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...
27,776
总 Skills
171.6M
总安装量
2,753
贡献者
# Skill 仓库 描述 安装量
17201 idea-validator shipshitdev/library
Validate — Pressure-Test the Idea This skill pressure-tests a product idea before the founder invests in planning, building, or launching. It surfaces fatal flaws, tests whether the problem is real, maps actual competition (including current behavior), defines the smallest 2-week MVP test, and returns a direct strong / weak / pivot verdict. The Idea Validator sits between the Idea Generator and Product Planner skills in the BuilderOS pipeline. It also runs fully standalone — if no docs/product-i...
 93
17202 next-cache-components vercel/next.js
Cache Components (Next.js 16+) Cache Components enable Partial Prerendering (PPR) - mix static, cached, and dynamic content in a single route. Enable Cache Components // next.config.ts import type { NextConfig } from 'next' const nextConfig: NextConfig = { cacheComponents: true, } export default nextConfig This replaces the old experimental.ppr flag. Three Content Types With Cache Components enabled, content falls into three categories: 1. Static (Auto-Prerendered) Synchronous code, ...
 93
17203 email-triage casper-studios/casper-marketplace
Email Triage You are an email triage system. Your job is to process a user's inbox and, for each message, make four decisions: Pre-filter — Is this an automated calendar notification that can be silently skipped? Respond? — Does the latest message require the user to personally write a reply? Important? — Does this email contribute to the user's goals, relationships, or business outcomes? Urgent? — Does this email require action soon or have a time-sensitive deadline? For emails that need a resp...
 93
17204 mystery-novel-conventions wordflowlab/novel-writer-skills
悬疑推理小说创作规范 快速参考 元素 指导原则 位置 触发事件 案件/谜团发生 前 10% 误导线索 错误的引导 贯穿全文，3-5 个 真实线索 公平游戏的证据 75% 之前 真相揭露 真相揭示 85-95% 收尾 结束所有线索 最后 5% 核心原则 公平游戏原则 黄金法则：读者必须在侦探之前获得所有解决谜团所需的线索。 没有隐藏信息 所有关键线索都必须呈现给读者 侦探不能基于读者不知道的信息破案 只在结尾揭示的秘密证据违反公平游戏 逻辑推理 解决方案必须能从呈现的事实中逻辑推导 巧合可以使情况复杂化，但永远不能解决 直觉可以，但必须基于已展示的证据 不使用机械降神 不能突然出现新角色作为罪犯 不能有之前未提及的能力或工具 不能有神的干预或纯粹的运气 悬疑小说结构 第一幕：铺垫（0-25%） 建立常态世界： 介绍主角和他们的世界 展示角色能力 埋下性格怪癖的种子 案件发生： 在前 10% 发生 必须足够有趣/不寻常以证明调查的必要性 风险应该清晰 初步调查： 主角接受案件 首次访谈和证据收集 建立关键嫌疑人 第二幕：调查（25-75%） 收集线索： 呈现所...
 93
17205 performance optimizer daffy0208/ai-dev-standards
Performance Optimizer Make applications fast, scalable, and cost-efficient. Core Principle Measure first, optimize second. Don't guess at bottlenecks—profile, measure, then fix the slowest parts. Performance Budget Web Vitals (Target Metrics) Core Web Vitals : Largest Contentful Paint (LCP) : < 2.5s Main content visible First Input Delay (FID) : < 100ms Interaction responsiveness Cumulative Layout Shift (CLS) : < 0.1 Visual stability Additional Metrics : First Contentful Paint (FCP) : < 1.8s ...
 93
17206 meeting-followup casper-studios/casper-marketplace
Meeting Follow-Up This skill turns a Fireflies meeting transcript into a structured summary and a ready-to-send Gmail draft addressed to all attendees. The goal is to close the loop on meetings fast — the user should be able to say "process my meeting with Acme" and get a polished follow-up draft in their inbox within a couple of minutes. Workflow Step 1: Find the meeting The user will reference a meeting by name, topic, or participants. Use the Fireflies search and transcript tools to locate it...
 93
17207 weekly-report yunshu0909/yunshu_skillshub
Weekly Report Overview This skill helps you create consistent, well-structured weekly status reports that communicate progress, blockers, and plans effectively to your team, manager, or stakeholders. Use Cases: Individual contributor status updates Team lead rollup reports Project status updates Executive summaries Client progress reports How to Use Tell me what you accomplished this week Share any blockers or challenges Describe your plans for next week Specify your audience (manager, team, exe...
 93
17208 shader-effects bbeierle12/skill-mcp-claude
Shader Effects Visual effects that add polish, style, and atmosphere to shader output. Quick Start // Combine multiple effects vec3 color = baseColor; color = applyVignette(color, uv, 0.5); color = applyGrain(color, uv, uTime, 0.1); color = applyChromaticAberration(color, uv, 0.005); Glow / Bloom Simple Glow // Distance-based glow float glow(float d, float radius, float intensity) { return pow(radius / max(d, 0.001), intensity); } // Usage float d = sdCircle(uv, 0.2); vec3 color = vec3(glo...
 93
17209 mcp-cli obra/superpowers-lab
MCP-CLI Access MCP servers through the command line. MCP enables interaction with external systems like GitHub, filesystems, databases, and APIs. Commands Command Output mcp-cli List all servers and tool names mcp-cli <server> Show tools with parameters mcp-cli <server>/<tool> Get tool JSON schema mcp-cli <server>/<tool> '<json>' Call tool with arguments mcp-cli grep "<glob>" Search tools by name Add -d to include descriptions (e.g., mcp-cli filesystem -d) Workflow Discover: mcp-cli → see av...
 93
17210 tax-invoice-credit-context kazukinagata/shinkoku
インボイス仕入税額控除コンテキスト（Input Tax Credit Context） このスキルはインボイス制度における仕入税額控除の要件・例外に関するコンテキストを提供する。 仕入税額控除の情報提供 仕入税額控除に関する回答を行う際は、 references/input-tax-credit-rules.md を読み込んで以下を実行する: 原則（適格請求書＋帳簿の保存）を確認して案内する 帳簿のみ保存の恒久特例6類型（公共交通機関・自販機・郵便等）への該当を確認する 免税事業者からの仕入れに係る経過措置の控除率（80%→70%→50%→30%→0%）を案内する 課税売上割合に応じた控除方式（全額控除・個別対応方式・一括比例配分方式）を説明する 保存期間（7年間）と電子取引データ保存の要件を案内する 参照ファイル ファイル 内容 references/input-tax-credit-rules.md 仕入税額控除の原則・帳簿記載要件・恒久特例6類型・経過措置・課税売上割合と控除方式
 93
17211 reporting-pipelines bobmatnyc/claude-mpm-skills
Reporting Pipelines Overview Your reporting pattern is consistent across repos: run a CLI or script that emits structured data, then export CSV/JSON/markdown reports with timestamped filenames into reports/ or tests/results/. GitFlow Analytics Pattern Basic run gitflow-analytics -c config.yaml --weeks 8 --output ./reports Explicit analyze + CSV gitflow-analytics analyze -c config.yaml --weeks 12 --output ./reports --generate-csv Outputs include CSV + markdown narrative reports with date s...
 93
17212 docx iofficeai/aionui
DOCX creation, editing, and analysis Overview A .docx file is a ZIP archive containing XML files. Quick Reference Task Approach Read/analyze content pandoc or unpack for raw XML Create new document Use docx-js - see Creating New Documents below Edit existing document Unpack → edit XML → repack - see Editing Existing Documents below Converting .doc to .docx Legacy .doc files must be converted before editing: python scripts/office/soffice.py --headless --convert-to docx document.doc Reading Conten...
 93
17213 pulumi-typescript dirien/claude-skills
Project structure: ``` my-project/ ├── Pulumi.yaml ├── Pulumi.dev.yaml Stack config (use ESC instead) ├── package.json ├── tsconfig.json └── index.ts ``` 2. Pulumi ESC Integration Instead of using `pulumi config set` or stack config files, use Pulumi ESC for centralized secrets and configuration. Link ESC environment to stack: ``` Create ESC environment pulumi env init myorg/myproject-dev Edit environment pulumi env edit myorg/myproject-dev Link to Pulumi stack pulumi config en...
 93
17214 context-driven-development sickn33/antigravity-awesome-skills
Context-Driven Development Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structured project documentation. When to Use This Skill Setting up new projects with Conductor Understanding the relationship between context artifacts Maintaining consistency across AI-assisted development sessions Onboarding team members to an existing Conductor project Deciding when to update context documents Managing ...
 93
17215 zustand pproenca/dot-skills
LobeHub Zustand State Management Action Type Hierarchy 1. Public Actions Main interfaces for UI components: Naming: Verb form ( createTopic , sendMessage ) Responsibilities: Parameter validation, flow orchestration 2. Internal Actions ( internal_* ) Core business logic implementation: Naming: internal_ prefix ( internal_createTopic ) Responsibilities: Optimistic updates, service calls, error handling Should not be called directly by UI 3. Dispatch Methods ( internal_dispatch* ) State update hand...
 93
17216 axiom-realitykit-ref charleswiltgen/axiom
RealityKit API Reference Complete API reference for RealityKit organized by category. When to Use This Reference Use this reference when: Looking up specific RealityKit API signatures or properties Checking which component types are available Finding the right anchor type for an AR experience Browsing material properties and options Setting up physics body parameters Looking up animation or audio API details Checking platform availability for specific APIs Part 1: Entity API Entity // Creation l...
 93
17217 vector-index-tuning sickn33/antigravity-awesome-skills
Vector Index Tuning Guide to optimizing vector indexes for production performance. When to Use This Skill Tuning HNSW parameters Implementing quantization Optimizing memory usage Reducing search latency Balancing recall vs speed Scaling to billions of vectors Core Concepts 1. Index Type Selection Data Size Recommended Index ──────────────────────────────────────── < 10K vectors → Flat (exact search) 10K - 1M → HNSW 1M - 100M → HNSW + Quantization > 100M →...
 93
17218 executive-dashboard-generator onewave-ai/claude-skills
Executive Dashboard Generator Turn raw data into executive-ready insights with visualizations and recommendations. Instructions You are an expert data analyst and business intelligence specialist who transforms raw data into compelling executive narratives. Your mission is to take complex datasets and distill them into clear, actionable insights that drive decision-making at the highest levels. Core Capabilities Data Input Handling: CSV files (single or multiple) Excel spreadsheets (.xlsx,...
 93
17219 jj-workflow trevors/dot-claude
jj Workflow CRITICAL: Avoid Interactive Mode Always use -m flag to prevent jj from opening an editor: WRONG - opens editor, blocks AI jj new jj describe jj squash CORRECT - non-interactive jj new -m "message" jj describe -m "message" jj squash -m "message" Never use these interactive commands: jj split - inherently interactive, no non-interactive mode Mental Model No staging area. Your working directory is always a commit. Every save is tracked. @ = your current change (the working cop...
 93
17220 github-automation composiohq/awesome-claude-skills
GitHub Automation Skill Purpose GitHub workflow automation, PR management, and repository coordination. When to Trigger Creating pull requests Managing issues Setting up CI/CD workflows Code review automation Release management Commands Create Pull Request gh pr create --title "feat: description" --body " Summary \n ..." Review Code npx claude-flow github review --pr 123 Manage Issues npx claude-flow github issues list --state open npx claude-flow github issues create --title "Bug: ..." Setup Wo...
 93
17221 tooluniverse-install-skills mims-harvard/tooluniverse
ToolUniverse Install Skills Checks whether the ToolUniverse specialized skills are installed and installs them automatically if not. Detection Use the Shell tool to check for the canary file across all common client locations: ls .cursor/skills/tooluniverse-drug-research/SKILL.md 2 > /dev/null \ || ls .agents/skills/tooluniverse-drug-research/SKILL.md 2 > /dev/null \ || ls .windsurf/skills/tooluniverse-drug-research/SKILL.md 2 > /dev/null \ || ls .gemini/skills/tooluniverse-drug-research/SKILL.m...
 93
17222 service-mesh-expert sickn33/antigravity-awesome-skills
Service Mesh Expert Expert service mesh architect specializing in Istio, Linkerd, and cloud-native networking patterns. Masters traffic management, security policies, observability integration, and multi-cluster mesh configurations. Use PROACTIVELY for service mesh architecture, zero-trust networking, or microservices communication patterns. Do not use this skill when The task is unrelated to service mesh expert You need a different domain or tool outside this scope Instructions Clarify goals, c...
 92
17223 remotion-best-practices freestylefly/canghe-skills
When to use Use this skills whenever you are dealing with Remotion code to obtain the domain-specific knowledge. Captions When dealing with captions or subtitles, load the ./rules/subtitles.md file for more information. Using FFmpeg For some video operations, such as trimming videos or detecting silence, FFmpeg should be used. Load the ./rules/ffmpeg.md file for more information. Audio visualization When needing to visualize audio (spectrum bars, waveforms, bass-reactive effects), load the ./rul...
 92
17224 hft-quant-expert kasyap1234/delta-go
HFT Quant Expert Quantitative trading expertise for DeFi and crypto derivatives. When to Use Building trading strategies and signals Implementing risk management Calculating position sizes Backtesting strategies Analyzing volatility and correlations Workflow Step 1: Define Signal Calculate z-score or other entry signal. Step 2: Size Position Use Kelly Criterion (0.25x) for position sizing. Step 3: Validate Backtest Check for lookahead bias, survivorship bias, overfitting. Step 4: Account for Cos...
 92
17225 openserv-agent-sdk openserv-labs/skills
OpenServ Agent SDK Build and deploy custom AI agents for the OpenServ platform using TypeScript. Why build an agent? An OpenServ agent is a service that runs your code and exposes it on the OpenServ platform—so it can be triggered by workflows, other agents, or paid calls (e.g. x402). The platform sends tasks to your agent; your agent runs your capabilities (APIs, tools, file handling) and returns results. You don't have to use an LLM—e.g. it could be a static API that just returns data. If you ...
 92
17226 ens-primary-name bankrbot/openclaw-skills
ENS Primary Name Set your primary ENS name on Base and other L2 chains via the ENS Reverse Registrar. A primary name creates a bi-directional link: Forward: name.eth → 0x1234... (set in ENS resolver) Reverse: 0x1234... → name.eth (set via this skill) Requirements Required: Transaction Signing This skill requires a way to sign and submit transactions. It looks for the bankr skill which provides wallet functionality via the Bankr API. If you don't have bankr installed: Install from: https://github...
 92
17227 paypal-integration sickn33/antigravity-awesome-skills
PayPal Integration Master PayPal payment integration including Express Checkout, IPN handling, recurring billing, and refund workflows. When to Use This Skill Integrating PayPal as a payment option Implementing express checkout flows Setting up recurring billing with PayPal Processing refunds and payment disputes Handling PayPal webhooks (IPN) Supporting international payments Implementing PayPal subscriptions Core Concepts 1. Payment Products PayPal Checkout One-time payments Express checko...
 92
17228 java-best-practices leavesfly/jimi
单例模式（枚举实现）： ``` public enum Singleton { INSTANCE; public void doSomething() {} } ``` 工厂模式： ``` public class UserFactory { public static User createUser(String type) { return switch (type) { case "admin" -> new AdminUser(); case "guest" -> new GuestUser(); default -> new RegularUser(); }; } } ``` Builder 模式： ``` User user = User.builder() .name("张三") .age(25) .build(); ``` Stream API ``` List<String> names ...
 92
17229 multi-cloud-architecture sickn33/antigravity-awesome-skills
Multi-Cloud Architecture Decision framework and patterns for architecting applications across AWS, Azure, and GCP. Purpose Design cloud-agnostic architectures and make informed decisions about service selection across cloud providers. When to Use Design multi-cloud strategies Migrate between cloud providers Select cloud services for specific workloads Implement cloud-agnostic architectures Optimize costs across providers Cloud Service Comparison Compute Services AWS Azure GCP Use Case EC2 Vi...
 92
17230 ai-models alinaqi/claude-bootstrap
AI Models Reference Skill Load with: base.md + llm-patterns.md Last Updated: December 2025 Philosophy Use the right model for the job. Bigger isn't always better - match model capabilities to task requirements. Consider cost, latency, and accuracy tradeoffs. Model Selection Matrix Task Recommended Why Complex reasoning Claude Opus 4.5, o3, Gemini 3 Pro Highest accuracy Fast chat/completion Claude Haiku, GPT-4.1 mini, Gemini Flash Low latency, cheap Code generation Claude Sonnet 4.5, Codestr...
 92
17231 meta-cognitive-reasoning 89jobrien/steve
This skill provides disciplined reasoning frameworks for avoiding cognitive failures in analysis, reviews, and decision-making. It enforces evidence-based conclusions, multiple hypothesis generation, and systematic verification. When to Use This Skill - Before making claims about code, systems, or versions - When conducting code reviews or architectural assessments - When debugging issues with multiple possible causes - When encountering unfamiliar patterns or versions - When making recom...
 92
17232 cli tambo-ai/tambo
Tambo CLI Agent-friendly CLI for project setup and component management. Quick Start npx tambo init --api-key = sk_ .. . Initialize with API key npx tambo add message-thread-full --yes Add a component npx tambo create-app my-app --template = standard New app from template Non-Interactive Mode The CLI detects non-interactive environments and returns guidance instead of hanging: In CI or piped environments, this returns guidance (exit 2) instead of prompting npx tambo init Error: Project name...
 92
17233 cli-design joelhooks/joelclaw
Agent-First CLI Design CLIs in this system are agent-first, human-distant-second . Every command returns structured JSON that an agent can parse, act on, and follow. Humans are welcome to pipe through jq . Core Principles 1. JSON always Every command returns JSON. No plain text. No tables. No color codes. Agents parse JSON; they don't parse prose. This is the ONLY output format joelclaw status → { "ok": true, "command": "joelclaw status", "result": {...}, "next_actions": [...] } No --json flag...
 92
17234 code-comments petekp/claude-code-setup
Write documentation that lives with the code it describes. Plain language. No jargon. Explain the *why*, not the *what*. Core Philosophy Co-location wins. Documentation in separate files drifts out of sync. Comments next to code stay accurate because they're updated together. Write for three audiences: - Future you, six months from now - Teammates reading unfamiliar code - AI assistants (Claude, Copilot) who see one file at a time The "why" test: Before writing a comment, ask: "Does this...
 92
17235 internal-comms aiskillstore/marketplace
When to use this skill To write internal communications, use this skill for: 3P updates (Progress, Plans, Problems) Company newsletters FAQ responses Status reports Leadership updates Project updates Incident reports How to use this skill To write any internal communication: Identify the communication type from the request Load the appropriate guideline file from the examples/ directory: examples/3p-updates.md - For Progress/Plans/Problems team updates examples/company-newsletter.md - For compan...
 92
17236 jadx brownfinesecurity/iothackbot
Jadx - Android APK Decompiler You are helping the user decompile Android APK files using jadx to convert DEX bytecode into readable Java source code for security analysis, vulnerability discovery, and understanding app internals. Tool Overview Jadx is a dex to Java decompiler that produces clean, readable Java source code from Android APK files. Unlike apktool (which produces smali), jadx generates actual Java code that's much easier to read and analyze. It's essential for: Converting DEX byteco...
 92
17237 clean-architecture-php giuseppe-trisciuoglio/developer-kit
Clean Architecture, Hexagonal Architecture & DDD for PHP/Symfony Overview This skill provides guidance for implementing Clean Architecture, Hexagonal Architecture (Ports & Adapters), and Domain-Driven Design patterns in PHP 8.3+ applications using Symfony 7.x. It ensures clear separation of concerns, framework-independent business logic, and highly testable code through layered architecture with inward-only dependencies. When to Use Architecting new enterprise PHP applications with Symfony 7.x R...
 92
17238 toutiao-news-trends wuchubuzai2018/expert-skills-hub
今日头条新闻热榜 技能概述 此技能用于抓取今日头条 PC 端热榜（hot-board）数据，包括： 热点标题 热度值（HotValue） 详情跳转链接（去除冗余查询参数，便于分享） 封面图（如有） 标签（如“热门事件”等） 数据来源：今日头条 ( www.toutiao.com ) 获取热榜 获取热榜（默认 50 条，按榜单顺序返回）： node scripts/toutiao.js hot 获取热榜前 N 条： node scripts/toutiao.js hot 10 返回数据字段说明 字段 类型 说明 rank number 榜单排名（从 1 开始） title string 热点标题 popularity number 热度值（HotValue，已转为数字；解析失败时为 0） link string 热点详情链接（已清理 query/hash） cover string | null 封面图 URL（如有） label string | null 标签/标识（如有） clusterId string 聚合 ID（字符串化） categories string[] 兴趣分类（如...
 92
17239 email-template-generator onewave-ai/claude-skills
Email Template Generator Generate professional, effective email templates for any business scenario. Instructions When a user requests an email template or needs help writing business emails: Identify Email Type: Sales/Cold outreach Customer support response Follow-up email Apology/service recovery Internal team communication Meeting request Thank you note Rejection/decline Gather Context: What is the purpose of this email? Who is the recipient (role, relationship)? What action do you wan...
 92
17240 framework-migration-deps-upgrade sickn33/antigravity-awesome-skills
Dependency Upgrade Strategy You are a dependency management expert specializing in safe, incremental upgrades of project dependencies. Plan and execute dependency updates with minimal risk, proper testing, and clear migration paths for breaking changes. Use this skill when Working on dependency upgrade strategy tasks or workflows Needing guidance, best practices, or checklists for dependency upgrade strategy Do not use this skill when The task is unrelated to dependency upgrade strategy You need...
 92
17241 bun-test daleseo/bun-skills
Bun Test Configuration Set up Bun's built-in test runner with Jest-compatible APIs and significantly faster execution (3-10x faster than Jest). Quick Reference For detailed patterns, see: Jest Migration: jest-migration.md - Complete Jest to Bun migration guide Mocking: mocking.md - Mock functions, spies, module mocking Examples: examples.md - Test patterns for APIs, databases, async code Core Workflow 1. Check Prerequisites Verify Bun installation bun --version Check if project exists ls ...
 92
17242 ollama rawveg/skillsforge-marketplace
Comprehensive assistance with Ollama development - the local AI model runtime for running and interacting with large language models programmatically. When to Use This Skill This skill should be triggered when: - Running local AI models with Ollama - Building applications that interact with Ollama's API - Implementing chat completions, embeddings, or streaming responses - Setting up Ollama authentication or cloud models - Configuring Ollama server (environment variables, ports, proxies) ...
 92
17243 tonejs plyght/tonejs-skill
Tone.js Skill Build interactive music applications in the browser using the Web Audio API through Tone.js's high-level abstractions. When to Use This Skill Use Tone.js when: Creating synthesizers, samplers, or musical instruments Building step sequencers, drum machines, or DAWs Adding sound effects or music to games Implementing audio visualizations synchronized to sound Processing audio in real-time with effects Scheduling musical events with precise timing Working with musical concepts (no...
 92
17244 template-skill aiskillstore/marketplace
Insert instructions below
 92
17245 test-quality-inspector bobmatnyc/claude-mpm-skills
Example Test Inspection Report Scenario: User Registration Feature Engineer's Test Suite test_user_registration.py def test_user_creation(): """Test user creation""" user = create_user("test@example.com", "password123") assert user def test_login(): """Test login""" user = create_user("test@example.com", "password123") result = login("test@example.com", "password123") assert result def test_duplicate_email(): """Test duplicate email""" create_user("test@ex...
 92
17246 api designer daffy0208/ai-dev-standards
API Designer Design robust, scalable, and developer-friendly APIs. Core Principles 1. Developer Experience First Clear, predictable naming conventions Comprehensive documentation Helpful error messages Consistent patterns across endpoints 2. Design for Evolution Versioning strategy from day one Backward compatibility Deprecation process Migration guides for breaking changes 3. Security by Default Authentication and authorization Rate limiting and throttling Input validation and sanitization HTTP...
 92
17247 zapper bankrbot/openclaw-skills
No SKILL.md available for this skill. View on GitHub
 92
17248 strapi-expert ayhid/claude-skill-strapi-expert
Strapi v5 Expert You are an expert Strapi v5 developer specializing in plugin development, custom APIs, and CMS architecture. Your mission is to write production-grade Strapi v5 code following official conventions and best practices. Core Mandate: Document Service API First In Strapi v5, always use the Document Service API ( strapi.documents ) for all data operations. The Entity Service API from v4 is deprecated. Document Service vs Entity Service Operation Document Service (v5) Entity Service (...
 92
17249 videocut-subtitle zrt-ai-lab/opencode-skills
字幕 转录 → 纠错 → 审核 → 匹配 → 烧录 流程 1. 转录视频（Whisper） ↓ 2. 词典纠错 + 分句 ↓ 3. 输出字幕稿（纯文本，一句一行） ↓ 【用户审核修改】 ↓ 4. 用户给回修改后的文本 ↓ 5. 我匹配时间戳 → 生成 SRT ↓ 6. 烧录字幕（FFmpeg） 转录 使用 OpenAI Whisper 模型进行语音转文字： whisper video.mp4 --model medium --language zh --output_format json 模型 用途 medium 默认，平衡速度与准确率 large-v3 高精度，较慢 输出 JSON 包含逐词时间戳，用于后续 SRT 生成。 字幕规范 规则 说明 一屏一行 不换行，不堆叠 ≤15字/行 超过15字必须拆分（4:3竖屏） 句尾无标点 你好 不是 你好。 句中保留标点 先点这里，再点那里 词典纠错 读取 词典.txt ，每行一个正确写法： skills Claude iPhone 我自动识别变体： claude → Claude 字幕稿格式 我给用户的 （纯文本，≤15字/行）： 今天给...
 92
17250 ln-003-push-all levnikolaevich/claude-code-skills
Paths: File paths ( shared/ , references/ , ../ln-* ) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Push All (Standalone Utility) Type: Standalone Utility Category: 0XX Shared Commits and pushes ALL current changes (staged, unstaged, untracked) to the remote repository in a single operation. When to Use This Skill Quick push of all accumulated changes without manual staging End-of-session commit when all changes are ready...
 92