Software Development AI agent skills

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

• Claude Code

  by @taracodlabs

  Delegate coding and file edits to Anthropic Claude Code CLI

• Pokemon Player

  by @taracodlabs

  Automate Pokémon games via headless emulation + RAM reading

• Windows Registry

  by @taracodlabs

  Read, write, query Windows Registry via PowerShell provider

• Blogwatcher

  by @taracodlabs

  Monitor RSS / Atom feeds for new posts (Python feedparser)

• Gif Search

  by @taracodlabs

  Search and fetch Tenor GIFs (free Tenor API key required)

• Github Repo Management

  by @taracodlabs

  GitHub repos: create, clone, fork, archive (gh CLI + git)

• Ocr And Documents

  by @taracodlabs

  Extract text from PDFs, images, scans, Word docs (Python)

• Ascii Art

  by @taracodlabs

  ASCII text banners and box art (pyfiglet, cowsay, boxes)

• Wsl Bridge

  by @taracodlabs

  Run Linux in WSL from Windows; share files between hosts

• Minecraft Modpack Server

  by @taracodlabs

  Set up a modded Minecraft server (NeoForge or Forge)

• Github Auth

  by @taracodlabs

  GitHub auth setup via gh CLI, SSH keys, HTTPS PATs

• Codex

  by @taracodlabs

  Delegate coding tasks to OpenAI Codex CLI

• Code Execution

  by @taracodlabs

  Running scripts and code on Windows

• Setup

  by @hashgraph-online

  Install or initialize HOL Guard local runtime protection for Claude Code. Use when the user explicitly asks to install, enable, set up, or repair HOL Guard.

• Generating Images

  by @spencerpauly

  Generate or edit images using the OpenAI Image API (gpt-image-2). Use when the user asks to generate, create, draw, render, illustrate, mock up, or edit an image, icon, logo, mockup, illustration, OG image, blog hero, marketing…

• Phone Use

  by @pockebot

  Use OpenPocket MCP tools to inspect or control an Android emulator, physical Android phone, Android TV, or ADB-backed app. Trigger for phone use, Android automation, mobile UI testing, emulator control, physical-device control,…

• Updating Npm Package

  by @spencerpauly

  Safely update an npm package by checking npmjs.com for the latest version, reading release notes, and handling minor vs major upgrades differently. For minor updates, just do it. For major updates, find the upgrade guide,…

• Best Of N Solving

  by @spencerpauly

  Solve a hard problem by trying multiple approaches in parallel using isolated git worktrees. Each attempt runs in its own branch, and the best solution is selected. Use for complex refactors, tricky bugs, or architectural…

• Grinding Until Pass

  by @spencerpauly

  Keep iterating on code changes until the tests pass, the build succeeds, or linting is clean. Runs in a tight loop of fix → run → check → repeat. Use when you want the agent to autonomously grind through test failures or build…

• Clash Of Clans Play

  by @pockebot

  Play Clash of Clans on mobile with autonomous tactical decisions. Use when the user asks to attack, farm resources, push trophies/rank, run Builder Base attacks, collect rewards, or manage daily village upgrades in Clash of Clans.

• Parallel Code Review

  by @spencerpauly

  Run four parallel read-only subagents that each review the same diff from a different lens — security, performance, correctness, and readability — then merge findings into one report. Use before merging large or risky PRs.

• Verifying In Browser

  by @spencerpauly

  After making code changes, start the dev server, open the app in Cursor's built-in browser, and verify everything works — check rendering, console errors, and network health. Use proactively after any UI or API change.

• Switching Projects

  by @spencerpauly

  Switch the current Cursor workspace to a different project directory using the cursor-app-control MCP. Use when the user asks to switch projects, open another repo, jump to a different codebase, or move to a worktree.

• Visual Qa Testing

  by @spencerpauly

  Visually QA a web application by launching it in Cursor's built-in browser, taking screenshots, checking console errors, and auditing network requests. Use after making UI changes to verify they look correct.

• Building Skills From Patterns

  by @spencerpauly

  When the same multi-step workflow repeats in Cursor (user corrections or agent redos), capture it as a new SKILL.md under .cursor/skills/ so future sessions load it automatically.

• Babysitting Pr

  by @spencerpauly

  Monitor a pull request for CI failures, review comments, and merge conflicts — then fix them automatically. Use when a PR is open and you want the agent to keep it merge-ready.

• Screenshotting Changelog

  by @spencerpauly

  Generate a visual changelog or PR description by taking before/after screenshots of UI changes using Cursor's built-in browser. Use when preparing a PR with visual changes.

• Converting Css Modules To Tailwind

  by @spencerpauly

  Migrate CSS Modules (.module.css/.module.scss) to Tailwind utility classes. Handles styles object removal, className interpolation, composition, and global overrides.

• Monitoring Terminal Errors

  by @spencerpauly

  Watch running terminal processes for crashes and stack traces. When an error appears, navigate to the failing file and line, diagnose, and fix it automatically.

• Database Design

  by @spencerpauly

  Design database schemas — tables, relationships, indexes, constraints, and ORM setup. Covers relational design, normalization, and common patterns.

• Tailing Build Output

  by @spencerpauly

  Monitor a build process (webpack, turbo, docker) for warnings and errors as they stream. Summarize issues and fix them before the build finishes.

• Systematic Debugging

  by @spencerpauly

  Structured debugging methodology — reproduce, isolate, hypothesize, verify. Covers git bisect, binary search, logging, and minimal reproduction.

• Python Tdd With Uv

  by @spencerpauly

  Test-driven development in Python using uv as the package manager. Covers the red-green-refactor cycle, vertical slicing, and uv project setup.

• Auto Type Checking

  by @spencerpauly

  Run TypeScript type checking after file edits and immediately flag type errors before moving on. Uses Cursor hooks for automatic enforcement.

• Detecting Port Conflicts

  by @spencerpauly

  Detect EADDRINUSE and port conflicts, find what's using the port, and resolve it by killing the process or suggesting an alternative port.

• Finding Dev Server Url

  by @spencerpauly

  Scan running terminals for dev server URLs (localhost ports), report them, and optionally open the app in Cursor's built-in browser.

• Dark Mode Testing

  by @spencerpauly

  Toggle between light and dark mode in Cursor's browser, screenshot both states, and flag missing token mappings or contrast issues.

• Adding Api Docs

  by @spencerpauly

  Generate OpenAPI/Swagger documentation for an API, including endpoint schemas, request/response types, and interactive docs UI.

• Creating Pr

  by @spencerpauly

  Create a clean, review-ready pull request with a good title, structured description, linked issues, and appropriate reviewers.

• Verifying Markdown Formatting

  by @spencerpauly

  Verify that a Markdown file has correct formatting — headings, lists, links, code blocks, spacing, and consistent style.

• Suggesting Cursor Rules

  by @spencerpauly

  When the user repeats the same correction or convention multiple times, suggest a Cursor rule to encode it permanently.

• Prompt Engineering

  by @spencerpauly

  Write effective prompts for LLMs — structure, few-shot examples, chain-of-thought, system prompts, and output parsing.

• Api Smoke Testing

  by @spencerpauly

  Start the dev server, discover API routes from the codebase, hit every endpoint, and report which ones return errors.

• Exporting To Png

  by @spencerpauly

  Export code, terminal output, diagrams, or UI components to PNG images using headless browser rendering or CLI tools.

• Adding Analytics

  by @spencerpauly

  Add PostHog analytics to a web application, including event tracking, page views, feature flags, and session replay.

• Auditing Performance

  by @spencerpauly

  Audit and optimize application performance, including bundle size, rendering, database queries, and Core Web Vitals.

• React Native Patterns

  by @spencerpauly

  Build mobile apps with React Native and Expo — navigation, platform-specific code, performance, and native modules.

• Adding Stripe

  by @spencerpauly

  Integrate Stripe payments into a web application, including checkout sessions, webhooks, and customer portal.

• Reviewing Code

  by @spencerpauly

  Perform a thorough code review focused on correctness, maintainability, performance, and best practices.

• Writing Commit Messages

  by @spencerpauly

  Write clear, conventional commit messages with proper type prefixes, scopes, and body content.

• Adding Error Tracking

  by @spencerpauly

  Add Sentry error tracking, performance monitoring, and source maps to a web application.

• Incident Response

  by @spencerpauly

  Handle production incidents — triage, mitigate, communicate, and write postmortems.

• Curriculum Crosswalk

  by @GarethManning

  Compares two or more band-tagged frameworks and produces a framework-neutral topic matrix showing coverage and gaps across all inputs, plus an optional reference-centric PLC crosswalk document when a reference framework is…

• Adaptive Hint Sequence Designer

  by @GarethManning

  Generate a cascading hint sequence for a problem type, revealing progressively without giving answers. Use when designing tutoring dialogues or scaffolded worksheets.

• Skylos

  by @duriantaco

  Run, interpret, or modify Skylos safely. Use when the user asks to scan code with Skylos, explain SKY-* findings, triage dead-code false positives, audit security/secrets/SCA/LLM behavior, update Skylos rules/docs/CI, benchmark…

• Harness Engineering

  by @TencentBlueKing

  Harness Engineering 编排器——为 AI Agent 构建运行环境规范。 通过触发词路由到两个子 skill：harness-generating（规范文档生成/修正） 和 harness-gardening（文档一致性巡检与修复）。 Use this skill whenever the user mentions Harness Engineering, AI Agent 运行环境, 驾驭工程, Agent 规范, 上下文工程,…

• Tapd Story Pipeline

  by @TencentBlueKing

  单需求实现流水线——把一个 TAPD 需求从零推进到代码提交。自动串联技术澄清、 开发计划、任务拆分、TDD 实现、架构/安全校验、代码提交六个阶段。 Use this skill whenever the user mentions 需求实现, 实现需求 #ID, 开发需求, TDD 开发单个需求, story pipeline, single story, 独立需求, 紧急需求, bug 修复, hotfix, or any…

• Tapd Iteration Runner

  by @TencentBlueKing

  TAPD 迭代调度器——批量开发一个迭代中的全部需求。自动完成环境初始化、 需求依赖分析、逐需求调度 pipeline 实现、迭代汇总报告四段编排。 Use this skill whenever the user mentions 迭代执行, 开发迭代, 批量需求实现, TDD 迭代, dry run, batch requirement implementation, TAPD iteration development,…

• Tapd Product Discovery

  by @TencentBlueKing

  Use when work starts before a complete PRD exists, including 产品前置, 产品调研, 用户调研, 竞品分析, PRD, 原型, 想法建单, 老板需求, 需求来源, 产品父单, 角色拆单, 设计子单, 前端子单, 后端子单, 页面原型 Spec, BKUI 原型, HTML 原型, 原型评审, product discovery, product research, PRD drafting,…

• Harness Gardening

  by @TencentBlueKing

  文档园艺——持续维护 harness-engineering 产出的文档与项目实际状态的一致性。 支持 PR 轻量检查（代码变更后按需触发受影响维度）、全量深度扫描（十二维度完整检测） 和定向检测（targeted，指定单个组件/维度进行针对性巡检）。 完整扫描后：若存在 P1，向用户列出方案并请求确认，确认后与 P0 一并修复并提交；仅有 P0 时自动修复提交。 由 harness-engineering 按维护类触发词路由调用，不独立触发。

• Smithery Homepage

  by @arcadeai-labs

  Build and edit the Smithery homepage app -- a TanStack Start + shadcn/ui web app at ~/.smithery/homepage that connects to MCP servers through the Smithery Connect API. Use this skill whenever the user wants to create, modify, or…

• Harness Generating

  by @TencentBlueKing

  Harness 规范文档生成——harness-engineering 的子 skill，负责项目上下文感知、 信息收集、五大组件与技术规范文档的生成/修正、开发地图生成及总结报告。 由 harness-engineering 按生成类触发词路由调用，不独立触发。

• Tapd Story Score

  by @TencentBlueKing

  TAPD 需求评分子技能。对需求进行工时预估、规模评分（size，斐波那契）与业务价值（RICE）评分，并更新到需求文档中。 本技能作为 tapd-story-evaluation 的子技能被调用，不独立触发。

• Tapd Story Implement

  by @TencentBlueKing

  迭代执行流水线代码实现阶段。基于 tasks.md 调用 /speckit.implement 以 TDD 模式完成全部任务。 本子 skill 不创建/切换分支，重试策略为原地修复；仅在跨 attempt 回退时做 git 路径级 checkout。 命令详见 ../references/subagent-prompt-template.md §2.5。

• Tapd Iteration Report

  by @TencentBlueKing

  迭代执行流水线的收尾阶段。当迭代内所有需求 phase 均为 committed 后触发， 扫描 commit.md 生成 changelog，汇总研发效能数据写入 summary.md， 清理临时文件，递增 patch 版本号，最终提交并推送至远程仓库。

• Tapd Iteration Init

  by @TencentBlueKing

  迭代执行流水线启动器。分三个阶段执行：信息检查（验证 git 环境、获取迭代信息、 解析迭代分支）→ 恢复检测（已有状态文件时判定恢复策略）→ 新流程初始化（创建分支、 迭代目录和 iteration-state.json）。

• Tapd Story Commit

  by @TencentBlueKing

  迭代执行流水线提交阶段。在主会话中直接执行（不走 subagent），负责： 变更统计、成本数据汇总、构建 commit 信息、git 提交、TAPD 状态更新。 是 pipeline 中唯一在主会话执行的子 skill。

• Developing With Turbo Drive

  by @hotwired-laravel

  Develops with Turbo Drive for SPA-like navigation. Activates when configuring page morphing with x-turbo::refreshes-with; working with data-turbo, data-turbo-track, data-turbo-permanent, or data-turbo-preload attributes;…

• Developing With Turbo Basics

  by @hotwired-laravel

  Basics of developing with Turbo Laravel. Activates when starting a new Turbo Laravel project; using dom_id, dom_class, turbo_stream(), or turbo_stream_view() helpers; working with Blade components like x-turbo::frame,…

• Temps

  by @gotempsh

  Manage, deploy, operate, and instrument applications with Temps. Use this skill whenever the user mentions Temps, `@temps-sdk/cli@0.1.37`, deploying or migrating an app to Temps, projects, environments, services, domains,…

• CTF•Web 漏洞

  by @asdfgh1445

  用于 XSS、SQL 注入、SSTI、SSRF、XXE、JWT、鉴权绕过、文件上传、请求走私、OAuth/OIDC、SAML 与原型污染等 Web 类 CTF 题;触发名:ctf-web

• Temps Best Practices

  by @gotempsh

  Best-practices reference for preparing and instrumenting applications on Temps. Covers the app runtime contract (`.temps.yaml` health, HOST/PORT, readiness, SIGTERM, replicas, migrations) and production observability (errors,…

• Temps Cli

  by @gotempsh

  Operate Temps through the pinned `@temps-sdk/cli` package with bunx or npx. Use when the user mentions Temps CLI, `@temps-sdk/cli`, a CLI command, or asks to deploy, configure, inspect, automate, or administer Temps from a…

• Temps Plugin

  by @gotempsh

  Design, build, test, and distribute external Temps plugins with TypeScript/Bun; provide development and local-testing guidance for existing Rust plugins. Use for creating a plugin, adding an embedded console UI or…

• Add React Analytics

  by @gotempsh

  Add Temps analytics to React applications with comprehensive tracking capabilities including page views, custom events, scroll tracking, engagement monitoring, session recording, and Web Vitals performance metrics. Use when the…

• Add Error Tracking

  by @gotempsh

  Add Temps error tracking to applications using the Sentry-compatible SDK. Temps exposes a Sentry-compatible DSN that works with the official Sentry SDK for each language/framework — no code changes beyond initialization are…

• Temps Mcp Setup

  by @gotempsh

  Configure Temps as an MCP (Model Context Protocol) server so AI assistants can interact with a Temps instance directly -- listing/inspecting projects and deployments, and (when write mode is enabled) triggering deployments with…

• Add Session Recording

  by @gotempsh

  Add privacy-aware session recording and replay to React applications using the Temps SDK. Captures user interactions for playback while respecting privacy through input masking, element blocking, and GDPR-compliant consent…

• Deploy To Temps

  by @gotempsh

  Deploy applications to the Temps platform with automatic framework detection, Dockerfile generation, and container orchestration. Supports Next.js, Vite, React, Node.js, Python, Go, Rust, Java, and C# applications. Use when the…

• Add Node Sdk

  by @gotempsh

  Integrate the Temps Node.js SDKs for server-side platform access, KV storage, and Blob storage. Use when the user wants to: (1) Call the Temps platform API from Node.js (deployments, projects, analytics, session replay, etc.),…

• Strix•CSRF 测试

  by @asdfgh1445

  Strix CSRF 测试手册,覆盖 token 绕过、SameSite、CORS 误配与状态变更滥用;触发名:strix-csrf

• Strix•Katana 用法

  by @asdfgh1445

  Strix Katana 爬虫命令手册,覆盖深度、JS 抓取与稳定并发控制;触发名:strix-katana

• Strix•XSS 测试

  by @asdfgh1445

  Strix XSS 测试手册,覆盖反射型、存储型、DOM 型向量与 CSP 绕过;触发名:strix-xss

• Bevy Master

  by @thedivergentai

  Bevy ECS hub for this library. Routes the docs-first Bevy domain skills. Use when starting a Bevy game, choosing ECS boundaries, or picking a Bevy skill. The parity matrix is the routing table. Keywords: Bevy, ECS, bevy-master,…

• Codex Autoresearch

  by @TheGreenCedar

  Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests…

• Bevy Performance

  by @thedivergentai

  Docs-first stub for Bevy runtime cost. Godot counterpart: godot-performance-optimization. Not a full port. Keywords: Bevy, parallel systems, chain, FrameTimeDiagnosticsPlugin, Handles.

• Bevy Debugging Profiling

  by @thedivergentai

  Docs-first stub for Bevy logs and diagnostics. Godot counterpart: godot-debugging-profiling. Not a full port. Keywords: Bevy, LogPlugin, DiagnosticsPlugin, FrameTimeDiagnosticsPlugin.

• Bevy Project Foundations

  by @thedivergentai

  Docs-first stub for a Bevy Rust project layout. Godot counterpart: godot-project-foundations. Not a full port. Keywords: Bevy, Cargo, features, project layout.

• Bevy Shaders

  by @thedivergentai

  Docs-first stub for Bevy shaders. Godot counterpart: godot-shaders-basics. Keywords: Bevy, shader, material, bevy_shader, bevy_material, StandardMaterial.

• Bevy Testing Patterns

  by @thedivergentai

  Docs-first stub for Cargo tests around Bevy work. Godot counterpart: godot-testing-patterns. Not a GdUnit port. Keywords: Bevy, cargo test, Rust, libtest.

• Bevy Character Movement

  by @thedivergentai

  Docs-first stub for Bevy character movement. Godot counterpart: godot-characterbody-2d. Not a full port. Keywords: Bevy, movement, ECS, fixed timestep.

• Bevy Ecs Composition

  by @thedivergentai

  Docs-first stub for Bevy entity composition. Godot counterpart: godot-composition. Not a full port. Keywords: Bevy, ECS, Component, Query, systems.

• Bevy Camera Systems

  by @thedivergentai

  Docs-first stub for Bevy cameras. Godot counterpart: godot-camera-systems. Not a full port. Keywords: Bevy, Camera, Camera2d, Camera3d, Transform.

• Bevy Physics 2d

  by @thedivergentai

  Docs-first stub for Bevy 2D physics. Godot counterpart: godot-2d-physics. Not a full port. Keywords: Bevy, physics, 2D, ECS, collision, gaps.

• Bevy Physics 3d

  by @thedivergentai

  Docs-first stub for Bevy 3D physics. Godot counterpart: godot-physics-3d. Not a full port. Keywords: Bevy, physics, ECS, 3D.

• Svc Pivoting

  by @s0ld13rr

  Turn a foothold into a RELIABLE pivot (SOCKS tunnel + persistent shell) so internal volume never rides a fragile stateless RCE. Use the moment you have code-exec on a dual-homed/edge host and need to reach an internal segment.…

• Web Deserialization

  by @s0ld13rr

  Insecure deserialization to RCE for web apps. Use when the app deserializes attacker-controlled data - cookies/tokens/hidden fields/params that are serialized blobs, VIEWSTATE, Java/PHP/.NET/Python/Node apps. Triggers - base64…

• Svc Web Server

  by @s0ld13rr

  Web SERVER software (not app-layer) attack techniques — server misconfigs, known server CVEs, path traversal, exposed status/config. Use when you fingerprint the web server itself (for app-layer bugs use the web-<class> skills).…

• Web Ssti

  by @s0ld13rr

  Server-Side Template Injection detection→engine-fingerprint→RCE for web apps. Use when user input renders into a server-side template (names, greetings, email/PDF/report generators, error pages, profile fields) and math payloads…

• Mcp Client

  by @coleam00

  Universal MCP client for connecting to any MCP server with progressive disclosure. Wraps MCP servers as skills to avoid context window bloat from tool definitions. Use when interacting with external MCP servers (Zapier,…