Software Development AI agent skills

13,359 skills in the archive. Read a skill’s instructions or open its original repository.

• Argument Evaluation

  by @Tibsfox

  Systematic evaluation of arguments for structure, validity, soundness, and charitable interpretation. Covers premise identification, conclusion extraction, argument mapping, steel-manning, and the distinction between validity…

• Active Listening

  by @Tibsfox

  Active listening techniques for effective communication. Covers attending behaviors, paraphrasing, reflective listening, clarifying questions, empathic response, barriers to listening, listening in conflict, and cross-cultural…

• Review Agents Md

  by @richtabor

  Creates minimal, effective AGENTS.md files using progressive disclosure. Triggers on "create agents.md", "refactor agents.md", "review my agents.md", "claude.md", or questions about agent configuration files. Also triggers…

• Fresh Eyes

  by @richtabor

  Re-reads code you just wrote with fresh perspective to catch bugs, errors, and issues. Use after completing a feature, fixing a bug, or any code changes. Triggers on "review my code", "fresh eyes", "check for bugs", "did I miss…

• Review Pr

  by @richtabor

  Reviews PR comments from GitHub (Copilot, reviewers), evaluates against actual code, replies with reasoning, and resolves threads. Triggers on "review pr comments", "address pr feedback", "fix pr comments", or "review copilot…

• Og Images

  by @richtabor

  Guides creation of OpenGraph and Twitter share images using next/og ImageResponse. Covers layout patterns, custom fonts, avatars, title case, and Satori rules. Use when building OG images, Twitter cards, or social previews.

• Codebase Inspection

  by @seaworld008

  Use when a user needs reproducible repository sizing, language composition, file counts, or code-versus-comment ratios with pygount; record exclusions and verify measurement scope before interpreting results.

• Agent Browser

  by @seaworld008

  Use when an agent needs real browser automation for semantic element targeting, form interaction, screenshots, recordings, script execution, session reuse, or end-to-end web workflow verification.

• Andrej Karpathy Skills

  by @seaworld008

  Karpathy-inspired coding discipline for AI agents: think before coding, keep changes simple, edit surgically, and define verifiable success criteria before implementation.

• Competitive Teardown

  by @seaworld008

  Analyze competitors from product, pricing, reviews, SEO, and hiring evidence to produce feature comparisons, positioning, and actionable recommendations.

• Beautiful Commits

  by @Tibsfox

  Crafts professional git commit messages following Conventional Commits. Use when committing changes or writing commit messages.

• Codeql Security Scanner

  by @seaworld008

  用于通过 CodeQL 执行语义代码扫描、安全查询、自定义规则、SARIF 报告和 GitHub Code Scanning 集成。

• Multi Chart Draw

  by @LingyiChen-AI

  支持多种图表类型的绘制工具，包括思维导图、流程图、数据可视化图表、数学函数图等；可根据用户需求生成 Mermaid、ECharts、Mindmap、DrawIO、GeoGebra 等格式的图表，并导出为 PNG、SVG、HTML 等格式

• Avalonia Zafiro Development

  by @SamarthaKV29

  Mandatory skills, conventions, and behavioral rules for Avalonia UI development using the Zafiro toolkit.

• Feishu Doc To Dev Spec

  by @LingyiChen-AI

  读取飞书云文档（支持多个链接），解析文档中的文本、表格、图片等内容，根据用户选择的开发语言和存储结构，将产品需求文档转换为研发开发需求文档

• Just Scrape

  by @ScrapeGraphAI

  Search, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON from a site, crawl documentation…

• Analytics Tracking

  by @SamarthaKV29

  Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data. Use when the user wants to set up, fix, or evaluate analytics tracking (GA4, GTM, product analytics, events, conversions, UTMs).…

• Azure Functions

  by @SamarthaKV29

  Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when:…

• Langconfig Builder

  by @LangConfig

  Complete guide for building agents and workflows in LangConfig. Use when users need help configuring nodes, connecting agents, setting up tools, or designing multi-agent systems within the LangConfig platform.

• Aws Serverless

  by @SamarthaKV29

  Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization.

• Security Review

  by @LangConfig

  Comprehensive security code review covering OWASP Top 10, authentication, authorization, and secure coding practices. Use when reviewing code for vulnerabilities or implementing security features.

• Langchain Agents

  by @LangConfig

  Expert guidance for building LangChain agents with proper tool binding, memory, and configuration. Use when creating agents, configuring models, or setting up tool integrations in LangConfig.

• Debugging

  by @LangConfig

  Expert guidance for debugging code, analyzing errors, and systematic problem-solving. Use when troubleshooting bugs, understanding error messages, or investigating unexpected behavior.

• Langgraph Workflows

  by @LangConfig

  Expert guidance for designing LangGraph state machines and multi-agent workflows. Use when building workflows, connecting agents, or implementing complex control flow in LangConfig.

• Git Workflow

  by @LangConfig

  Expert guidance for Git workflows, branching strategies, and version control best practices. Use when managing repositories, resolving conflicts, or establishing team workflows.

• Documentation

  by @LangConfig

  Expert guidance for writing clear, comprehensive documentation including READMEs, API docs, docstrings, and technical guides. Use when creating or improving documentation.

• Mcp Builder

  by @LangConfig

  Comprehensive guide for creating Model Context Protocol (MCP) servers. Use when building MCP servers, integrating external APIs, or creating tool interfaces for LLMs.

• Python Testing

  by @LangConfig

  Expert guidance for writing Python tests with pytest and unittest. Use when writing tests, debugging test failures, or improving test coverage for Python projects.

• Inertia Rails Controllers

  by @inertia-rails

  ALWAYS `render inertia: { key: data }` to pass data as props — instance variables are NOT auto-passed (only alba-inertia does that). Rails controller patterns for Inertia.js: render inertia, prop types (defer, optional, merge,…

• Context7

  by @telagod

  Search and query up-to-date documentation for any programming library via Context7 API. Use when you need current docs, code examples, or API references for libraries and frameworks.

• Inertia Rails Setup

  by @inertia-rails

  One-time project initializer for Inertia Rails skills. Detects stack and frontend framework (React/Vue/Svelte) from Gemfile and package.json, offers to install recommended deps (alba-inertia, js-routes, pagy, shadcn), and…

• Runway Dev

  by @runwayml

  Foundation for building, modifying, debugging, or verifying Runway Dev Platform integrations in an application: connect Dev MCP, use llms.txt to find current resources, resolve project context, use SDK wait helpers, and handle…

• Runway Dev Models

  by @runwayml

  Build, modify, debug, or verify Runway model generation in an application: discover accessible models and constraints with MCP, implement SDK calls, and wire inputs and outputs into the product UI. Use with +runway-dev. Not for…

• Runway Dev Recipes

  by @runwayml

  Choose, build, modify, debug, or verify Runway recipe integrations: match a recipe to the user's use case, follow its current contract, implement SDK client.recipes calls, and wire results into the application. Use with…

• Runway Dev Characters

  by @runwayml

  Build, modify, debug, or verify Runway Characters integrations: inspect preset or custom avatars with MCP, manage live Sessions via SDK, and connect the application UI. Use with +runway-dev. UI says Characters; MCP/API use…

• Runway Dev Model Routers

  by @runwayml

  Build, modify, debug, or verify Runway Model Routers: inspect live config and eligible models via MCP, manage approved settings, integrate routed SDK calls, and inspect routing results. Use with +runway-dev. Not for direct…

• Runway Dev Workflows

  by @runwayml

  Build, modify, debug, or verify integrations that expose Runway app workflows as API endpoints. Use get_workflows_setup_guide for current setup and API guidance. Use with +runway-dev. Not for model generation, routers, or…

• Rw Generate Video

  by @runwayml

  Generate videos directly using the Runway API via runnable scripts. Supports text-to-video, image-to-video, and video-to-video with seedance2, gen4.5, veo3, and more.

• Git Workflow

  by @telagod

  Git workflow assistant for branching, commits, PRs, and conflict resolution. Use when user asks about git strategy, branch management, or PR workflow.

• Quick Setup

  by @telagod

  Detect project type and generate .pi/ configuration. Use when setting up pi for a new project or when user asks to initialize pi config.

• Rw Generate Image

  by @runwayml

  Generate images directly using the Runway API via runnable scripts. Supports text-to-image with optional reference images.

• Perseus:Start

  by @kaivyy

  Use when you want to run a full, automated penetration test from start to finish (Scan -> Audit -> Exploit -> Report)

• Rw Check Org Details

  by @runwayml

  Query the Runway API for organization details: rate limits, credit balance, usage tier, and daily generation counts

• Perseus:Scan

  by @kaivyy

  Use when starting a security assessment to map architecture, entry points, and attack surface (Phase 1 & 2)

• Perseus Injection

  by @kaivyy

  Deep-dive injection vulnerability analysis (NoSQL, LDAP, XPath, Template, OS Command, Expression Language)

• Perseus Crypto

  by @kaivyy

  Deep-dive cryptography and secrets analysis (JWT, hashing, encryption, key management)

• Perseus Client

  by @kaivyy

  Client-side security analysis (DOM XSS, React/Vue/Angular, SSR, prototype pollution)

• Perseus Api

  by @kaivyy

  Deep-dive API security analysis (REST, GraphQL, WebSocket, gRPC, OAuth, Cache)

• Perseus Supply Chain

  by @kaivyy

  Supply chain security analysis (CVEs, dependencies, typosquatting, licenses)

• Perseus File

  by @kaivyy

  File security analysis (path traversal, upload bypass, XXE, zip slip)

• Perseus:Report

  by @kaivyy

  Use when generating the final executive security report (Phase 4)

• Perseus Logic

  by @kaivyy

  Business logic, race conditions, and AI security analysis

• Deep Research

  by @lovstudio

  Use when the user needs multi-source research with citation tracking, evidence persistence, structured report generation, or an implementation landscape that includes GitHub and other open-source forges. Triggers on "deep…

• Lov Cli2anything

  by @lovstudio

  将已授权观察到的网站 API 转成可验证的 OpenAPI、SDK、Swagger 或任务型 CLI。适用于“把这个网站 API 变成 CLI”“生成可调用 Swagger”以及 “turn observed APIs into a CLI”。

• Lov Create Qrcode

  by @lovstudio

  将网址、文本或任意 UTF-8 内容生成可扫码验证的二维码 PNG，默认只输出码本体，并复用个人配色、圆角、纠错与海报偏好；适用于“生成二维码”“按我的偏好做 QR code”和 “create a QR code”。

• Cyberwise Crashes

  by @zenobi-us

  Diagnose Cyberpunk 2077 crashes, hangs and failures to launch on a modded install - which log actually says what, how to bisect a large mod list without wasting launches, and why the obvious memory reading is usually wrong. Use…

• Lov Check Balance

  by @lovstudio

  一条命令查清 Claude、Codex、DeepSeek 等 agent 账号的剩余额度与重置时间，合并官方订阅窗口、API 余额、本地网关消费与消耗速率；用户说“查我的额度”“还有多少用量”“什么时候重置”，或问 how much quota is left 时使用。

• Cyberwise Reports

  by @zenobi-us

  Generate deliverables about a modded Cyberpunk 2077 install - a system profile that says what is likely wrong, a full mod-list inventory with descriptions, and the house style plus headless verification for any HTML or…

• Lov Ataru Indexing

  by @lovstudio

  检查并构建本地 Ataru 会话记忆索引，让无界面调用方在检索前拿到 searchable 状态。 Use when asked to build, rebuild, repair, or check the Ataru memory index.

• Lov Architecture Documentation

  by @lovstudio

  从项目实际实现生成架构视图、接口说明与决策记录草稿。支持明确输入与结果回读。Use to create architecture documentation from a codebase.

• Lov Distill

  by @lovstudio

  将真实解决过程整理为可复用经验文档并维护知识索引。支持明确输入与结果回读。Use to distill a solved problem into reusable knowledge.

• Shared Context

  by @zenobi-us

  Routes shared engineering context work to the right procedure — report or change where context is stored, pull an external source (Confluence page, Jira issue, web page, PDF, screenshot) into it, and publish the write so other…

• Writing Reports

  by @zenobi-us

  Writes a self-contained HTML evidence report with screenshots, captions, result badges and a clickable summary table. Use when work must be proved rather than claimed - manual test results, acceptance evidence, an audit, a…

• Firefox Devtools

  by @zenobi-us

  Enables Firefox remote debugging workflows, when browser automation or protocol-level Firefox inspection is needed, resulting in configured Firefox RDP access and repeatable debugging steps.

• Lov Better Github Desc

  by @lovstudio

  依据 README 更新 GitHub 仓库描述、主题标签及已核实的官网链接。支持明确输入与结果回读。Use to update a GitHub repository description from its README.

• Lov Filing Monitor

  by @lovstudio

  定期打开接入商、工信部或公安平台权威页面，比较备案状态并追加巡检台账；用户说“每天检查备案”“没变化就静默”或 "monitor the filing status" 时使用，只在变化或需人工动作时提醒。

• Lov Add Tool

  by @lovstudio

  为现有网站新增可用的在线工具，并接入多语言、工具目录、站点地图和必要的成本提示。支持明确输入与结果回读。Use to add an online tool to an existing website.

• Lov Clone Rebrand

  by @lovstudio

  将模板或 fork 改造为新项目，按范围同步品牌、语言和部署设置。支持明确输入与结果回读。Use to create a project from a template and rebrand it.

• Hunter

  by @GadaaLabs

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• Lov Code Review

  by @lovstudio

  审查实际差异中的正确性、安全和维护风险并给出可定位意见。支持明确输入与结果回读。Use to review a code change for actionable defects.

• Lov Better Statusline

  by @lovstudio

  配置并备份 Agent 状态栏，支持列出历史版本和恢复。支持明确输入与结果回读。Use to update an agent status line with rollback.

• Lov Better Project Structure

  by @lovstudio

  分析任意语言项目的目录职责并渐进调整文件结构和引用。支持明确输入与结果回读。Use to improve a project directory structure.

• Lov Checkpoint List

  by @lovstudio

  汇总 Git 与项目日志中的检查点、时间范围和演进记录。支持明确输入与结果回读。Use to list a project checkpoint history.

• Lov Checkpoint

  by @lovstudio

  根据当前 Git 差异和历史记录保存项目里程碑及后续事项。支持明确输入与结果回读。Use to create a project checkpoint.

• Cyberwise Conflicts

  by @zenobi-us

  Cyberpunk 2077 load order and mod conflicts - why earlier in modlist.txt wins, detecting archives that are installed but contributing nothing, and visual bugs that are not conflicts at all. Use when a mod is installed and…

• Cyberwise Hotkeys

  by @zenobi-us

  Find what every key is actually bound to on a modded Cyberpunk 2077 install, across the five separate stores that hold bindings, and generate a hotkey cheatsheet from what is really on disk. Also reads a Corsair iCUE mouse…

• Chrome Debug

  by @zenobi-us

  Use when debugging web applications in chrome via the remote debugging protocol. Provides capabilities for inspecting DOM, executing JS, taking screenshots, and automating browser interactions.

• Lov Document Illustrator

  by @lovstudio

  为文档原地插入 AI 配图。读取文档后全局规划插入点，并行生成所有图片， 异步插回原文。支持封面图、自定义比例和三种风格。 Use when: 用户要求为文档/文章/笔记生成配图、插图。 Also trigger when user mentions: 配图、插图、illustration、 generate images、document images、为文章加图。

• Lov Clash Tun Doctor

  by @lovstudio

  Diagnose and repair application connectivity failures caused by Clash Verge Rev TUN routing, rule precedence, stale runtime state, proxy timeouts, or unusable IPv6 paths. Trigger for symptoms such as WeChat images failing to…

• Lov Bp Polish

  by @lovstudio

  Review and improve an existing BP outline, PPTX, PDF, or rendered slide set across investment logic, evidence, copy, charts, and visual quality. Produces a scored report, page-level revisions, and targeted regeneration…

• Publishing With Release Please And Moonrepo On Github Actions

  by @zenobi-us

  Coordinates Release Please policy, Moon project selection, source-derived publish metadata, and SHA-pinned GitHub Actions publication. Use when standardizing monorepo release.yml/publish.yml workflows across main and release/*…

• Codemapper

  by @zenobi-us

  Use when analyzing codebases for structure, finding symbols, tracing call paths, checking test coverage, or analyzing dependencies - provides instant AST-based code analysis using tree-sitter for Python, JavaScript, TypeScript,…

• Twg Jira

  by @zenobi-us

  Use with root `twg` for Jira workitems, projects, boards, sprints, fields, transitions, comments, links, and administration. Applies Jira semantics and safe mutation rules.

• Legion

  by @GadaaLabs

  Select optimal subagent topology (hierarchical, mesh, ring, star) based on task structure; adds Ruflo-style swarm intelligence to Superpowers

• Ironcore

  by @GadaaLabs

  State machines, ISRs, RTOS, hardware abstraction, and timing analysis — domain expertise for electrical and embedded systems engineers

• Gradient

  by @GadaaLabs

  ML-specific patterns for data pipelines, model training, MLOps, and evaluation — domain expertise for machine learning engineers

• Cyberwise Modbase

  by @zenobi-us

  Build and maintain a per-user knowledge base covering every mod actually deployed on this install - the inventory that comes from the deployment manifest rather than a manager's list, how to derive a Nexus id without guessing…

• Prism

  by @GadaaLabs

  UI/UX design intelligence, accessibility, performance, SEO, and data visualization — domain expertise for web and app developers. Includes 67 UI styles, 25 chart types, font pairing, and UX guidelines.

• Phantom

  by @GadaaLabs

  Use when executing implementation plans with independent tasks in the current session

• Simple English

  by @zenobi-us

  Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes,…

• Lov Auto Context

  by @lovstudio

  Manual or hook-triggered context operator. Evaluates the current session for pollution (long conversations, topic drift, stale noise), AND takes concrete context-shaping actions: writing project memory, updating global or…

• Cyberwise Feedback

  by @zenobi-us

  Help someone report a problem with Cyberwise itself, or correct something it got wrong - gather the facts the author needs, write it up, and send it to the right place (Discord or a GitHub issue). Use when someone says a…

• Surf

  by @zenobi-us

  Controls Chrome through surf-cli for browser automation, debugging, and AI-assisted browsing. Use when tasks need navigation, form filling, screenshots, page inspection, network diagnostics, session-scoped multi-agent browsing,…

• Creating Cli Tools

  by @zenobi-us

  Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI…

• Dsh Plugin Publisher

  by @lovstudio

  Publish a validated DSH plugin package (`@deepseek-ai/dsh-*` or `@lovstudio/dsh-*`) to npm, git, or tarball channels and verify it loads in the DeepSeek Harness. Use when the user asks to publish, release, or ship a plugin.…

• Twg Engineering Work

  by @zenobi-us

  Use with root `twg` for code search, repositories using an API/package, implementation and reverse-dependency discovery, PR status and reviews, repo contributors, hot areas, and issue-to-PR lookups.

• Lov Describe Image

  by @lovstudio

  给纯文本模型"看图"：调用智谱 GLM-4V-Flash（免费）把图片转成文字描述。当用户要求描述/识别/读取图片，或任务里出现图片文件（截图/图表/照片）而当前模型无法直接看图时，优先调用本 skill。需要图片磁盘路径，可附带具体问题。

• Dead Code Sweep

  by @zenobi-us

  This skill should be used when cleaning up codebases that have accumulated dead code, redundant implementations, and orphaned artifacts — especially codebases maintained by coding agents. Triggers on "find dead code", "clean up…

• Code Comments

  by @zenobi-us

  Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline documentation—file headers, function docs, architectural decisions, or explanatory…

• Create New Bun Package Repo

  by @zenobi-us

  Use when creating new Bun packages from zenobi-us/bun-module template - automates repo creation, cloning, and setup using GitHub CLI; note setup.sh runs non-interactively with defaults requiring manual package.json updates