Software Development AI agent skills

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

• Dual Agent Collaboration

  by @yunshu0909

  让 Codex 与 Claude Code 通过本机 CLI 组成“主执行者 + 独立审查者”的对称协作闭环。用于用户要求两个模型一起完成、交叉校核、独立审查、修到 ACK，或任务涉及产品需求收敛、复杂方案、跨模块开发、迁移、安全、重要重构和高质量交付时；无论从 Codex 还是 Claude Code 启动，都由当前模型主持，并完整调用另一方完成需求挑战、方案门禁、实现冷审和最终验收。

• Req Change Workflow

  by @yunshu0909

  已有功能的需求变更闭环（门禁式七步）。触发硬条件：要改的功能已经实现并跑起来了。当用户说"改需求""需求变更""调整交互""改功能""重构流程"，或改动容易散到多个文件、碰到鉴权/存储/配置/权限、需要可靠验证 + 回滚方案时使用。流程：锁 scope 写 change brief → 从代码确认当前行为（不靠记忆和假设）→ 影响面与风险评估 + 回滚计划 → 提出新设计等用户批准（**未获批准绝不动代码**）→ 小而局部的 diff →…

• Git Push

  by @yunshu0909

  把项目推送到 GitHub，三种模式自动判断：**首次推送**（大文件扫描 → 生成 .gitignore → git init → gh 建仓 → 推送）、**日常更新**（commit + push）、**版本发布**（打 tag + 建 Release，可附下载文件）。核心原则是安全第一：推之前必扫大文件和敏感文件，宁可多问一句也不把不该推的东西推上去。当用户说"推到GitHub""推送到GitHub""git…

• Github Repo Search

  by @yunshu0909

  帮助用户搜索和筛选 GitHub 开源项目，输出结构化推荐报告。当用户说"帮我找开源项目"、"搜一下GitHub上有什么"、"找找XX方向的仓库"、"开源项目推荐"、"github搜索"、"/github-search"时触发。

• Polycss

  by @layoutit

  Build PolyCSS scenes that render 3D meshes, primitive shapes, or custom polygons as DOM/CSS polygon elements. Use when asked to create, port, debug, or explain PolyCSS code in vanilla JavaScript, React, or Vue.

• Building Inferencesh Apps

  by @inference-sh

  Build and deploy applications on inference.sh. Use when getting started, understanding the platform, creating apps, configuring resources, or needing an overview of inference.sh app development. Supports both Python and Node.js.…

• Google Veo

  by @inference-sh

  Generate videos with Google Veo models via inference.sh CLI. Models: Veo 3.1, Veo 3.1 Fast. Capabilities: text-to-video, cinematic output, high quality video generation. Triggers: veo, google veo, veo 3, veo 2, veo 3.1, vertex…

• Web Shader Extractor

  by @lixiaolin94

  Use when a user gives or references a webpage URL and wants to extract, reproduce, port, or locally replay a WebGL, WebGPU, Canvas, shader-like, animated background, interactive 3D, or web visual effect. Locks the target…

• Conversion Path Builder

  by @realkimbarrett

  Design the optimal funnel from click to conversion. Trigger on "funnel", "conversion path", "booked calls".

• Avatar Extraction

  by @realkimbarrett

  Use when you need to define exactly who the buyer is, what they want, what they’ve tried, and what’s driving their decisions. Trigger on "target audience", "ideal client", "who is this for", "avatar", "customer profile".

• Objection Crusher

  by @realkimbarrett

  Identify and neutralize buyer objections. Trigger on "why wouldn't someone buy", "objections", "hesitation", "conversion issues".

• Blog 3p Human Handoff

  by @flaqai

  编译/校验博客 3P 统一可视化富文本载荷，生成 WQ 作者自查或 WR 独立审稿后由 G 验收的人工发布交接包及公开页回传证据；不操作平台编辑器。

• Blog 3p Writer

  by @flaqai

  在博客 WQ/WR 双线工作流中连续完成搜索导向调研、写作、图片和载荷；默认做同上下文对抗式自查，高风险升级独立 R。用于研究、撰写、修订和准备人工发布文章包。

• Blog 3p Review

  by @flaqai

  仅在博客 3P 的 WR 独立审稿路线审阅证据、文章和人工交付包；输出有证据的问题项、独立 FULL_REVIEW 或有限 R-Δ。默认 WQ 作者自查不调用本角色。

• Perfect Company List

  by @growthenginenowoslawski

  Build a near-complete company list for any ICP by learning how your real customers label themselves, pulling every industry and keyword they use, judging every single row with a cheap AI model (Jev or gpt-5-nano), and running a…

• Playbook Social Posts

  by @growthenginenowoslawski

  Fetches the most recent usable LinkedIn post from a company page OR a person's profile and stores the post content itself, with an optional AI personalization line on top. Triggers on "what did they post about", "recent LinkedIn…

• Playbook Job Posting Language

  by @growthenginenowoslawski

  Produces a copy-ready clause about a role a company is currently hiring for, filtered by language the client cares about (for example "cold call", "outbound prospecting", "Salesforce"). Triggers on "they're hiring", "job posting…

• Playbook Tech On Website

  by @growthenginenowoslawski

  Decides which named technologies a company actually runs on its website, verified against the live site. Triggers on "find companies using Shopify", "they're on HubSpot", "tech stack targeting", "technographics", "who uses…

• Positive Reply Scoring

  by @growthenginenowoslawski

  Pulls replies from a Smartlead campaign, classifies each as positive/neutral/negative/OOO/bounce/unsubscribe using Claude, and reports the positive reply rate — the north-star metric for cold email. Use when the user wants to…

• Playbook Social Link Finding

  by @growthenginenowoslawski

  Resolve a company domain to its verified official social profile URLs (LinkedIn, X, Facebook, Instagram, YouTube, TikTok). Triggers on "find their LinkedIn", "get the company LinkedIn URL", "find their Instagram", "we need…

• Playbook Name To Other Prospects

  by @growthenginenowoslawski

  Names 2 other right-fit people at the prospect's own company so an email can ask "is this you or them?" without ever naming the person being emailed. Triggers on "name two other people at the company", "who else works there",…

• Personalization Subagent Pattern

  by @growthenginenowoslawski

  Reusable approval-loop pattern for fanning out lead personalization across parallel Claude Code Task sub-agents. Shows the user 1 sample personalization, collects feedback, runs 10 more, approves, runs 10 more — stops when 2…

• Disco Like

  by @growthenginenowoslawski

  Find lookalike companies via DiscoLike's 65M+ business domain database. Search by seed domains ("find companies like clay.com and apollo.io") or natural-language ICP text ("B2B cold email outreach"). Supports negation domains…

• Deliverability Test Public

  by @growthenginenowoslawski

  Compare reply rates, bounce rates, and positive reply rates broken down by inbox type (SMTP / Gmail / Outlook) for a Smartlead account. Use when you want to know "which inbox type delivers best" or when debugging unexplained…

• Icp Prompt Builder

  by @growthenginenowoslawski

  Interactive loop that builds and tunes an AI prompt for evaluating whether a company fits a client's ICP. Run after any list-building skill (disco-like, blitz-list-builder, google-maps-list-builder, prospeo-full-export) to…

• Prospeo Full Export

  by @growthenginenowoslawski

  Export your entire Prospeo people search to CSV. Build filters in Prospeo's UI, then use this skill to extract every result via the API — even searches over 25K. Handles pagination, rate limiting, deduplication, and…

• Google Maps List Builder

  by @growthenginenowoslawski

  Scrape Google Maps for local businesses by category and location, output CSV ready for cold email enrichment. Best for SMB campaigns targeting restaurants, clinics, gyms, salons, contractors, etc. Uses RapidAPI Maps Data API.…

• Prospeo Search Api

  by @growthenginenowoslawski

  This skill should be used when searching for people/leads using the Prospeo Search Person API. It provides the correct API format, filter types, rate limiting patterns, and state-by-state crawling techniques to overcome the 25K…

• Zapmail Domain Setup Public

  by @growthenginenowoslawski

  Public guide: Generate short domain names, check availability, purchase on Dynadot, switch nameservers, set up on Zapmail, create inboxes, and export to your email sending platform. Requires your own Dynadot and Zapmail API…

• Progress Reading Protocol

  by @Archive228

  Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work. The orientation ritual that lets fresh-context sessions…

• Feature List Json

  by @Archive228

  Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order. The ledger fresh-context sessions read to know what's done, what's next, and what they're…

• Eval Harness

  by @Archive228

  Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed. Reuses loopkit's verifier subagent as the grader — do not build a new one.

• Sprint Contract

  by @Archive228

  Negotiate a pre-code contract between generator and evaluator personas that defines what "done" means before any code is written. Turns fuzzy specs into a testable target the evaluator can hold the generator to.

• Verification Before Completion

  by @Archive228

  Use before claiming work is complete, fixed, or passing — before committing, opening a PR, or handing off. Requires running the verification command in THIS turn and reading its output before any success claim.

• Shift Notes

  by @Archive228

  Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context. Structured prose, not JSON — the model writes prose better.

• Using Loopkit

  by @Archive228

  Use when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including clarifying questions.

• Broken Window Check

  by @Archive228

  Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.

• Self Eval Bias

  by @Archive228

  Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. Same-context grading is not review — it's rationalization.

• Structured Output

  by @Archive228

  Get JSON out of the model reliably. Prefer tool_use with a schema over prompted-JSON, validate on receive, retry on parse fail. Use when downstream code will parse the response.

• Suggest Next Features

  by @Archive228

  Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so feature_list.json stays immutable

• Systematic Debugging

  by @Archive228

  Use for ANY bug, test failure, crash, or unexpected behavior. Forces reproduce-then-isolate before proposing a fix. Stops the agent from guessing.

• Evaluator Calibration

  by @Archive228

  Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.

• Harness Stripping

  by @Archive228

  Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.

• Init Script Contract

  by @Archive228

  Author idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on.

• Secret Scan

  by @Archive228

  Catch hardcoded secrets, keys, and tokens before they get committed. Use before any commit and on any file with credentials.

• Rebase Safely

  by @Archive228

  Rebase, squash, or rewrite history without losing work or breaking shared branches. Use before any history rewrite.

• Changelog From Diff

  by @Archive228

  Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.

• Input Validation

  by @Archive228

  Validate and constrain untrusted input at the boundary. Use on any handler that accepts external data.

• Clean Commits

  by @Archive228

  Turn messy WIP into clean, atomic commits with messages that explain why. Use before opening a PR.

• Migration Writer

  by @Archive228

  Write safe, reversible database migrations for this repo's conventions. Use for any schema change.

• Kill Dead Code

  by @Archive228

  Find and remove unreachable/unused code safely. Use during cleanup or before a refactor.

• Pr From Diff

  by @Archive228

  Write a PR description a reviewer can approve fast. Use when opening any pull request.

• Kraken Setup

  by @krakenfx

  Install kraken-cli, create API credentials, and go from paper trading to live in under five minutes.

• Recipe Playground Webhook

  by @krakenfx

  Example driver: turn incoming webhook signals into validated paper trades inside a recorded session.

• Kraken Autonomy Levels

  by @krakenfx

  Progress from manual trading to full agent autonomy with controlled risk at each level.

• Recipe Playground Price Alert

  by @krakenfx

  Example driver: drive a price-level-alert hypothesis into a recorded session.

• User Profile Keeper

  by @dongshuyan

  Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete,…

• Run History Skill Upgrader

  by @dongshuyan

  Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing…

• Task Clarifier

  by @dongshuyan

  Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's…

• Code Migration

  by @anthropics

  Run a large-scale language migration with the six-step process: create the map and the rules, stress-test the rules, translate everything, compile, run it, match behavior. Use when the user wants to migrate, port, or rewrite a…

• Skill Creator

  by @ClawRunr

  Create new skills, modify and improve existing skills for JavaClaw. Use when users want to create a skill from scratch, edit or improve an existing skill, or refine a skill's description so it triggers more reliably. Also use…

• Crack

  by @ethanplusai

  Lead substantial Codex builds with one configured implementation worker and lead acceptance. Use when the user requests codex-on-crack, names a model to delegate work to, asks to run subagents through Claude, or requests a…

• Astra Flash Orchestrator

  by @ethanplusai

  Plan and execute substantial multi-file builds, features, migrations, and refactors with Astra as orchestrator and DeepSeek V4.1 Flash as the native Codex implementation worker. Use for phased planning and delegated build…

• Solid Principles

  by @decebals

  SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov,…

• Clean Code

  by @decebals

  Clean Code principles (DRY, KISS, YAGNI), naming, function design and readability. Use when code is hard to read, with long methods, unclear names, duplication or deep nesting. For how responsibilities are split across classes…

• Architecture Review

  by @decebals

  Analyze Java project architecture at macro level - package structure, module boundaries, dependency direction, and layering. Use when user asks "review architecture", "check structure", "package organization", or when evaluating…

• Concurrency Review

  by @decebals

  Review Java concurrency code for thread safety, race conditions, deadlocks, and modern patterns (Virtual Threads, CompletableFuture, @Async). Use when user asks "check thread safety", "concurrency review", "async code review",…

• Spring Boot Patterns

  by @decebals

  Spring Boot best practices and patterns. Use when creating controllers, services or repositories, or when the user asks about Spring Boot layering, wiring, configuration or exception handling. For JPA and Hibernate behaviour,…

• Performance Smell Detection

  by @decebals

  Detect potential code-level performance smells in Java - streams, collections, boxing, regex, object creation. Provides awareness, not absolutes - always measure before optimizing. For JPA/database performance, use jpa-patterns…

• Api Contract Review

  by @decebals

  Review REST API contracts for HTTP semantics, versioning, backward compatibility, and response consistency. Use when user asks "review API", "check endpoints", "REST review", or before releasing API changes.

• Java Code Review

  by @decebals

  Systematic code review for Java with null safety, exception handling, concurrency, and performance checks. Use when user says "review code", "check this PR", "code review", or before merging changes.

• Java Migration

  by @decebals

  Guide for upgrading Java projects between major versions (8→11→17→21→25). Use when user says "upgrade Java", "migrate to Java 25", "update Java version", or when modernizing legacy projects.

• Test Quality

  by @decebals

  Write high-quality JUnit 5 tests with AssertJ assertions. Use when user says "add tests", "write tests", "improve test coverage", or when reviewing/creating test classes for Java code.

• Git Commit

  by @decebals

  Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.

• Changelog Generator

  by @decebals

  Generate changelogs from git commits. Use when user says "generate changelog", "update changelog", "what changed since last release", or before preparing a new release.

• Old Coder

  by @AmazingAng

  Evidence-first development — surround the implementation with an executable spec and a gauntlet of constraints (tests, types, coverage, mutation) so line-by-line review becomes optional. Use when the user explicitly asks for…

• Makepad 2.0 Splash

  by @ZhangHanDong

  CRITICAL: Use for Makepad 2.0 Splash scripting language. Triggers on: splash language, makepad script, script_mod!, makepad scripting, splash 脚本, makepad 2.0 script, mod.state, on_render, script_eval, streaming evaluation,…

• Makepad 2.0 App Structure

  by @ZhangHanDong

  CRITICAL: Use for Makepad 2.0 app structure and Rust integration. Triggers on: makepad app, makepad getting started, app_main!, App::run, MatchEvent, AppMain, handle_event, handle_actions, ScriptVm, from_script_mod, makepad…

• Makepad 2.0 Dsl

  by @ZhangHanDong

  CRITICAL: Use for Makepad 2.0 DSL syntax and property system. Triggers on: makepad dsl, script_mod!, makepad syntax, makepad property, makepad 2.0 syntax, colon syntax, merge operator, named instance, let binding, mod.widgets,…

• Makepad 2.0 Events

  by @ZhangHanDong

  CRITICAL: Use for Makepad 2.0 event and action handling. Triggers on: makepad event, makepad action, MatchEvent, handle_event, handle_actions, on_click, on_render, on_return, on_startup, script_eval!, script_apply_eval!, button…

• Makepad 2.0 Migration

  by @ZhangHanDong

  CRITICAL: Use for migrating from Makepad 1.x to 2.0. Triggers on: makepad migration, live_design to script_mod, makepad upgrade, makepad 1.x, old syntax, new syntax, makepad breaking changes, makepad 迁移, 旧语法, LiveHook to…

• Generators

  by @rshankras

  Code generator skills that produce production-ready Swift code for common app components. Use when user wants to add logging, analytics, onboarding, review prompts, networking, authentication, paywalls, settings, persistence,…

• Analytics Setup

  by @rshankras

  Generates protocol-based analytics infrastructure with swappable providers (TelemetryDeck, Firebase, Mixpanel). Use when user wants to add analytics, track events, or set up telemetry.

• Error Monitoring

  by @rshankras

  Generates protocol-based error/crash monitoring with swappable providers (Sentry, Crashlytics). Use when user wants to add crash reporting, error tracking, or production monitoring.

• Networking Layer

  by @rshankras

  Generates a protocol-based networking layer with async/await, error handling, and swappable implementations. Use when user wants to add API client, networking, or HTTP layer.

• Logging Setup

  by @rshankras

  Generates structured logging infrastructure using os.log/Logger to replace print() statements. Use when user wants to add proper logging, replace print statements, or set up app logging.

• App Icon Generator

  by @rshankras

  Generates an app icon for macOS or iOS — a fast CoreGraphics placeholder and/or flat layered source art to finish in Icon Composer (the Liquid Glass / iOS 26+ standard). Produces appearance variants (light/dark/tinted) and…

• Consent Flow

  by @rshankras

  Generates GDPR/CCPA/DPDP privacy consent flows with granular category preferences, consent state persistence, audit logging, and ATT (App Tracking Transparency) integration. Use when user needs privacy consent UI,…

• Feedback Form

  by @rshankras

  Generates an in-app feedback collection form with category selection, text input, optional screenshot attachment, device diagnostics, and smart routing — directing happy users to App Store reviews and unhappy users to support.…

• App Extensions

  by @rshankras

  Generates app extension infrastructure for Share Extensions, Action Extensions, Keyboard Extensions, and Safari Web Extensions with data sharing via App Groups. Use when user wants to add a share extension, action extension,…

• Debug Menu

  by @rshankras

  Generates a developer debug menu with feature flag toggles, environment switching, network log viewer, cache clearing, crash trigger, and diagnostic info export. Only included in DEBUG builds. Use when user wants a debug panel,…

• Force Update

  by @rshankras

  Generates a minimum version enforcement system with hard-block and soft-prompt update flows, App Store redirect, and remote config or App Store lookup for version checks. Use when user wants force update, mandatory update, or…

• Feature Flags

  by @rshankras

  Generate feature flag infrastructure with local defaults, remote configuration, SwiftUI integration, and debug menu. Use when adding feature flags or A/B testing to iOS/macOS apps.

• Iap Finalizer

  by @rshankras

  Take a one-time in-app purchase from MISSING_METADATA to READY_TO_SUBMIT in App Store Connect — set its price schedule and localized display name/description (and optional review screenshot) via the ASC REST API. Use at Phase 6…

• Ad Attribution

  by @rshankras

  Privacy-preserving ad measurement with AdAttributionKit (SKAdNetwork's successor) — install and re-engagement attribution, conversion-value strategy under crowd anonymity, and end-to-end postback testing. Use when running paid…

• Review Response Writer

  by @rshankras

  Write professional, empathetic responses to App Store reviews that build trust and turn critics into fans. Use when responding to negative reviews, drafting templates for common review types, or improving review management…

• Llama Index Wiki

  by @chujianyun

  LlamaIndex 官方用户文档离线知识库，用于检索并回答 LlamaIndex Python 框架的安装、RAG、数据加载、索引、检索与查询、Agent、Workflow、模型、Embedding、向量库、评估、可观测性、部署、LlamaCloud 和 LlamaParse 等问题，也可生成有文档依据的示例代码与排障建议。当用户提到…

• Typesafe Wiki

  by @chujianyun

  TypeSafe AI（typesafe.ai）官方文档离线 Wiki，覆盖 Jev System One 模型、Choice/Score/Noul 问题原语、state 结构与置信度、架构 Patterns、Python/JavaScript SDK、HTTP API 参考与 Cookbooks 示例；用于查询 TypeSafe API/SDK 的接入、用法与示例。不用于其他 LLM 厂商 API、千问或百炼系列文档问题。

• Deepseek Harness Wiki

  by @chujianyun

  DeepSeek Harness 开发文档离线 Wiki，检索导航涵盖的插件开发、工具、配置、生命周期、服务、事件、LLM 适配器和 Cordis 教程。用户询问这些开发主题时使用；不用于日常产品使用、部署运维或完整 API 参考。

• Qwenwork Wiki

  by @chujianyun

  千问办公（QwenWork）官方文档 Wiki，用于查询网页端和桌面端使用、安装、工作台、技能与连接器、定时任务、IM 频道、企业管理及排障；也用于定位企业管理 API 文档。不用于千问AI平台、百炼或 DashScope 模型 API 接入，也不因普通办公任务而触发。