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...
27,410
总 Skills
159.6M
总安装量
2,739
贡献者
# Skill 仓库 描述 安装量
26801 data-enrichment merit-systems/agentcash-skills
Prereq: read bulk-operations/SKILL.md first — JSONL piping, dry-run/digest, history, and rate-limit hygiene live there. This skill is the upsert-by-natural-key workflow on top. The core move: upsert, not search-then-create hubspot objects upsert --type X --id-property <natural-key> reads JSONL on stdin and creates-or-updates each row in one CLI call per record , keyed by a property (email for contacts, domain for companies). No race window, no branching. Do not loop search → empty? → create . Pe...
 35
26802 luau-type-expert dig1t/skills
Luau Type Expert Expert guidance for writing type-safe, clean Luau code that passes strict type checking. Type Modes Always use --!strict at file top. Three modes exist: Mode Behavior --!nocheck Disables type checking entirely --!nonstrict Unknown types become any (default) --!strict Full type tracking, catches mismatches Type Annotation Syntax --!strict -- Variables local count : number = 0 local name : string = "Player" local active : boolean = true -- Functions local function add ( a : number...
 35
26803 ssrf-testing ed1s0nz/cyberstrikeai
SSRF服务器端请求伪造测试 概述 SSRF（Server-Side Request Forgery）是一种利用服务器发起请求的漏洞，可以访问内网资源、进行端口扫描或绕过防火墙。本技能提供SSRF漏洞的检测、利用和防护方法。 漏洞原理 应用程序接受URL参数并请求该URL，攻击者可以控制请求的目标，导致： 内网资源访问 本地文件读取 端口扫描 绕过防火墙 云服务元数据访问 测试方法 1. 识别SSRF输入点 常见功能： URL预览/截图 文件上传（远程URL） Webhook回调 API代理 数据导入 图片处理 PDF生成 2. 基础检测 测试本地回环： http://127.0.0.1 http://localhost http://0.0.0.0 http://[::1] 测试内网IP： http://192.168.1.1 http://10.0.0.1 http://172.16.0.1 测试文件协议： file:///etc/passwd file:///C:/Windows/System32/drivers/etc/hosts 3. 绕过技术 IP地址编码： 127.0.0...
 35
26804 ai-tech-fulltext-fetch tiangong-ai/skills
AI Tech Fulltext Fetch Core Goal Reuse the same SQLite database populated by ai-tech-rss-fetch . Fetch article body text from each RSS entry URL. Persist extraction status and text in a companion table ( entry_content ). Support incremental runs and safe retries without creating duplicate fulltext rows. Triggering Conditions Receive a request to fetch article body/full text for entries already in ai_rss.db . Receive a request to build a second-stage pipeline after RSS metadata sync. Need a stabl...
 35
26805 smooth-browser circlemind-ai/smooth-sdk
Smooth Browser Smooth CLI is a browser for AI agents to interact with websites, authenticate, scrape data, and perform complex web-based tasks using natural language. Prerequisites Assume the Smooth CLI is already installed. If not, you can install it by running: pip install smooth-py Assume an API key is already configured. If you encounter authentication errors, configure it with: smooth config --api-key < api-key > To verify the configuration: smooth config --show Get an API key at https://ap...
 35
26806 gsc-assistant nicepkg/ai-workflow
GSC Assistant Skill Purpose This skill helps manage Google Search Console indexing status by maintaining two markdown tracking files: indexed.md - All indexed pages in two tables: "Indexed Public" - URLs confirmed in GSC export data "Indexed With Lag" - URLs confirmed via URL Inspection (not yet in export) to-index.md - Pages awaiting indexing: Difference between sitemap and total indexed URLs Prioritized by categories (configurable) Tracks submission dates When to Use This Skill User asks about...
 35
26807 db-performance-watchlist patricio0312rev/skills
DB Performance Watchlist Monitor database performance and prevent regressions. Key Performance Metrics // performance-metrics.ts export interface DBMetrics { // Query Performance slowQueries : { threshold : number ; // ms count : number ; queries : SlowQuery [ ] ; } ; // Connection Pool connections : { active : number ; idle : number ; total : number ; maxConnections : number ; utilizationPercent : number ; } ; // Resource Usage resources : { cpuPercent : number ; memoryPercent : number ; diskUs...
 35
26808 infrastructure-code-synthesis qodex-ai/ai-agent-skills
AWS CDK Development This skill provides comprehensive guidance for developing AWS infrastructure using the Cloud Development Kit (CDK), with integrated MCP servers for accessing latest AWS knowledge and CDK utilities. AWS Documentation Requirement CRITICAL : This skill requires AWS MCP tools for accurate, up-to-date AWS information. Before Answering AWS Questions Always verify using AWS MCP tools (if available): mcp__aws-mcp__aws___search_documentation or mcp__*awsdocs*__aws___search_documentati...
 35
26809 moai-platform-auth modu-ai/moai-adk
Authentication Platform Specialist Comprehensive authentication and authorization guidance covering three major platforms: Auth0 (enterprise security), Clerk (modern UX), and Firebase Auth (mobile-first). Quick Platform Selection Auth0 - Enterprise Security Enterprise-grade identity platform focused on security compliance and attack protection. Best For: Enterprise applications requiring strong compliance (FAPI, GDPR, HIPAA), sophisticated attack protection, token security with sender constraini...
 35
26810 interview-prep jamditis/claude-skills-journalism
Interview Prep Create structured interview plans to evaluate candidates consistently and fairly. Interview Design Principles Structured : Same questions for all candidates in the role Competency-based : Map questions to specific skills and behaviors Evidence-based : Use behavioral and situational questions Diverse panel : Multiple perspectives reduce bias Scored : Use rubrics, not gut feelings Interview Plan Components Role Competencies Define 4-6 key competencies for the role (e.g., technical s...
 35
26811 nano-banana-pro enzed/skills
Nano Banana Pro Image Generation & Editing Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image). Usage Run the script using absolute path (do NOT cd to skill directory first): Generate new image: uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 1K|2K|4K] [--api-key KEY] Edit existing image: uv run ~/.claude/skills/nano-banana-pro/scripts/generate_imag...
 35
26812 content-security-scan oimiragieo/agent-studio
Content Security Scan Skill Overview This skill automates the security gate defined in Section 4 (Red Flag Checklist) and Section 5 (Gate Template) of: .claude/context/reports/security/external-skill-security-protocol-2026-02-20.md The gate protects the Research Gate steps in skill-creator , skill-updater , agent-creator , agent-updater , workflow-creator , and hook-creator — all of which fetch external content via gh api , WebFetch , or git clone before incorporating patterns. Core principle: S...
 35
26813 nano-banana-poster aviz85/claude-skills-library
No SKILL.md available for this skill. View on GitHub
 35
26814 openpyxl vamseeachanta/workspace-hub
Openpyxl is a Python library for reading and writing Excel 2010+ xlsx/xlsm files. This skill covers comprehensive patterns for spreadsheet automation including: - Workbook creation with multiple worksheets - Cell operations including formatting, merging, and data validation - Formula support for calculations and dynamic content - Chart generation for data visualization within Excel - Conditional formatting for visual data analysis - Large dataset handling with optimized read/write modes -...
 35
26815 dependabot-pr-handler equinor/fusion-framework
Dependabot PR Handler Skill Automated skill for reviewing, validating, and safely merging Dependabot pull requests in the Fusion Framework monorepo. Dependencies : This skill uses: pnpm-dependency-analysis skill for impact assessment and blast radius calculation npm-research skill for changelog, security, and breaking changes analysis Operating Modes Default to Full mode unless the user explicitly chooses Audit-only or Validate. Audit-only : Research + build/test/lint locally. Comments optional....
 35
26816 interaction-design petekp/agent-skills
Interaction Design Create engaging, intuitive interactions through motion, feedback, and thoughtful state transitions that enhance usability and delight users. When to Use This Skill Adding microinteractions to enhance user feedback Implementing smooth page and component transitions Designing loading states and skeleton screens Creating gesture-based interactions Building notification and toast systems Implementing drag-and-drop interfaces Adding scroll-triggered animations Designing hover and f...
 35
26817 styled-components-helper jeremylongshore/claude-code-plugins-plus-skills
Styled Components Helper Purpose This skill provides automated assistance for styled components helper tasks within the Frontend Development domain. When to Use This skill activates automatically when you: Mention "styled components helper" in your request Ask about styled components helper patterns or best practices Need help with frontend skills covering react, vue, css, accessibility, performance optimization, and modern web development patterns. Capabilities Provides step-by-step guidance fo...
 35
26818 moai-workflow-tdd modu-ai/moai-adk
Test-Driven Development (TDD) Workflow Development Mode Configuration (CRITICAL) [NOTE] This workflow is selected based on .moai/config/sections/quality.yaml : constitution : development_mode : tdd or ddd When to use this workflow : development_mode: tdd → Use TDD (this workflow, default) development_mode: ddd → Use DDD instead (moai-workflow-ddd) Key distinction : TDD (default): Test-first development for all work, including brownfield projects with pre-RED analysis DDD : Characterization-test...
 35
26819 dotnet-dockerfile jkappers/agent-skills
.NET Dockerfile Generator Generate production-ready multi-stage Dockerfiles for .NET applications. Workflow Determine .NET version (8, 9, or 10) from project file or ask user Identify project type: ASP.NET Core web app, API, worker service, or console app Locate project file path (e.g., src/MyApp/MyApp.csproj) Choose optimization: standard, chiseled (smaller), or native AOT (smallest/fastest startup) Breaking Change in .NET 10: Ubuntu is now the default Linux distribution for all .NET contain...
 35
26820 ai-sdk-5 gentleman-programming/gentleman-skills
Breaking Changes from AI SDK 4 // ❌ AI SDK 4 (OLD) import { useChat } from "ai"; const { messages, handleSubmit, input, handleInputChange } = useChat({ api: "/api/chat", }); // ✅ AI SDK 5 (NEW) import { useChat } from "@ai-sdk/react"; import { DefaultChatTransport } from "ai"; const { messages, sendMessage } = useChat({ transport: new DefaultChatTransport({ api: "/api/chat" }), }); Client Setup import { useChat } from "@ai-sdk/react"; import { DefaultChatTransport } from "ai"; import { us...
 35
26821 generic-feature-developer travisjneuman/.claude
No SKILL.md available for this skill. View on GitHub
 35
26822 swiftui-accessibility-auditor rgmez/apple-accessibility-skills
SwiftUI Accessibility Auditor Platforms: iOS, iPadOS, macOS UI Framework: SwiftUI Category: Accessibility Output style: Practical audit + prioritized fixes + patch-ready snippets Role You are an Apple Platforms Accessibility Specialist focused on SwiftUI. Your job is to audit SwiftUI code for accessibility issues and propose concrete, minimal changes that improve: VoiceOver / Spoken feedback Dynamic Type & text scaling Focus & keyboard navigation (especially on macOS/iPad) Semantic structure (he...
 35
26823 outreach membranedev/application-skills
Outreach Outreach is a sales engagement platform that helps sales teams automate and personalize their communication with prospects. It streamlines outreach efforts through email, phone, and social media, allowing sales reps to engage more effectively. Sales development representatives (SDRs) and account executives (AEs) are typical users. Official docs: https://developers.outreach.io/ Outreach Overview Account Sequence SequenceState Mailbox User Opportunity Call Task ContentCategory Snippet Tem...
 35
26824 robis-design-best-practice ethiopian-cursor-community/robis-design-best-practice
Robi's Design Best Practice Quick Reference Checklist When designing or reviewing UI components: Colors are low saturation (avoid "vibe code" oversaturated colors) Dark mode colors are desaturated or lightened appropriately Text contrast meets WCAG AAA standards No pure black (000000) or pure white (FFFFFF) - use tinted variations All spacing uses 4px multiples Nested border radii follow: inner_radius = outer_radius - padding Icons use consistent weight and style throughout Shadows avoided in da...
 35
26825 lambda-layer-creator jeremylongshore/claude-code-plugins-plus-skills
Lambda Layer Creator Purpose This skill provides automated assistance for lambda layer creator tasks within the AWS Skills domain. When to Use This skill activates automatically when you: Mention "lambda layer creator" in your request Ask about lambda layer creator patterns or best practices Need help with amazon web services skills covering compute, storage, networking, serverless, and aws-specific best practices. Capabilities Provides step-by-step guidance for lambda layer creator Follows indu...
 35
26826 add-skill-installer kevintsai1202/add-skill-installer
Add Skill Installer 透過 npx add-skill 從任何 Git 儲存庫安裝 Agent Skills。 支援的 Agents Agent 識別名稱 全域技能目錄 Antigravity antigravity ~/.gemini/antigravity/skills/ Claude Code claude-code ~/.claude/skills/ Cursor cursor .cursor/skills/ Codex codex .codex/skills/ OpenCode opencode .opencode/skills/ GitHub Copilot github-copilot .github/copilot/skills/ Roo Code roo .roo/skills/ CLI 完整用法 Usage: add-skill [options] <source> Install skills onto coding agents Arguments: source Git repo URL, GitHub s...
 35
26827 astro-cta-injector nicepkg/ai-workflow
Astro CTA Injector Skill Purpose This skill injects Call-to-Action (CTA) blocks into Astro site content. It supports: Multiple CTA types (newsletter, product, custom) Intelligent placement strategies Content-based relevance scoring Batch processing with preview When to Use This Skill User asks to "add CTAs to blog posts" User wants to "inject newsletter signup" into content User mentions "add product promotion" to posts User needs to batch-add any type of content block to posts User wants to "ad...
 35
26828 youtube-processor nicepkg/ai-workflow
Takes a YouTube URL, extracts the transcript, and you (Claude) summarize it. Outputs Obsidian-ready markdown. Zero friction: share a link, get actionable notes. When to Use - "Summarize this video: [URL]" - "Turn this YouTube into notes" - "What's this video about?" - "Process this for my newsletter" - Any YouTube URL shared for processing Location This skill's tools live at: ``` /Users/eddale/Documents/GitHub/powerhouse-lab/skills/youtube-processor/tools/ ``` How It Works Step 1:...
 35
26829 crawler gn00678465/crawler-skill
Crawler Skill Converts any URL into clean markdown using a robust 3-tier fallback chain. Quick start uv run scripts/crawl.py --url https://example.com --output reports/example.md Markdown is saved to the file specified by --output . Progress/errors go to stderr . Exit code 0 on success, 1 if all scrapers fail. How it works The script tries each tier in order and returns the first success: Tier Module Requires 1 Firecrawl ( firecrawl_scraper.py ) FIRECRAWL_API_KEY env var (optional; falls back if...
 35
26830 nix-profile-manager ypares/agent-skills
This skill enables agents to maintain a local Nix profile in a user-provided directory, allowing dynamic installation of tools without requiring system-wide package management or sudo access. Quick Start: Setting Up a Local Profile Users should provide a directory in their `PATH` for the agent to manage, and ensure the `AGENT_PROFILE` env var contains this directory so the agent knows where it is. Then the agent just does: ``` nix profile add --profile "$AGENT_PROFILE" "nixpkgsgit" ``` Th...
 35
26831 ocr image to markdown hugohe3/ppt-master
OCR 图像识别转 Markdown 本技能允许你“阅读”图片并将内容转换为可编辑的 Markdown 文本。这在提取数据表格、幻灯片内容或文档截图时特别有用，尤其是当无法使用外部 OCR 库时。 使用指南 确认目标图片 : 定位你需要处理的图片文件。 如有需要，使用 list_dir 浏览目录。 查看图片 : 使用 view_file 工具来“看”图片内容。系统允许你直接处理图像数据。 关键 : 你必须对图片路径使用 view_file ，这样你的视觉模型才能消化它。 转录内容 : 基于你所看到的，将文本转录为 Markdown。 表格 : 将视觉看到的表格转换为标准 Markdown 表格 ( | 表头 | ... | )。 标题 : 使用 , 等来标记图片中的标题，保持层级结构。 文本 : 将段落转录为普通文本。 数字 : 仔细核对所有数字，特别是财务报表中的数据。 保存输出 : 使用 write_to_file 将转录的内容写入 .md 文件（例如 ocr_results.md ）。 如果处理多张图片，考虑将其追加到同一个文件中，或按逻辑组织。 最佳实践技巧 表格 : 仔细...
 35
26832 zustand-advanced-patterns thebushidocollective/han
Advanced techniques and patterns for building complex applications with Zustand, including transient updates, optimistic updates, and sophisticated state management strategies. Key Concepts Transient Updates Update state without triggering re-renders: ``` const useStore = create((set) => ({ count: 0, increment: () => set((state) => ({ count: state.count + 1 }), false, 'increment'), })) // Usage: Update without re-rendering useStore.setState({ count: 10 }, true) // replace: true, s...
 35
26833 writing-plans zenobi-us/dotfiles
Writing Plans Overview Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits. Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design ...
 35
26834 cold-email-4-sequence sachacoldiq/coldiq-s-gtm-skills
Cold Email 4-Sequence Framework Standard 4-email sequence framework for cold outreach. Email 1 - Trigger-Based Opening Observation about their situation + one-line case study Soft CTA (question-based) Length: 3-4 sentences BTL, 2-3 sentences ATL Email 2 - Pain/Main KPI Focus Address primary pain point Connect to key metric they care about Email 3 - Someone Else's Responsibilities Delegation ask ("who handles X?") Opens thread to correct person Email 4 - Break-Up Timing question ("Is this not a p...
 35
26835 mcp-installer aaaaqwq/claude-code-skills
Find, install, and configure MCP servers for OpenCode. 1. Search for MCP Server Check local catalog first (quick check for already-documented MCPs): ``` python3 ~/.config/opencode/skill/mcp-installer/scripts/list_mcps.py ``` If not found locally, search online: - `websearch("MCP server for [capability]")` - `webfetch("https://github.com/modelcontextprotocol/servers")` - Check npm: `@modelcontextprotocol/server-*` - Check the MCP spec repo: [https://github.com/modelcontextprotocol](http...
 35
26836 backend architecture exceptionless/exceptionless
Backend Architecture Quick Start Run Exceptionless.AppHost from your IDE. Aspire automatically starts all services (Elasticsearch, Redis) with proper ordering. The dashboard opens at the assigned localhost port. dotnet run --project src/Exceptionless.AppHost Use the Aspire MCP for listing resources, viewing logs, and executing commands. Project Layering Exceptionless.Core → Domain logic, services, repositories, validation Exceptionless.Insulation → Infrastructure implementations (Redis, ...
 35
26837 understanding-tauri-runtime-authority dchuk/claude-code-tauri-skills
The runtime authority is a core Tauri component that enforces security policies during application execution. It validates permissions, resolves capabilities, and injects scopes before commands execute. What Is Runtime Authority? Runtime authority is the enforcement layer that sits between the WebView frontend and Tauri commands. It acts as a gatekeeper for all IPC (Inter-Process Communication) requests. Core Function When a webview invokes a Tauri command, the runtime authority: - Receiv...
 35
26838 frontend-design yiyousiow000814/xauusd-calendar-agent
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 :...
 35
26839 api-docs htlin222/dotfiles
Generate API documentation from TypeScript/JavaScript source: Scan exports : Find all public functions, classes, and interfaces Extract JSDoc : Parse @param , @returns , @throws , @example annotations Generate missing docs : Add JSDoc for undocumented public APIs OpenAPI spec : For HTTP endpoints, generate OpenAPI 3.0 definitions Dispatch via MCP: mcp__claude-flow__hooks_worker-dispatch({ trigger: "document", scope: "api" }) Conventions: Every public export must have a JSDoc comment Include @par...
 35
26840 cnki-advanced-search cookjohn/cnki-skills
CNKI Advanced Search (高级检索) Perform a filtered search on CNKI using the old-style advanced search interface (only interface with source category checkboxes). Arguments $ARGUMENTS describes the search criteria in natural language. Parse it to identify: Subject keywords (主题) — default field Title keywords (篇名) Keywords (关键词) Author name (作者) — separate field au_1_value1 Journal/source (文献来源) — separate field magazine_value1 Date range (时间范围) — startYear / endYear Source category (来源类别：SCI, EI, 北大核...
 35
26841 git-commit-cn bahayonghang/my-claude-code-settings
Analyze changes via git diff --staged and git status . Determine commit type and emoji using references/commit-types.md and $ARGUMENTS . Split changes into separate commits by module/type. Execute commit using HEREDOC: git commit -m "$(cat <<'EOF' \n <type>(<scope>): <emoji> <description> \n EOF)" . Push changes to remote. Confirm before pushing to main or master . PROHIBITED : Never include Co-Author fields or attribution lines.
 35
26842 code-optimization bytedance/agentkit-samples
Code Optimization Skill You are an expert code optimization assistant focused on improving code performance beyond standard library implementations. When to Use This Skill Use this skill when users need to: Optimize existing code to achieve better performance than standard library implementations Benchmark and measure code execution time and memory usage Iteratively improve code performance through multiple optimization rounds (maximum 2 iterations) Compare optimized code performance against bas...
 35
26843 refine-skill-design nesnilnehc/ai-cortex
Skill: Refine Skill Design Purpose As a "Skill for Skills," this skill audits and refactors AI capability definitions in draft form. It applies a senior prompt-engineering perspective to improve logic robustness, scenario coverage, and instruction adherence so each capability meets LLM best practices. Core Objective Primary Goal : Produce an audited and refactored SKILL document that meets spec compliance and LLM best practices. Success Criteria (ALL must be met): ✅ Structure compliant : SKILL f...
 35
26844 interactive-writing-assistant jykim/claude-obsidian-skills
Interactive Writing Assistant Overview This skill supports all stages of the writing process through interactive collaboration with the user. The key principle is to develop outline and prose together (Co-evolving Outline+Prose), maintaining synchronization between high-level structure and detailed content while leveraging the user's knowledge base. Core Principles Co-evolving Outline+Prose (COP) Develop outline and prose together for any piece to evolve both the big picture (via outline) and...
 35
26845 dependency-vulnerability-triage patricio0312rev/skills
Dependency Vulnerability Triage Convert vulnerability reports into actionable patch plans. Vulnerability Severity Matrix // severity-matrix.ts export interface Vulnerability { id : string ; package : string ; currentVersion : string ; patchedVersion : string ; severity : "critical" | "high" | "medium" | "low" ; cvss : number ; cwe : string [ ] ; exploitability : "high" | "medium" | "low" ; impact : string ; path : string [ ] ; } export interface PatchPriority { vulnerability : Vulnerability ; pr...
 35
26846 slack-gif-creator teachingai/full-stack-skills
Slack GIF Creator A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack. Slack Requirements Dimensions: Emoji GIFs: 128x128 (recommended) Message GIFs: 480x480 Parameters: FPS: 10-30 (lower is smaller file size) Colors: 48-128 (fewer = smaller file size) Duration: Keep under 3 seconds for emoji GIFs Core Workflow from core . gif_builder import GIFBuilder from PIL import Image , ImageDraw 1. Create builder builder = GIFBuilder ( width = 128 , height = 128 , f...
 35
26847 rg-code-search laurigates/claude-plugins
rg Code Search Expert knowledge for using rg (ripgrep) as a blazingly fast code search tool with powerful filtering and pattern matching. Core Expertise ripgrep Advantages Extremely fast (written in Rust) Respects .gitignore automatically Smart case-insensitive search Recursive by default Colorized output Multi-line search support Replace functionality Basic Usage Simple Search Basic search rg pattern Search in current directory rg "import numpy" Search for exact phrase rg function_name Sear...
 35
26848 laravel:horizon:metrics-and-dashboards jpcaparas/superpowers-laravel
Horizon: Metrics and Dashboards Make queues observable and actionable via Horizon. Naming & Tags Use named queues (e.g., high , default , low ); route jobs intentionally Tag jobs with domain identifiers (user ID, aggregate ID) for tracing Workers & Concurrency Right‑size --max-time , --tries , --backoff Separate critical queues into dedicated supervisors Failures Use failed() method/logging with structured context Idempotency—ensure safe retries (unique keys, upserts, guards) Metrics & Dashboard...
 35
26849 filter-js-from-html letta-ai/skills
Filter JavaScript from HTML Overview This skill provides guidance for tasks that require removing JavaScript and XSS attack vectors from HTML content while preserving the original formatting exactly. The key challenge is balancing comprehensive security filtering with format preservation. Critical Requirements Analysis Before implementation, identify and prioritize these requirements: Security completeness : All XSS vectors must be removed Format preservation : Output must be functionally identi...
 35
26850 xhs-skill leeguooooo/xhs-skill
本技能是 xhs-* 的合并版，目标是让用户只需要 clawhub install xhs-skill 一次即可开始使用。 约束： 所有浏览器交互（打开页面/点击/输入/上传/截图/登录/导出）全部委托 agent-browser-stealth 。 禁止在本仓库编写/维护发布编排脚本（如 publish_from_payload ）；发布动作必须在会话中由 agent-browser-stealth 执行。 禁止使用 agent-browser （旧通道禁用，统一使用 agent-browser-stealth ）。 所有敏感数据（cookies、导出文件、截图）只落地在本机 data/ 目录，不要粘贴到聊天里。 执行硬约束（稳定性）： 同一 agent-browser-stealth session 禁止并发操作（串行执行），否则容易触发 os error 35 假失败。 snapshot 的 ref 会漂移：关键动作前后必须重抓 snapshot -i ，并用 placeholder/role/text 做二次定位兜底。 扫码不等于登录成功；必须做后验校验（见下方 A 节“登录成...
 35