT - background agent writes to file, main reads file Task(subagent_type="...", run_in_background=true, prompt="... Output to: /path/to/file.md") WRONG - foreground agent dumps full transcript into main context Task(subagent_type="...", run_in_background=false) Background agents with run_in_background=true isolate their context. Have them writ...
 316
6665 codebase-documenter mhattingpete/claude-skills-marketplace
Codebase Documenter Overview This skill enables creating comprehensive, beginner-friendly documentation for codebases. It provides structured templates and best practices for writing READMEs, architecture guides, code comments, and API documentation that help new users quickly understand and contribute to projects. Core Principles for Beginner-Friendly Documentation When documenting code for new users, follow these fundamental principles: Start with the "Why" - Explain the purpose before div...
 316
6666 python-sdk inference-sh/skills
Python SDK Build AI applications with the inference.sh Python SDK. Quick Start pip install inferencesh from inferencesh import inference client = inference ( api_key = "inf_your_key" ) Run an AI app result = client . run ( { "app" : "infsh/flux-1-dev" , "input" : { "prompt" : "A sunset over mountains" } } ) print ( result [ "output" ] ) Installation Standard installation pip install inferencesh With async support pip install inferencesh [ async ] Requirements: Python 3.8+ Authentication impor...
 316
6667 design-system-starter davila7/claude-code-templates
Design System Starter Build robust, scalable design systems that ensure visual consistency and exceptional user experiences. Quick Start Just describe what you need: Create a design system for my React app with dark mode support That's it. The skill provides tokens, components, and accessibility guidelines. Triggers Trigger Example Create design system "Create a design system for my app" Design tokens "Set up design tokens for colors and spacing" Component architecture "Design component structur...
 316
6668 json-canvas davila7/claude-code-templates
JSON Canvas Skill This skill enables skills-compatible agents to create and edit valid JSON Canvas files (.canvas) used in Obsidian and other applications. Overview JSON Canvas is an open file format for infinite canvas data. Canvas files use the .canvas extension and contain valid JSON following the JSON Canvas Spec 1.0. File Structure A canvas file contains two top-level arrays: { "nodes": [], "edges": [] } nodes (optional): Array of node objects edges (optional): Array of edge obje...
 316
6669 rabbitmq-expert martinholovsky/claude-skills-generator
RabbitMQ Message Broker Expert 1. Overview You are an elite RabbitMQ engineer with deep expertise in: 2. Core Principles TDD First - Write tests before implementation; verify message flows with test consumers Performance Aware - Optimize prefetch, batching, and connection pooling from the start Reliability Obsessed - No message loss through durability, confirms, and proper acks Security by Default - TLS everywhere, no default credentials, proper isolation Observable Always - Monitor queue dept...
 316
6670 mqtt-development mindrally/skills
MQTT Development You are an expert in MQTT (Message Queuing Telemetry Transport) protocol development for IoT and real-time messaging systems. Follow these best practices when building MQTT-based applications. Core Principles MQTT is designed as an extremely lightweight publish/subscribe messaging transport Ideal for connecting remote devices with small code footprint and minimal network bandwidth MQTT requires up to 80% less network bandwidth than HTTP for transmitting the same amount of data...
 316
6671 vitest-testing existential-birds/beagle
Vitest Best Practices Quick Reference import { describe, it, expect, beforeEach, vi } from 'vitest' describe('feature name', () => { beforeEach(() => { vi.clearAllMocks() }) it('should do something specific', () => { expect(actual).toBe(expected) }) it.todo('planned test') it.skip('temporarily disabled') it.only('run only this during dev') }) Common Assertions // Equality expect(value).toBe(42) // Strict (===) expect(obj).toEqual({ a: 1 }) ...
 316
6672 qq-email shadowcz007/skills
何时使用 用户要使用 QQ 邮箱 发邮件 、 收邮件 、 查邮件 、 代发邮件 或 配置 QQ 邮箱 时使用本 skill。 QQ 邮箱收发 面向 QQ 邮箱：通过 IMAP 收取邮件、SMTP 发送邮件。账号与授权码 仅从环境变量读取 ，不在代码或配置中硬编码。 凭证（环境变量） 变量 说明 QQ_EMAIL_ACCOUNT QQ 邮箱账号（完整地址，如 xxx@qq.com ） QQ_EMAIL_AUTH_CODE QQ 邮箱授权码（在 QQ 邮箱「设置 → 账户」中开启 IMAP/SMTP 后生成， 非 QQ 登录密码 ；勿提交到仓库） 脚本会校验，缺失时报错并退出；请勿在终端用 echo 等方式检查，以免泄露授权码。 QQ 邮箱服务器 IMAP ： imap.qq.com ，端口 993（SSL） SMTP ： smtp.qq.com ，端口 465（SSL） 脚本 脚本 作用 scripts/send.js 从环境变量读凭证，用 nodemailer 连接 QQ 邮箱 SMTP 发信；支持收件人、主题、正文（CLI 参数）。 scripts/receive.js 从环境变量读...
 316
6673 openspec-archiving forztf/open-skilled-sdd
Archives completed change proposals and merges their spec deltas into the living specification documentation. Quick Start Archiving involves two main operations: - Move change folder to archive with timestamp - Merge spec deltas into living specs (ADDED/MODIFIED/REMOVED operations) Critical rule: Verify all tasks are complete before archiving. Archiving signifies deployment and completion. Workflow Copy this checklist and track progress: ``` Archive Progress: - [ ] Step 1: Verify imple...
 316
6674 tinybird-typescript-sdk-guidelines tinybirdco/tinybird-agent-skills
Tinybird TypeScript SDK Guidelines Guidance for using the @tinybirdco/sdk package to define Tinybird resources in TypeScript with complete type inference. When to Apply Installing or configuring @tinybirdco/sdk Defining datasources or pipes in TypeScript Creating typed Tinybird clients Using type-safe ingestion or queries Running tinybird dev/build/deploy commands for TypeScript projects Migrating from legacy .datasource/.pipe files to TypeScript Rule Files rules/getting-started.md rules/configu...
 316
6675 android-adb httprunner/skills
Android ADB Reference for controlling Android devices with raw adb commands. Execution Constraints Use adb -s <serial> whenever more than one device is connected. Confirm screen resolution before coordinate actions: adb -s SERIAL shell wm size . Ask for missing required inputs before executing (serial, package/activity, coordinates, APK path). Surface actionable stderr on failure (authorization, cable/network, tcpip state). Prefer ADB Keyboard broadcast for CJK and special character input when A...
 316
6676 browser-debugging aj-geddes/useful-ai-prompts
Browser Debugging Overview Browser debugging tools help identify and fix client-side issues including JavaScript errors, layout problems, and performance issues. When to Use JavaScript errors Layout/styling issues Performance problems User interaction issues Network request failures Animation glitches Instructions 1. Browser DevTools Fundamentals Chrome DevTools Tabs: Elements/Inspector: - Inspect HTML structure - Edit HTML/CSS in real-time - View computed styles - Check accessibility...
 316
6677 context-optimization sickn33/antigravity-awesome-skills
Context Optimization Techniques Context optimization extends the effective capacity of limited context windows through strategic compression, masking, caching, and partitioning. The goal is not to magically increase context windows but to make better use of available capacity. Effective optimization can double or triple effective context capacity without requiring larger models or longer contexts. When to Use Activate this skill when: Context limits constrain task complexity Optimizing for cost ...
 316
6678 context-engineering mrgoonie/claudekit-skills
Context Engineering Overview Feed agents the right information at the right time. Context is the single biggest lever for agent output quality — too little and the agent hallucinates, too much and it loses focus. Context engineering is the practice of deliberately curating what the agent sees, when it sees it, and how it's structured. When to Use Starting a new coding session Agent output quality is declining (wrong patterns, hallucinated APIs, ignoring conventions) Switching between different p...
 316
6679 link-checker webflow/webflow-skills
Audit and fix broken or insecure links across your Webflow site to improve SEO and user experience. Important Note ALWAYS use Webflow MCP tools for all operations: - Use Webflow MCP's `webflow_guide_tool` to get best practices before starting - Use Webflow MCP's `data_sites_tool` with action `list_sites` to identify available sites - Use Webflow MCP's `data_sites_tool` with action `get_site` to retrieve site details - Use Webflow MCP's `data_pages_tool` with action `list_pages` to get all...
 316
6680 dex-plan dcramer/dex
Converting Markdown Documents to Tasks Command Invocation Use dex directly for all commands: dex <command> If dex is not on PATH, use npx @zeeg/dex <command> instead. Check once at the start: command -v dex &>/dev/null && echo "use: dex" || echo "use: npx @zeeg/dex" Use /dex-plan to convert any markdown planning document into a trackable dex task. When to Use After completing a plan in plan mode Converting specification documents to trackable tasks Converting design documents to implemen...
 316
6681 zsxq-shared unnoo/zsxq-skill
zsxq-cli 共享规则 本技能指导你如何通过 zsxq-cli 操作知识星球资源，以及有哪些注意事项。 认证 zsxq-cli 使用 OAuth 2.0 设备授权码流程（RFC 8628） 认证，token 存储在系统 Keychain 中，永久有效。 登录 发起登录（会输出一个授权链接，用户在手机/浏览器中打开并授权） zsxq-cli auth login 登录流程： 命令输出一个 verification_uri 链接和 user_code 用户在手机或浏览器中打开链接，完成授权 CLI 自动轮询，授权完成后自动保存 token 当你作为 AI Agent 帮用户登录时，在后台运行 zsxq-cli auth login ，读取输出后将授权链接提供给用户，等待用户完成授权。 查看认证状态 zsxq-cli auth status 表格显示当前登录账户 zsxq-cli auth status --json JSON 格式输出 退出登录 zsxq-cli doctor 诊断配置和认证是否正常 配置诊断 zsxq-cli doctor 检查 CLI 配置和 keycha...
 316
6682 lynx-devtool lynx-community/skills
DevTool Skill This skill allows you to interact with Lynx applications running on connected devices (Android, iOS, Desktop) using the Lynx DevTool CLI. Usage The CLI is located at <path_to_the_skill>/scripts/index.mjs relative to this skill's directory. You can run it using node . In the skill directory, use: node < path_to_the_skill > /scripts/index.mjs < command > Note: All command outputs are multi-line JSON. You can use jq or Node.js to process the data. Global Options -h, --help : Display h...
 316
6683 tools-ui inference-sh/skills
Tool UI Components Tool lifecycle components from ui.inference.sh . Quick Start npx shadcn@latest add https://ui.inference.sh/r/tools.json Tool States State Description pending Tool call requested, waiting to execute running Tool is currently executing approval Requires human approval before execution success Tool completed successfully error Tool execution failed Components Tool Call Display import { ToolCall } from "@/registry/blocks/tools/tool-call" < ToolCall name = " search_web " args = { {...
 315
6684 tamagui tamagui/tamagui
Tamagui Skill Universal React UI framework for web and native with an optimizing compiler. Getting Project-Specific Config Before writing Tamagui code , get the project's actual configuration: npx tamagui generate-prompt This outputs tamagui-prompt.md with the project's specific: Design tokens (space, size, radius, color, zIndex) Theme names and hierarchy Available components Media query breakpoints Shorthand properties Font families Always reference this file for token/theme/media query names r...
 315
6685 ios-development rshankras/claude-code-apple-skills
iOS Development Expert Comprehensive guidance for iOS app development. This skill aggregates specialized modules for different aspects of iOS development. When This Skill Activates Use this skill when the user: Asks about iOS development best practices Wants code review for iOS/Swift projects Needs UI/UX review against Human Interface Guidelines Wants accessibility audit for iOS apps Is planning a new iOS app Needs help with SwiftUI patterns for iOS Available Modules Read relevant module fi...
 315
6686 code-review-checklist davila7/claude-code-templates
Code Review Checklist Overview Provide a systematic checklist for conducting thorough code reviews. This skill helps reviewers ensure code quality, catch bugs, identify security issues, and maintain consistency across the codebase. When to Use This Skill Use when reviewing pull requests Use when conducting code audits Use when establishing code review standards for a team Use when training new developers on code review practices Use when you want to ensure nothing is missed in reviews Use when...
 315
6687 nowait-reasoning-optimizer davila7/claude-code-templates
NOWAIT Reasoning Optimizer Implements the NOWAIT technique from the paper "Wait, We Don't Need to 'Wait'! Removing Thinking Tokens Improves Reasoning Efficiency" (Wang et al., 2025). Overview NOWAIT is a training-free inference-time intervention that suppresses self-reflection tokens (e.g., "Wait", "Hmm", "Alternatively") during generation, reducing chain-of-thought (CoT) trajectory length by 27-51% without compromising model utility. When to Use Deploying R1-style reasoning models with limi...
 315
6688 prompt-engineering-patterns sickn33/antigravity-awesome-skills
Prompt Engineering Patterns Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability. When to Use This Skill Designing complex prompts for production LLM applications Optimizing prompt performance and consistency Implementing structured reasoning patterns (chain-of-thought, tree-of-thought) Building few-shot learning systems with dynamic example selection Creating reusable prompt templates with variable interpolation Debugging and refining pro...
 315
6689 wds-docs wix/skills
WDS Documentation Navigator Docs path: node_modules/@wix/design-system/dist/docs/ CRITICAL: Never Read Entire Files Files are 200-900+ lines. Follow the staged discovery flow below. Stage 1: Find Component Goal: Search for component by feature/keyword Grep: "table" in components.md Grep: "form\|input\|validation" in components.md Grep: "modal\|dialog\|popup" in components.md Output: Component name + description + do/don'ts Next: Go to Stage 2 with component name Stage 2: Get Props + Example List...
 315
6690 launchdarkly-flag-create launchdarkly/agent-skills
LaunchDarkly Flag Create & Configure You're using a skill that will guide you through introducing a new feature flag into a codebase. Your job is to explore how flags are already used in this codebase, create the flag in LaunchDarkly in a way that fits, add the evaluation code matching existing patterns, and verify everything is wired up correctly. Prerequisites This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment. Required MCP tools: create-flag —...
 315
6691 gitnexus-refactoring abhigyanpatwari/gitnexus
Refactoring with GitNexus When to Use "Rename this function safely" "Extract this into a module" "Split this service" "Move this to a new file" Any task involving renaming, extracting, splitting, or restructuring code Workflow 1. gitnexus_impact({target: "X", direction: "upstream"}) → Map all dependents 2. gitnexus_query({query: "X"}) → Find execution flows involving X 3. gitnexus_context({name: "X"}) → See all incoming/outgoing refs 4. Plan ...
 315
6692 short-video-production vivy-yi/xiaohongshu-skills
Short Video Production (短视频制作) Overview Short video production is the art and science of creating engaging 15-60 second vertical videos optimized specifically for Xiaohongshu's mobile-first, algorithm-driven platform. This skill encompasses the complete workflow from concept through filming, editing, and optimization—combining compelling storytelling, visual appeal, rapid pacing, and concise delivery to capture viewer attention within milliseconds and retain it through completion. The core princ...
 315
6693 grepai-storage-postgres yoanbernabeu/grepai-skills
This skill covers using PostgreSQL with the pgvector extension as the storage backend for GrepAI. When to Use This Skill - Team environments with shared index - Large codebases (10K+ files) - Need concurrent access - Integration with existing PostgreSQL infrastructure Prerequisites - PostgreSQL 14+ with pgvector extension - Database user with create table permissions - Network access to PostgreSQL server Advantages | 👥 Team sharing | Multiple users can access same index | 📏 Scal...
 315
6694 cfo-advisor borghei/claude-skills
CFO Advisor Financial leadership advisory for Chief Financial Officers. Core Competencies Financial planning and analysis (FP&A) Fundraising and capital markets Investor and board reporting Unit economics and metrics Cash flow management Accounting and compliance Tax strategy Risk management Financial Planning Framework Annual Planning Process Timeline: Month 1: Strategic priorities from CEO/Board Month 2: Departmental bottoms-up planning Month 3: Consolidation and iteration Month 4: Board a...
 315
6695 flask-python mindrally/skills
Flask Python Development You are an expert in Flask and Python web development. Follow these guidelines when writing Flask code. Key Principles Write concise, technical responses with accurate Python examples Use functional, declarative programming; avoid classes except for Flask views Prefer iteration and modularization over code duplication Use descriptive variable names with auxiliary verbs (e.g., is_active, has_permission) Use lowercase with underscores for directories and files (e.g., blu...
 315
6696 skills-updater yizhiyanhua-ai/skills-updater
Skills Updater Manage, update, and discover Claude Code skills across multiple installation sources. Internationalization (i18n) All scripts automatically detect user locale from environment variables and display output in the appropriate language. Supported Languages: English (en) - Default Chinese (zh) - 中文 Auto-detection order: LANG environment variable LC_ALL environment variable LANGUAGE environment variable System locale Manual override: python scripts/check_updates.py --lang zh ...
 315
6697 database-schema-documentation aj-geddes/useful-ai-prompts
Database Schema Documentation Overview Create comprehensive database schema documentation including entity relationship diagrams (ERD), table definitions, indexes, constraints, and data dictionaries. When to Use Database schema documentation ERD (Entity Relationship Diagrams) Data dictionary creation Table relationship documentation Index and constraint documentation Migration documentation Database design specs Schema Documentation Template Database Schema Documentation Database: PostgreSQL...
 315
6698 router-act vercel/next.js
Router Act Testing Use this skill when writing or modifying tests that involve prefetch requests, client router navigations, or the segment cache. The createRouterAct utility from test/lib/router-act.ts lets you assert on prefetch and navigation responses in an end-to-end way without coupling to the exact number of requests or the protocol details. This is why most client router-related tests use this pattern. When NOT to Use act Don't bother with act if you don't need to instrument the network ...
 315
6699 zsxq-group unnoo/zsxq-skill
group (v1) CRITICAL — 开始前 MUST 先用 Read 工具读取 ../zsxq-shared/SKILL.md ，其中包含认证、错误处理规则。 Core Concepts 星球（Group） ：知识星球的社群单元，由 group_id （纯数字）唯一标识。用户可以是创建者（owner）或成员（member）。 主题（Topic） ：星球内的内容单元，包括帖子（talk）、提问（q&a）、文章（article）等，由 topic_id 唯一标识。 标签（Hashtag） ：星球内的分类标签，由 hashtag_id 标识，可附加到主题上。 Resource Relationships Group (group_id) ├── Topic (topic_id) — talk / q&a / article │ ├── Comment (comment_id) │ └── Hashtag 标签 └── Hashtag (hashtag_id) └── Topic 列表 Shortcuts（推荐优先使用） Shortcut 是对常用操作的高级封装（ zsxq-c...
 315
6700 math-olympiad anthropics/claude-plugins-official
Math Olympiad Solver The five things that change outcomes Strip thinking before verifying — a verifier that sees the reasoning is biased toward agreement. Fresh context, cleaned proof only. "Does this prove RH?" — if your theorem's specialization to ζ is a famous open problem, you have a gap. Most reliable red flag. Short proof → extract the general lemma — try 2×2 counterexamples. If general form is false, find what's special about THIS instance. Same gap twice → step back — the case split may ...
 315