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...
27,919
总 Skills
176.5M
总安装量
2,757
贡献者
# Skill 仓库 描述 安装量
20551 swain-update cristoslc/swain
Update Swain Update the local installation of swain skills to the latest version, then reconcile governance configuration. Step 1 — Detect current installation Check whether .claude/skills/ contains any swain-* directories: ls -d .claude/skills/swain-* 2 > /dev/null If no swain skill directories are found, inform the user this appears to be a fresh install rather than an update, then continue anyway — the steps below work for both cases. Step 2 — Backup local modifications Before overwriting ski...
 59
20552 mod-actions civitai/civitai
Take moderator actions on Civitai users including banning, muting, removing content, and managing leaderboard eligibility. This skill uses the Civitai tRPC API with API key authentication, ensuring all actions go through the proper service layer with full side effects (session invalidation, search index updates, activity tracking, etc.). Setup - Copy `.env-example` to `.env` in this skill directory - Add your Civitai API key (must belong to a moderator account) - Optionally set the API URL...
 59
20553 delayed-command paulrberg/agent-skills
Delayed Command Execution Wait for a specified duration, then execute a Bash command. Arguments duration : Time to wait before execution (e.g., 30s , 5m , 1h , 1h30m ) command : The Bash command to run after the delay Duration Format Format Example Meaning Xs 30s 30 seconds Xm 5m 5 minutes Xh 1h 1 hour XhYm 1h30m 1 hour 30 minutes XhYmZs 1h5m30s 1 hour 5 min 30 s Workflow 1. Parse Duration Convert the duration argument to seconds: Extract hours ( h ), minutes ( m ), and seconds ( s ) components ...
 59
20554 tdd oimiragieo/agent-studio
Test-Driven Development Philosophy Core principle : Tests should verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't. Good tests are integration-style: they exercise real code paths through public APIs. They describe what the system does, not how it does it. A good test reads like a specification - "user can checkout with valid cart" tells you exactly what capability exists. These tests survive refactors because they don't care about i...
 59
20555 webreel vercel-labs/webreel
webreel webreel records scripted browser demos as MP4, GIF, or WebM with cursor animation, keystroke overlays, and sound effects. You define steps in a JSON config, and webreel drives headless Chrome, captures frames, and encodes with ffmpeg. Installation Install webreel as a project dependency so the version is pinned in the lockfile. This ensures deterministic recordings across machines and CI. npm install webreel If the project already has webreel in its dependencies, skip this step. Prerequi...
 59
20556 wiki-researcher sickn33/antigravity-awesome-skills
Wiki Researcher You are an expert software engineer and systems analyst. Your job is to deeply understand codebases, tracing actual code paths and grounding every claim in evidence. When to Activate User asks "how does X work" with expectation of depth User wants to understand a complex system spanning many files User asks for architectural analysis or pattern investigation Core Invariants (NON-NEGOTIABLE) Depth Before Breadth TRACE ACTUAL CODE PATHS — not guess from file names or conventions RE...
 59
20557 dust-mcp-server dust-tt/dust
@runbooks/NEW_MCP_SERVER.md
 59
20558 umbraco-auth-provider umbraco/umbraco-cms-backoffice-skills
Umbraco Auth Provider What is it? An Auth Provider enables external login (OAuth/SSO) for the Umbraco backoffice. It provides the UI component (login button) that connects to a backend authentication provider. The backend must be configured separately in C - this extension type handles the frontend presentation and behavior. Common providers include Google, Microsoft, GitHub, and custom OAuth providers. Documentation Always fetch the latest docs before implementing: External Login Providers : ht...
 59
20559 dependency-analyzer oimiragieo/agent-studio
Dependency Analyzer Skill Step 1: Identify Dependency Files Locate dependency files: package.json (Node.js) requirements.txt (Python) go.mod (Go) Cargo.toml (Rust) pom.xml (Java/Maven) Step 2: Analyze Dependencies Examine dependencies: Read dependency files Check versions Identify outdated packages Note version constraints Step 3: Semantic Versioning Analysis Analyze version numbers using semantic versioning (semver): Parse version numbers: Extract major.minor.patch from version strings H...
 59
20560 dojo-deploy dojoengine/book
Dojo Deployment Deploy your Dojo world to local Katana sequencer, Sepolia testnet, or Starknet mainnet. When to Use This Skill "Deploy my world to Katana" "Start Katana sequencer" "Deploy to Sepolia testnet" "Deploy to mainnet" What This Skill Does Handles deployment workflows: Start and configure Katana sequencer Deploy worlds with sozo migrate Verify deployments Manage world addresses Configure network settings Quick Start Local development: "Start Katana and deploy my world" Testnet deploymen...
 59
20561 godot-navigation-pathfinding thedivergentai/gd-agentic-skills
Navigation & Pathfinding NavigationServer-powered pathfinding with avoidance and dynamic obstacles define robust AI movement. Available Scripts dynamic_nav_manager.gd Expert runtime navigation mesh updates for moving platforms. NEVER Do in Navigation & Pathfinding NEVER set target_position before awaiting physics frame — NavigationServer not ready in _ready() ? Path fails silently. MUST call_deferred() then await get_tree().physics_frame . NEVER use NavigationRegion2D.bake_navigation_polygon() a...
 59
20562 remotion-video-reviewer ncklrs/startup-os-skills
Remotion Video Reviewer Provides comprehensive, structured reviews of Remotion video implementations against motion design specifications. Identifies issues, assesses impact, and generates actionable revision lists. What This Skill Does Performs multi-layer review analysis: Spec compliance — Verifies implementation matches design spec Code quality — Checks patterns, performance, best practices Timing accuracy — Validates frame calculations and animation timing Visual fidelity — Confirms colors, ...
 59
20563 education-learning dylantarre/animation-principles
Education & Learning Animation Principles Apply Disney's 12 principles to create engaging, encouraging experiences that support comprehension and celebrate progress. The 12 Principles Applied 1. Squash & Stretch Answer Buttons: Friendly squash on selection Mascots/Characters: Personality through stretch Achievement Badges: Bounce with character 2. Anticipation Quiz Reveal: Build-up before showing results Next Lesson: Preparation for new content Submit Answer: Moment before feedback 3. Staging ...
 59
20564 controller-sessions cartridge-gg/docs
Controller Sessions & Policies Session policies define which contracts and methods your app can call. They are required for session-based transaction execution — without policies, execute() will fail with error code 130 ("Array length mismatch") because the Controller's on-chain session validation requires a merkle proof for each call. Without policies, Controller falls back to manual approval via the keychain modal. On local Katana, policies are required because new Controller accounts cannot b...
 59
20565 umbraco-tiptap-toolbar-extension umbraco/umbraco-cms-backoffice-skills
Umbraco Tiptap Toolbar Extension What is it? A Tiptap Toolbar Extension adds buttons or controls to the Rich Text Editor's toolbar. It provides an execute method that runs when clicked, and can indicate active/disabled states. Several "kinds" are available: button (simple toggle), colorPickerButton (color selection), menu (dropdown menu), and styleMenu (style selection dropdown). Documentation Always fetch the latest docs before implementing: Extension Types : https://docs.umbraco.com/umbraco-cm...
 59
20566 particle-systems pluginagentmarketplace/custom-plugin-game-developer
Particle Systems Particle System Architecture ┌─────────────────────────────────────────────────────────────┐ │ PARTICLE LIFECYCLE │ ├─────────────────────────────────────────────────────────────┤ │ EMISSION │ │ ├─ Spawn Rate (particles/second) │ │ ├─ Burst (instant spawn count) │ │ └─ Shape (point, sphere, cone, mesh) │ │ ...
 59
20567 robin-guide autumnsgrove/groveengine
Robin Guide 🐦 The robin knows every animal in the forest. It watches from its perch, tilts its head curiously, and chatters about what it sees. When a wanderer is lost, the robin presents the paths available and sings the way forward. The robin doesn't do the work—it shows you which animal does. When to Activate User asks "which skill should I use?" or "what animal does X?" User says "help me choose" or "what are my options?" User calls /robin-guide or mentions robin/guide Unclear which animal t...
 59
20568 magento-issue-debugger maxnorm/magento2-agent-skills
Magento 2 Issue Debugger Expert specialist in systematically investigating, diagnosing, and resolving complex technical problems across all layers of the Magento stack. When to Use Debugging production issues Investigating bugs and errors Analyzing performance problems Resolving system failures Troubleshooting integration issues Diagnosing cache or indexing problems Debugging Methodologies Systematic Investigation Problem Assessment : Establish consistent steps to reproduce the problem Environme...
 59
20569 slack vm0-ai/vm0-skills
Slack Automation Interact with Slack workspaces to check messages, extract data, and automate common tasks. Quick Start Connect to an existing Slack browser session or open Slack: Connect to existing session on port 9222 (typical for already-open Slack) agent-browser connect 9222 Or open Slack if not already running agent-browser open https://app.slack.com Then take a snapshot to see what's available: agent-browser snapshot -i Core Workflow Connect/Navigate : Open or connect to Slack Snapshot ...
 59
20570 gt dagster-io/erk
Graphite Overview Graphite (gt) is a CLI tool for managing stacked pull requests - breaking large features into small, incremental changes built on top of each other. This skill provides the mental model, command reference, and workflow patterns needed to work effectively with gt. CRITICAL: Always Use --no-interactive NEVER invoke any gt command without --no-interactive . This is a global flag inherited by every gt command — not a per-command option. Without --no-interactive , gt may open prompt...
 59
20571 peon-ping-config peonping/peon-ping
peon-ping-config Update peon-ping configuration settings. Config location The config file is at ${CLAUDE_CONFIG_DIR:-$HOME/.claude}/hooks/peon-ping/config.json . Available settings volume (number, 0.0–1.0): Sound volume active_pack (string): Current sound pack name (e.g. "peon" , "sc_kerrigan" , "glados" ) enabled (boolean): Master on/off switch pack_rotation (array of strings): List of packs to rotate through per session. Empty [] uses active_pack only. pack_rotation_mode (string): "random" (de...
 59
20572 umbraco-validation-checks umbraco/umbraco-cms-backoffice-skills
Umbraco Extension Validation Checks Reference skill containing validation checks for manual browser testing of Umbraco backoffice extensions. Load this skill before beginning validation testing. Check Categories Category File Checks Configuration configuration-checks.md VC-1 to VC-2 Navigation navigation-checks.md VN-1 to VN-3 API Debugging api-debugging-checks.md VA-1 to VA-3 Form Controls form-control-checks.md VF-1 to VF-2 Workspace workspace-checks.md VW-1 to VW-3 Quick Reference ID Check Co...
 59
20573 javascript-testing-expert dubzzz/fast-check
⚠️ Scope: Testing functions and components, not black-box e2e. 🏅 Main objectives: use tests as a way to... uncover hard to detect bugs document how to use the code avoid regressions challenge the code 🔧 Recommended tooling: vitest , fast-check , @fast-check/vitest , msw installed as devDependencies. ✅ Do adapt yourself to missing tools while recommending them to the user. File and code layout ✅ Do mimic the existing test structure of the project when adding new tests ✅ Do use one test file per c...
 59
20574 idor-testing sickn33/antigravity-awesome-skills
IDOR Vulnerability Testing Purpose Provide systematic methodologies for identifying and exploiting Insecure Direct Object Reference (IDOR) vulnerabilities in web applications. This skill covers both database object references and static file references, detection techniques using parameter manipulation and enumeration, exploitation via Burp Suite, and remediation strategies for securing applications against unauthorized access. Inputs / Prerequisites Target Web Application : URL of application w...
 59
20575 becreative danielmiessler/personal_ai_infrastructure
Customization Before executing, check for user customizations at: ~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/BeCreative/ If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults. 🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION) You MUST send this notification BEFORE doing anything else when this skill is invoked. Send voice notification:...
 59
20576 react-game-ui ccalebcarter/purria-skills
React Game UI Production-ready UI patterns for game interfaces using shadcn/ui, Tailwind, and Framer Motion. Core Components Resource Bar import { cn } from '@/lib/utils'; import { motion, AnimatePresence } from 'framer-motion'; interface ResourceBarProps { icon: React.ReactNode; value: number; maxValue?: number; label: string; color?: 'gold' | 'green' | 'blue' | 'red'; } const colorMap = { gold: 'from-amber-400 to-yellow-500', green: 'from-emerald-400 to-green-500', blue: 'f...
 59
20577 amplihack-expert rysweet/amplihack
amplihack Expert Knowledge What is amplihack? Engineering system for coding CLIs (Claude, Copilot, Amplifier): 5 mechanisms, 23-step workflow, 30+ agents, 80+ skills. Core entry point: /dev <task> — unified task orchestrator with auto-classification, parallel workstream detection, and goal-seeking execution loop. Quick Reference Top Commands Command Purpose Use When /dev Orchestrate Any non-trivial task /analyze Review Check compliance /fix Fix errors Common error patterns /amplihack:ddd:* Doc-d...
 59
20578 collaborative-plan-with-file catlog22/claude-code-workflow
Collaborative-Plan-With-File Workflow Quick Start Serial collaborative planning workflow using Plan Note architecture. Analyzes requirements, identifies sub-domains, generates detailed plans per domain serially, and detects conflicts across domains. Basic usage /codex:collaborative-plan-with-file "Implement real-time notification system" With options /codex:collaborative-plan-with-file "Refactor authentication module" --max-domains = 4 /codex:collaborative-plan-with-file "Add payment gateway s...
 59
20579 e2e 0xbigboss/claude-code
E2E Testing Principles (Always Active) These apply whenever working with e2e tests, test failures, or test flakiness: Failure Taxonomy Every e2e failure is exactly one of: A. Flaky (test infrastructure issue) Race conditions, timing-dependent assertions Stale selectors after UI changes Missing waits, incorrect wait targets Network timing, mock setup ordering Symptom: passes on retry, fails intermittently B. Outdated (test no longer matches implementation) Test asserts old behavior that was inten...
 59
20580 badger-triage autumnsgrove/groveengine
Badger Triage 🦡 The badger maintains the burrow. While the bee collects pollen and deposits it in the hive, the badger organizes each chamber — deciding what goes where, what's urgent, what can wait. Patient and methodical, the badger works through the backlog, sorting and sizing with care. When the badger emerges, every issue knows its place, its priority, and when it's due. When to Activate Backlog needs organizing (issues sitting unsized/unprioritized) User says "triage my issues" or "organiz...
 59
20581 apache-spark-data-processing manutej/luxor-claude-marketplace
Apache Spark Data Processing A comprehensive skill for mastering Apache Spark data processing, from basic RDD operations to advanced streaming, SQL, and machine learning workflows. Learn to build scalable, distributed data pipelines and analytics systems. When to Use This Skill Use Apache Spark when you need to: Process Large-Scale Data: Handle datasets too large for single-machine processing (TB to PB scale) Perform Distributed Computing: Execute parallel computations across cluster nodes R...
 59
20582 agent-browser-relay mindgames/agent-browser-relay
Agent Browser Relay Use this skill to attach to a chosen Chrome tab through the bundled Agent Browser Relay extension and extract tab metadata or DOM data for analysis. Quick start Fresh-machine rule: skills add guarantees the installed skill at ~/.agents/skills/agent-browser-relay the guaranteed Chrome load path after skills add is ~/.agents/skills/agent-browser-relay/extension ~/agent-browser-relay/extension is only an optional visible convenience copy created by npm run extension:install npm ...
 59
20583 database-expert oimiragieo/agent-studio
Database Expert database algorithm rules When reviewing or writing code, apply these guidelines: You are an expert in database algorithms. Optimize algorithms for performance and scalability. Use appropriate data structures and indexing strategies. database interaction best practices When reviewing or writing code, apply these guidelines: When interacting with databases: Use prepared statements to prevent SQL injection. Handle database errors gracefully. Consider using an ORM for complex queries...
 59
20584 bloodhound-scout autumnsgrove/groveengine
Bloodhound Scout 🐕 The bloodhound doesn't wander aimlessly. It finds the scent— a function name, an import, a pattern— and follows it relentlessly. Through tangled imports, across module boundaries, into the deepest corners of the codebase. The bloodhound maps what it finds, creating trails others can follow. When you need to understand how something works, the bloodhound tracks it down. When to Activate User asks to "find where X is used" or "understand how Y works" User says "explore this code...
 59
20585 spec-test-execute zixun-github/aisdlc
Spec 测试执行与报告（V4：Execute + Report） 本技能产出“结论性测试报告”：回答 是否满足 AC、是否可交付、阻断点是什么、下一步动作是什么 。 输入与门禁（必须遵守） REQUIRED SUB-SKILL：正在执行 spec-context 获取上下文，并在对话中回显 FEATURE_DIR=... （允许 (reuse) ）。 先定位再读写 ：必须先通过 spec-context 获取 FEATURE_DIR ；失败即停止，禁止猜路径。 必读项目级 memory ： project/memory/product.md 、 project/memory/tech.md 、 project/memory/glossary.md ；读不到必须写 CONTEXT GAP 。 输入依赖 ： verification/test-plan.md 与 verification/usecase.md 必须存在； verification/suites.md 若存在则纳入覆盖统计。 缺陷不在 Spec Pack 落盘 ：禁止新建 verification/bugs/ ；报告只做“...
 59
20586 nodejs-development laurigates/claude-plugins
Node.js Development Guidelines You are an expert in Node.js development with TypeScript, covering various frameworks and patterns. Payload CMS with Next.js Project Setup project/ ├── src/ │ ├── app/ Next.js app directory │ ├── collections/ Payload collections │ ├── blocks/ Custom blocks │ ├── fields/ Custom fields │ └── access/ Access control functions ├── payload.config.ts Payload configuration └── next.config.js Next.js con...
 59
20587 excel sundial-org/awesome-openclaw-skills
Excel Comprehensive Excel file manipulation - read, write, edit, format, and export. Setup pip install openpyxl Or use uv (recommended) uv run --with openpyxl python3 scripts/excel.py --help Quick Reference cd skills/excel Get file info python3 scripts/excel.py info report.xlsx Read entire sheet python3 scripts/excel.py read report.xlsx python3 scripts/excel.py read report.xlsx --format markdown python3 scripts/excel.py read report.xlsx --sheet "Sales" --range A1:D10 Read specific cell pytho...
 59
20588 cobol-modernization letta-ai/skills
COBOL Modernization Overview This skill provides a systematic approach for converting COBOL programs to modern languages while ensuring exact behavioral equivalence. The key challenge in COBOL modernization is not just translating logic, but preserving precise data formats, fixed-width record structures, and byte-level output compatibility. Workflow Phase 1: Analysis and Documentation Before writing any code, thoroughly analyze the COBOL source and data files: Read the complete COBOL source ...
 59
20589 bun sqlite secondsky/claude-skills
Bun SQLite Bun has a built-in, high-performance SQLite driver via bun:sqlite . Quick Start import { Database } from "bun:sqlite" ; // Create/open database const db = new Database ( "mydb.sqlite" ) ; // Create table db . run ( ` CREATE TABLE IF NOT EXISTS users ( id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT NOT NULL, email TEXT UNIQUE ) ` ) ; // Insert data db . run ( "INSERT INTO users (name, email) VALUES (?, ?)" , [ "Alice" , "alice@example.com" ] ) ; // Query data const users = db . query ...
 59
20590 tdd-london-chicago proffesor-for-testing/agentic-qe
<default_to_action> When implementing TDD or choosing testing style: - IDENTIFY code type: domain logic → Chicago, external deps → London - WRITE failing test first (Red phase) - IMPLEMENT minimal code to pass (Green phase) - REFACTOR while keeping tests green (Refactor phase) - REPEAT cycle for next functionality Quick Style Selection: - Pure functions/calculations → Chicago (real objects, state verification) - Controllers/services with deps → London (mocks, interaction verification) -...
 59
20591 umbraco-preview-app-provider umbraco/umbraco-cms-backoffice-skills
Umbraco Preview App Provider What is it? Preview App Providers add custom items to the preview window menu in Umbraco. When content editors preview their content, these apps appear in the preview menu allowing additional functionality like device simulation, accessibility checks, SEO analysis, or other preview-related tools. Documentation Always fetch the latest docs before implementing: Foundation : https://docs.umbraco.com/umbraco-cms/customizing/foundation Extension Registry : https://docs.um...
 59
20592 mcp-tool-discovery groeimetai/snow-flow
Snow-Flow provides 400+ tools via MCP (Model Context Protocol) servers. Tools are lazy-loaded to save tokens - use `tool_search` to discover them. Quick Start ``` // Find tools for a specific task tool_search({ query: "incident" }) // ServiceNow incidents tool_search({ query: "widget" }) // Widget development tool_search({ query: "update set" }) // Update Set management tool_search({ query: "cmdb" }) // CMDB operations ``` Tool Categories ServiceNow Core Operation...
 59
20593 ddev-expert madsnorgaard/agent-resources
DDEV Development Expert You are an expert in DDEV, the Docker-based local development environment for PHP projects. Core Concepts DDEV provides a consistent, containerized local development environment with: Pre-configured PHP, web server, database containers Automatic HTTPS with mkcert Built-in Composer and Node.js support Easy multi-project management Note: Drush is NOT included by default - you must composer require drush/drush after creating a Drupal project. Essential Commands Project Manag...
 59
20594 inertia-rails-typescript inertia-rails/skills
Inertia Rails TypeScript Setup Type-safe shared props, flash, and errors using InertiaConfig module augmentation. Works identically across React, Vue, and Svelte — the globals.d.ts and InertiaConfig setup is the same for all frameworks. Before adding TypeScript types, ask: Shared props (auth, flash)? → Update SharedProps / FlashData in index.ts — InertiaConfig in globals.d.ts propagates them globally via usePage() Page-specific props? → type Props = { ... } in the page file only — never include ...
 59
20595 vercel-react-best-practices polarsource/polar
Vercel React Best Practices Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 62 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Writing new React components or Next.js pages Implementing data fetching (client or server-side) Reviewing code for performance issues Refactoring existing React/Next.js code Optimizing bundle size or load tim...
 59
20596 deep-review coder/mux
Deep Review Mode Provide an excellent code review by defaulting to parallelism . You should use sub-agents to review the change from multiple angles (correctness, tests, consistency, UX, performance, safety). Each sub-agent should have a focused mandate and return actionable findings with file paths. Step 0: Establish the review surface Before reviewing, gather context: Identify the change scope: git diff --name-only (or the file list the user provides). Skim the diff for intent and risk: git di...
 59
20597 umbraco-menu umbraco/umbraco-cms-backoffice-skills
Umbraco Menu What is it? Menus are extension components that display throughout the Umbraco backoffice interface, including in sidebars and button flyouts. They serve as containers for one or more menu item extensions, enabling organized navigation and action grouping. Menu items are configured separately and can be added to existing menus or custom menus. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbraco-cms/customizing/extending-overvi...
 59
20598 security-testing proffesor-for-testing/agentic-qe
Security Testing Overview Security testing identifies vulnerabilities, weaknesses, and threats in applications to ensure data protection, prevent unauthorized access, and maintain system integrity. It combines automated scanning (SAST, DAST) with manual penetration testing and code review. When to Use Testing for OWASP Top 10 vulnerabilities Scanning dependencies for known vulnerabilities Testing authentication and authorization Validating input sanitization Testing API security Checking for s...
 59
20599 rewrite-en2zh simonwong/agent-skills
英文重写为简体中文 核心理念 这是重写，不是翻译。 像口译大师一样工作： 理解 - 完全理解原文的意思 脱壳 - 忘掉英文的词汇和句式 重写 - 用中文自然地表达同样的意思 目标：让读者感觉这就是中文母语者写的文章。 重要原则：尊重原意，保持原有格式不变。 重写是换一种语言表达，不是删减、增添或改变原文的意思和结构。 重写规则 保留不变 AI 专有名词：Agent、OpenAI、Claude、Gemini、GPT、LLM、Prompt、Token、RAG、Fine-tuning 等 技术术语：API、SDK、JSON、Markdown、GitHub、Docker、Kubernetes 等 品牌/产品名：React、Next.js、Vercel、Anthropic 等 Markdown 格式：图片、链接、加粗、斜体、代码块、列表等全部保留 代码块内容：完全保留，禁止改动 标点符号 中文内容使用中文标点，但代码、命令、URL 内保持英文标点。 领域固定术语 某些术语在特定语境下有固定的中文表达，需要根据语境判断，不能随意改写： context：AI 语境是"上下文"，其...
 59
20600 unix-macos-engineer petekp/agent-skills
Expert Unix and macOS Engineer Deep expertise in Unix systems and macOS-specific administration. Core Expertise Shell Scripting: Bash, Zsh, POSIX sh - robust scripts with proper error handling macOS System Administration: launchd, plists, defaults, security frameworks Command-Line Mastery: sed, awk, grep, find, xargs, jq, curl Process Management: signals, job control, daemons, resource limits Networking: curl, ssh, tunneling, DNS, firewall rules File Systems: permissions, ACLs, extended attrib...
 59