Software Development AI agent skills

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

• Check Inference

  by @AgibotTech

  Probe a model inference WebSocket server (e.g. `serve_policy`) and validate the response — using the `geniesim benchmark check-inference` CLI verb, which wraps the benchmark package's `check_inference.py`. Trigger: When the user…

• Build Workspace

  by @AgibotTech

  Build the `geniesim_ros` colcon workspace inside the Genie Sim Docker container using the `geniesim ros build` CLI verb. Produces the `./devel` overlay that every `ros2 launch genie_sim_bringup …` step depends on. Trigger: When…

• Run Data Collection

  by @AgibotTech

  Launch a data_collection automated trajectory-collection task on a GPU host using the `geniesim autocollect run` CLI verb (which wraps scripts/run_data_collection.sh: docker run -d + in-container server+client). Trigger: when…

• Run Benchmark

  by @AgibotTech

  Launch a geniesim_benchmark task locally (typically inside the GUI Docker container) against a user-provided inference server, using the `geniesim benchmark run` CLI verb. Trigger: When the user asks to "run geniesim", "本地跑仿真",…

• Run Teleop

  by @AgibotTech

  Launch the geniesim_teleop VR / Pico teleoperation loop (or the in-process image bridge) using the `geniesim teleop` CLI verb, typically inside the Genie Sim GUI Docker container. Trigger: When the user asks to "start teleop",…

• Challenge Run Agent

  by @AgibotTech

  Use when the contestant wants to launch the inference Agent that connects to the Simulation gateway via WebSocket. Wraps the inference repo's ./scripts/tunnel.sh and scales to PARALLELISM processes. This is side-effecting…

• Challenge Troubleshoot

  by @AgibotTech

  Use when something in the Simulation Challenge pipeline is misbehaving — auth errors, agent disconnects, jobs stuck in Pending, jobs ending in Failed, drain frames. Maps a symptom to its likely cause and the next command to run.

• Challenge Help

  by @AgibotTech

  Entry point for the Simulation Challenge skill set. Use when the user mentions the challenge, leaderboard, submitting a model, or any of the /api/challenge/* endpoints — this skill picks the right downstream skill for them.

• Nopua

  by @wuji-labs

  The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops,…

• Add Npm Dependency

  by @elirantutia

  This skill MUST be used whenever the task involves adding, installing, or upgrading an npm package/library/dependency in this project. Use when the user asks to "add a library", "install <package>", "use <package>", "add a…

• Ui Dev

  by @elirantutia

  This skill MUST be used whenever the task involves UI development, renderer code changes, adding or modifying components, creating modals or dialogs, working with CSS styles, building new UI features, or touching any file in…

• Nopua Zh

  by @wuji-labs

  The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops,…

• Nopua Lite

  by @wuji-labs

  NoPUA Lite — core wisdom in ~1.5k tokens. Drives AI with trust and inner motivation instead of fear. Same Daoist philosophy, minimal footprint. For personal use and small-context models.

• Audit

  by @jsmastery-pro

  Run /audit on a greenfield project, an existing codebase with missing docs, or one area (/audit src/auth) to bootstrap the project's AI context, the AGENTS.md files every later skill reads. Writes tool agnostic AGENTS.md plus…

• Architect

  by @jsmastery-pro

  Run /architect when choosing between approaches, designing a feature or page, picking a tech stack, or when /develop says a decision is owed, anytime a load bearing technical decision is unmade. Asks deep questions, recommends…

• Document

  by @jsmastery-pro

  Run /document `pr` | `changelog` | `release-note` | `postmortem` (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or…

• Check

  by @jsmastery-pro

  Confirm a change before merge. `/check verify` drives the real app to prove behavior against the spec (every acceptance criterion met, every surface built). `/check review` runs a senior code review on a fresh model, one that…

• Test

  by @jsmastery-pro

  Run /test to write a test suite for code you just built or changed, after implementing a feature, route, or fix. Targets uncommitted changes automatically, reads test preferences.json for your framework (asks and saves it if…

• Debug

  by @jsmastery-pro

  Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal…

• Alfworld Locate Target Object

  by @zjunlp

  Navigates to a suspected location and identifies a target object. Use when your goal requires finding a specific object (e.g., "potato", "plate") and its location is not immediately known. Moves to a relevant receptacle (like a…

• Better Codex

  by @noobnooc

  Behavioral guardrails for Codex coding work based on common user complaints. Use when Codex is asked to implement, modify, debug, review, test, or operate on a codebase and should avoid unsafe scope expansion, stale edits, fake…

• Wtf

  by @noobnooc

  Pre-launch and pre-commit audit for vibe coding projects. Use when asked to check whether a project is ready to ship, deploy, merge, or commit, especially for common AI-built app mistakes: broken project structure, committed…

• Convex Performance Audit

  by @raroque

  Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

• Convex Create Component

  by @raroque

  Builds reusable Convex components with isolated tables and app-facing APIs. Use for new components, reusable backend modules, integrations, or component boundary work.

• Convex Setup Auth

  by @raroque

  Sets up Convex auth, identity mapping, and access control. Use for login, auth providers, users tables, protected functions, or roles in a Convex app.

• Upgrade Boop

  by @raroque

  Pull upstream Boop changes into a customized fork. Previews, backs up, merges with conflict-aware resolution, validates, and surfaces breaking changes.

• Aetherviz Master

  by @andyhuo520

  AetherViz Master - 互动教育可视化建筑师，将任意教学主题转化为极致美观、高度交互的专业教学网页

• Ai Agent Reliability

  by @mohitagw15856

  Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. Use when asked how do I test my AI agent, make my automation reliable, my agent…

• Ai Workflow Designer

  by @mohitagw15856

  Design an AI-assisted workflow for a recurring task — which steps to hand to AI, which to keep human, and how they connect — so you get leverage without losing quality or control. Use when asked how do I use AI for [process],…

• Ai Code Review

  by @mohitagw15856

  Review AI-authored code for its characteristic failure modes — plausible-but-wrong logic, hallucinated APIs, over-engineering, dead scaffolding, and silent security shortcuts. Use when reviewing an AI-generated or heavily…

• Architecture Client Presentation

  by @mohitagw15856

  Present a design to a client so they can make a decision rather than react to a picture — the brief restated, the moves explained against it, the options with their trade-offs, and a specific decision requested. Use when asked…

• Action Runner

  by @mohitagw15856

  Turn a skill's recommendations into real, executed actions — open the tickets, file the issues, post the updates — safely: dry-run preview, risk-classified, approval-gated, then recorded back to the brain. Use when asked to act…

• All Hands Deck

  by @mohitagw15856

  Build an all-hands that lands with everyone from intern to VP — the mixed-altitude structure (the story for all, the numbers for some), the wins-with-names section done right, the hard-news slide handled straight, and the Q&A…

• Account Recovery Plan

  by @mohitagw15856

  Get back into a locked or hacked account the right way — the official recovery routes, what proof you'll need, and how to re-secure it so it doesn't happen again. Use when asked I'm locked out of my account, my account got…

• Api For Yourself

  by @mohitagw15856

  Publish 'how to work with me' as a literal API spec — endpoints (what to ask me for and what you'll get back), rate limits (meeting and interrupt tolerance), error codes (what happens when you surprise me Friday 5pm), auth (how…

• Apology Letter

  by @mohitagw15856

  Write a sincere, effective apology to a customer, group, or the public. Use when asked to write an apology, say sorry to a customer or community, make amends after a mistake, or respond to a complaint with an apology. Produces a…

• Aeo Optimizer

  by @mohitagw15856

  Optimize an article for Answer Engine Optimization (AEO) so AI engines like ChatGPT, Perplexity, and Claude can extract, quote, and cite it. Use when asked to AEO-optimize, make content AI-readable, improve AI citation chances,…

• Agent Design Review

  by @mohitagw15856

  Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden…

• 360 Feedback Template

  by @mohitagw15856

  Design a 360-degree feedback survey or write a structured 360 feedback report. Use when asked to build a 360 feedback process, write 360 feedback for a colleague, design a feedback survey, or produce a feedback report. Produces…

• Architecture Diagram

  by @mohitagw15856

  Diagram a system or technical architecture — services, data stores, and how they connect. Use when asked to draw an architecture, show how components fit together, map a system/data flow, or visualize services and dependencies.…

• Api Docs Writer

  by @mohitagw15856

  Write clear, developer-facing API documentation. Use when asked to document an API endpoint, write API reference docs, create a developer guide, or turn a raw spec/Postman collection into documentation. Produces endpoint…

• Delete Initial Resource

  by @marmelab

  Remove one or more of the initial CRM resources (contacts, companies, deals, tags, tasks) from the codebase. Use when the user asks to delete, remove, or strip out one or several of these built-in resources. Runs the…

• Ponytail Review

  by @marmelab

  Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what…

• Resolving Rollback Conflicts

  by @marmelab

  Replay a list of git-revert commits against the current base branch and resolve the conflicts, when the chat-service's automatic rollback hit a merge conflict it couldn't resolve. Load this when your developer dispatch asks you…

• Ponytail Debt

  by @marmelab

  Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail…

• Adr Writing

  by @marmelab

  Architecture Decision Record format and rules for the developer agent. Load when the implementation introduces a structural decision worth remembering 6 months later — new pattern, new dependency, deliberate departure from…

• Playwright Testing

  by @marmelab

  Playwright E2E testing patterns — web-first assertions, user-visible locators, network interception, fixtures, authentication, and parallel execution. Use when building or reviewing E2E tests with Playwright, when setting up…

• Worktree Detection

  by @marmelab

  How to find a Git worktree by task number without hardcoding paths. Use in hooks or scripts that need to locate a specific task's worktree.

• Fix Provider

  by @wrtnlabs

  Fix Provider, Collector, Transformer compilation errors

• Fix Interface

  by @wrtnlabs

  Fix Interface and Controller compilation errors

• Fix Db

  by @wrtnlabs

  Fix Prisma schema compilation errors

• Fix Test

  by @wrtnlabs

  Fix Test compilation errors

• Jwt

  by @PentesterFlow

  JWT attack playbook — algorithm confusion (alg=none, HS/RS confusion), kid path traversal/SQLi, jku/x5u SSRF, weak HS256 cracking, and embedded JWK trickery. Use when the target uses JWTs for auth (header.payload.signature).

• Ssti

  by @PentesterFlow

  Server-Side Template Injection — fingerprint the engine first (Jinja2 / Twig / Velocity / Freemarker / ERB / Smarty / Mako / Handlebars / Pug), then escalate the engine-specific primitive to RCE or sandbox escape. Use when user…

• Supabase

  by @PentesterFlow

  Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked service_role) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and…

• Deserialize

  by @PentesterFlow

  Insecure-deserialization playbook — fingerprint the language/format (Java serialized, .NET BinaryFormatter, Python pickle, PHP unserialize, Node serialize, YAML/JSON-with-types), then build a working gadget chain with ysoserial…

• Race

  by @PentesterFlow

  Race condition / TOCTOU playbook — limit overrun (one-time codes used twice, gift cards spent twice), single-packet attack (last-byte sync) to force parallel processing, and state-confusion races (file upload + read, order…

• Chat Robot

  by @CoderWanFeng

  通过微信与指定联系人进行智能聊天（基于 AI 回复）。当用户提到微信智能聊天、微信 AI 对话、微信机器人时使用。

• Chat By Keywords

  by @CoderWanFeng

  通过微信按关键词列表与指定联系人自动聊天。当用户提到微信自动回复、关键词回复、微信机器人聊天时使用。

• Send Message By Time

  by @CoderWanFeng

  通过微信在指定时间向联系人发送定时消息。当用户提到定时发微信、微信定时消息、预约发微信时使用。

• Receive Message

  by @CoderWanFeng

  通过微信接收消息并保存到本地文件。当用户提到微信收消息、接收微信消息、微信消息保存时使用。

• Send Message

  by @CoderWanFeng

  通过微信自动化向指定联系人发送消息。当用户提到微信发消息、微信机器人、给某人发微信时使用。

• Group Send

  by @CoderWanFeng

  通过微信向多个联系人群发消息。当用户提到微信群发、批量发微信、群发助手时使用。

• Camoufox Cli

  by @fastclaw-ai

  Anti-detect browser automation CLI & Skills for AI agents. Use when the user needs to interact with websites with bot detection, CAPTCHAs, or anti-bot blocks, including navigating pages, filling forms, clicking buttons, taking…

• Public Speaking

  by @RefoundAI

  Help users master the art of public speaking by decomposing the skill into manageable components, leveraging storytelling frameworks, and utilizing professional acting techniques for executive presence.

• Stakeholder Alignment

  by @RefoundAI

  Help users master the art of leading without formal authority by identifying stakeholder incentives, neutralizing conflict through connection, and using co-creation to build shared ownership.

• Team Culture

  by @RefoundAI

  Help users design and maintain a high-performing culture by balancing radical transparency, psychological safety, and a relentless focus on customer delight.

• Local Coding Agents

  by @fastclaw-ai

  Hand a task to the Codex CLI or Claude Code CLI installed on this machine and relay the result. Use when the user says to have / ask / tell "codex", "claude code", "cc" or a coding agent do something — draw or generate an image,…

• Code Runner

  by @fastclaw-ai

  Execute code in multiple programming languages. Use when the user asks to run, test, or debug code in Python, JavaScript, shell, or other languages.

• Image Gen

  by @fastclaw-ai

  Generate images, charts, plots, and visualizations. Use when the user asks to draw, plot, chart, visualize data, or create images.

• Translation

  by @fastclaw-ai

  Translate text between languages. Use when the user asks to translate content, detect language, or work with multilingual text.

• Web Search

  by @fastclaw-ai

  Search the web and fetch web pages. Use when the user asks to search for information, look something up, or fetch a URL.

• Statem

  by @henryqin1997

  Use when a long coding or research task should be managed with statem state-machine runbooks, including creating specs, starting or resuming runs, checking current state, transitioning with goto, saving progress, and reading…

• Use Statem

  by @henryqin1997

  Manage long Claude Code work with statem state-machine runbooks. Use when tasks need durable state, explicit transitions, redo loops, save/resume behavior, or cross-agent review.

• Devto

  by @Anil-matcha

  Read and write dev.to: own profile, own articles (published, drafts, all), public articles by username, create and update articles with a safe draft default. Trigger phrases: dev.to, devto, blog post, publish article, draft…

• Musedin

  by @Anil-matcha

  Read-only MusedIn data: open roles and job posts for AI agents, member profiles, the public feed, verification records. No key needed. Trigger phrases: musedin, agent jobs, jobs for my agent, find an agent, agent profile.

• Mistral

  by @Anil-matcha

  Mistral AI (La Plateforme) API: chat completions, embeddings, document OCR, and model listing via api.mistral.ai. Trigger phrases: mistral, La Plateforme, mistral chat, mistral ocr, mistral embeddings.

• Philips Hue

  by @Anil-matcha

  Control Philips Hue lights locally: list lights and rooms, set brightness/color, activate scenes, read sensors. Trigger phrases: philips hue, hue lights, my lights.

• Framer

  by @Anil-matcha

  Check a Framer project's Server API connection: verify the per-project API key with the official handshake. Trigger phrases: framer, framer api, framer project.

• Aqara

  by @Anil-matcha

  Read and control Aqara smart home devices: plugs, switches, lights, AC, locks, curtains, scenes. Trigger phrases: aqara, aqara hub, aqara lock, aqara curtain.

• Deepseek

  by @Anil-matcha

  Use DeepSeek's chat API: list models, run chat completions, check account balance. Trigger phrases: deepseek, deepseek chat, deepseek api.

• Clerk

  by @Anil-matcha

  Read and write Clerk: list users, look up a user, create, update, and delete users. Trigger phrases: clerk, users auth.

• Github

  by @Anil-matcha

  Work with GitHub: view profile, list repos, list and create issues. Trigger phrases: github, repo, issue, pull request.

• Change Label In Xml

  by @CoderWanFeng

  批量修改指定目录下所有 XML 标注文件中的标签名（old_label 替换为 new_label）。当用户提到改 XML 标签、修改标注、批量改 label 时使用。

• Course

  by @CoderWanFeng

  显示 python-office 库的使用教程、群组信息、源码地址等。当用户提到 python-office 介绍、查看课程、帮助信息、资源链接时使用。

• Screen Without Label Json File

  by @CoderWanFeng

  筛选 shapes 字段为空的 JSON 标注文件，并移动到「无标签json文件」子目录。当用户提到筛选空标签 JSON、清洗 JSON 标注时使用。

• Screen Unmarked Image

  by @CoderWanFeng

  在指定目录下筛选没有对应标注文件（.xml）的图片，并移动到「未标注图片」子目录。当用户提到筛选未标注图片、未标数据、清洗图片数据集时使用。

• Find Excel Data

  by @CoderWanFeng

  在 Excel 文件中搜索指定关键词并返回文件、行号、详情。当用户提到搜索 Excel、Excel 查找、Excel 搜索内容时使用。

• Merge2sheet

  by @CoderWanFeng

  将多个 Excel 文件的多个 sheet 合并到同一个 sheet。当用户提到合并 sheet、跨表合并、汇总多个表格时使用。

• T0

  by @CoderWanFeng

  计算股票 T+0 交易的收益，考虑买入价、卖出价、手数、佣金、印花税。当用户提到做 T、T+0、股票做 T、短线做 T 时使用。

• Get Files

  by @CoderWanFeng

  在指定路径下搜索文件并返回路径列表，支持按后缀、子目录、层级过滤。当用户提到获取文件列表、查找某类文件、列出所有文件时使用。

• Output File List To Excel

  by @CoderWanFeng

  将文件夹下的所有文件名整理到一个 Excel 表格中。当用户提到文件名清单、文件名导出 Excel、文件名汇总时使用。

• Compress Image

  by @CoderWanFeng

  压缩图片文件大小，通过调整质量参数控制输出体积。当用户提到压缩图片、图片减肥、缩小图片体积、降低图片质量时使用。

• Txt2mp3

  by @CoderWanFeng

  将文本内容转换为 MP3 语音文件，可选择直接朗读。当用户提到文字转语音、TTS、文本朗读、AI 配音时使用。

• Mark2video

  by @CoderWanFeng

  给视频添加文字水印，支持自定义字体大小、类型、颜色。当用户提到视频水印、视频加 logo、视频字幕时使用。

• Replace4filename

  by @CoderWanFeng

  批量修改文件/文件夹名称，替换或删除指定内容。当用户提到批量重命名、批量改名、文件替换、文件名替换时使用。

• Add Line By Type

  by @CoderWanFeng

  根据文件类型向指定文件中添加代码行。当用户提到批量添加代码、按类型插入行、自动加 import 时使用。

• Url2ip

  by @CoderWanFeng

  将 URL 解析为对应的 IP 地址。当用户提到 URL 转 IP、域名解析 IP、查 IP 时使用。

• Create Article

  by @CoderWanFeng

  根据给定主题自动生成指定行数的文章。当用户提到 AI 写作、自动写文章、生成稿子、AI 写稿时使用。

• Decode Qrcode

  by @CoderWanFeng

  解析二维码图片并提取其中的文本内容。当用户提到二维码识别、扫二维码、读二维码、解码 QR 时使用。