AI Ml AI agent skills

8,771 skills in the archive. Read a skill’s instructions or open its original repository.

• Pr Review Response

  by @bradygaster

  Teaches agents to reply to PR review comment threads after fixing issues, making resolutions traceable

• Architectural Proposals

  by @bradygaster

  How to write comprehensive architectural proposals that drive alignment before code is written

• External Comms

  by @bradygaster

  Workflow for scanning, drafting, and presenting community responses with a human review gate

• History Hygiene

  by @bradygaster

  Record reconciled final outcomes to history.md, not intermediate requests or obsolete claims

• Ci Validation Gates

  by @bradygaster

  Defensive CI/CD patterns: semver validation, token checks, retry logic, and draft detection

• Cross Machine Coordination

  by @bradygaster

  Enables squad agents on different machines to share work via git-based task queuing

• Test Discipline

  by @bradygaster

  Design assertions that prove the actual contract and fail on realistic regressions

• Ralph Two Pass Scan

  by @bradygaster

  Cuts GitHub API calls by separating lightweight list scanning from full hydration

• Release Process

  by @bradygaster

  Prepare, publish, recover, and verify Squad insider, preview, and stable releases

• Reskill

  by @bradygaster

  Extract durable operating knowledge before slimming or replacing team charters

• Client Compatibility

  by @bradygaster

  Platform detection and adaptive spawning for CLI vs VS Code vs other surfaces

• Tiered Memory

  by @bradygaster

  Three-tier agent memory model (hot/cold/wiki) for context reduction per spawn

• Versioning Policy

  by @bradygaster

  SemVer rules for Squad's stable, preview, insider, and local package versions

• Gh Auth Isolation

  by @bradygaster

  Safely manage multiple GitHub identities (EMU + personal) in agent workflows

• Session Recovery

  by @bradygaster

  Find and resume interrupted Copilot CLI sessions using session_store queries

• Git Workflow

  by @bradygaster

  Squad branching model: dev-first workflow with insiders preview channel

• Pr Screenshots

  by @bradygaster

  Capture Playwright screenshots and embed them in GitHub PR descriptions

• Humanizer

  by @bradygaster

  Tone enforcement patterns for external-facing community responses

• Secret Handling

  by @bradygaster

  Never read .env files or write secrets to .squad/ committed files

• E2e Template Testing

  by @bradygaster

  End-to-end validation of coordinator and agent template changes

• Init Mode

  by @bradygaster

  Team initialization flow (Phase 1 proposal + Phase 2 creation)

• Docs Standards

  by @bradygaster

  Microsoft Style Guide + Squad-specific documentation patterns

• Personal Squad

  by @bradygaster

  User-level AI agents that travel with you across projects

• Nap

  by @bradygaster

  Context hygiene — compress, prune, archive .squad/ state

• Reviewer Protocol

  by @bradygaster

  Reviewer rejection workflow and strict lockout semantics

• Squad Conventions

  by @bradygaster

  Core conventions and patterns used in the Squad codebase

• Model Selection

  by @bradygaster

  Determines which LLM model to use for each agent spawn

• Agent Conduct

  by @bradygaster

  Shared hard rules enforced across all squad agents

• Windows Compatibility

  by @bradygaster

  Cross-platform path handling and command patterns

• Project Conventions

  by @bradygaster

  Core conventions and patterns for this codebase

• Ai Agent Dev

  by @Snailclimb

  用于 AI Agent 开发岗位面试出题；覆盖 Agent 架构、LLM 调用、工具集成、MCP 协议、RAG、上下文工程与多 Agent 协作，强调工程落地与故障处理能力。

• Java Backend

  by @Snailclimb

  用于 Java 后端面试出题；优先围绕 Java 核心、MySQL、Redis、Spring 与项目实战，追问设计取舍、故障处理和性能优化。

• Python Backend

  by @Snailclimb

  用于 Python 后端面试出题；覆盖 Python 基础、数据库、Django/Flask、缓存与部署，强调工程落地。

• Frontend

  by @Snailclimb

  用于前端工程面试出题；覆盖 JavaScript、React/Vue、浏览器原理和性能优化，强调业务实战与工程化能力。

• Test Development

  by @Snailclimb

  用于测试开发面试出题；覆盖测试基础、用例设计、自动化测试、性能测试与安全测试，兼顾工程化落地能力。

• Java Backend Tencent

  by @Snailclimb

  用于腾讯后端面试出题；重点考察计算机基础、计网与操作系统原理，并结合业务场景验证技术选型能力。

• Ali Backend

  by @Snailclimb

  用于阿里后端面试出题；强调业务深度、项目落地和中间件选型能力，关注复杂场景下的取舍与闭环。

• Bytedance Backend

  by @Snailclimb

  用于字节后端面试出题；以算法与编码能力为第一门槛，同时考察高并发场景下的系统设计能力。

• Algorithm

  by @Snailclimb

  用于算法面试出题；重点评估复杂度分析、边界处理和优化能力，区分背题与真实理解。

• System Design

  by @Snailclimb

  用于系统设计面试出题；聚焦容量估算、可用性与一致性权衡、可观测性和故障恢复。

• Search

  by @taishi-i

  Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

• Remix

  by @TanStack

  Build and review Remix 3 applications using the `remix` npm package and subpath imports. Use when working on Remix app structure, routes, controllers, middleware, validation, data access, auth, sessions, file uploads, server…

• Gap Analysis

  by @TanStack

  Audit TanStack AI provider adapters for feature parity gaps and outdated model lists. Triggered as /gap-analysis <provider|feature <name>|models|--all>. Produces a dated markdown report under .agent/gap-analysis/. Maintainer…

• Pr Sweep

  by @TanStack

  Sweep open (or listed) PRs with up to 100 parallel agents: security-scan outside contributors, rebase onto main when behind (push --force-with-lease), approve pending first-time-contributor CI when relevant, optionally rebase…

• Bugfix Pr

  by @TanStack

  Treats bug-fix pull requests as invasive and untrusted. The agent must security-scan the PR first, must not run any command supplied by the author or issue, must reproduce the claimed bug on clean main with an agent-written…

• Docs

  by @TanStack

  Use when writing, editing, or organizing documentation, when planning what docs a feature needs, and whenever planning or implementing a new feature or change in a repo (docs ship with the code). Also use when tempted to write…

• Triage Github

  by @TanStack

  Triage all open GitHub issues, PRs, and discussions in the current repository by fanning out up to 100 parallel subagents (one per item), then produce a single prioritized report ranking which PRs to review first, which issues…

• Pr Description

  by @TanStack

  Use when writing a pull request title or body, when about to run gh pr create, when about to git push on a branch that already has an open PR, or when the user says /pr-description, "write the PR description", or "update the PR…

• I Have Adhd

  by @TanStack

  Use when the user invokes /i-have-adhd, says they have ADHD, or asks for ADHD-friendly output. Also used as a required writing filter by the docs skill. Don't use for marketing copy or after the user says "stop adhd mode" or…

• Add Example Tutorial

  by @TanStack

  Use when adding a public teaching example or a docs tutorial. Don't use for an internal Nx playground (that is new-react-playground), for a package API change with no walkthrough, or for a docs-only copy edit.

• Ralph Docs

  by @mikeyobrien

  Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map. Use this skill whenever the user asks questions about Ralph's behavior, wants to understand how a Ralph internal works (event loop, hats,…

• Ralph Hats

  by @mikeyobrien

  Create, inspect, validate, explain, and improve Ralph hat collections. Use this skill whenever the user asks to make or refine a `.ralph/hats/*.yml` workflow, debug hat routing, explain event topology, or tune a multi-hat Ralph…

• Ralph Loop

  by @mikeyobrien

  Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.

• Find Code Tasks

  by @mikeyobrien

  Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

• Code Assist

  by @mikeyobrien

  Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and…

• Test Driven Development

  by @mikeyobrien

  Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptest guidance and backpressure integration.

• Tui Validate

  by @mikeyobrien

  Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG/SVG) and text-based validation modes.

• Code Task Generator

  by @mikeyobrien

  Generates structured .code-task.md files from descriptions or PDD implementation plans. Auto-detects input type, creates properly formatted tasks with Given-When-Then acceptance criteria.

• Pdd

  by @mikeyobrien

  Transforms a rough idea into a detailed design document with implementation plan. Follows Prompt-Driven Development — iterative requirements clarification, research, design, and planning.

• Tui Debug In Pane

  by @mikeyobrien

  Use when you need to reproduce or debug TUI rendering issues (garbled output, broken streaming, layout corruption) by running ralph in a tmux split pane and capturing live output.

• Pr Demo

  by @mikeyobrien

  Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding.

• Evaluate Presets

  by @mikeyobrien

  Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.

• Review Pr

  by @mikeyobrien

  Use when asked to review a PR, run a code review loop, or invoke the ralph reviewer against a pull request number or GitHub URL

• Playwriter

  by @mikeyobrien

  Browser automation via Playwriter (remorses) using persistent Chrome sessions and the full Playwright Page API.

• Release Bump

  by @mikeyobrien

  Use when bumping ralph-orchestrator version for a new release, after fixes are committed and ready to publish

• Tmux Terminal

  by @mikeyobrien

  Interactive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows.

• Arxiv Mcp Server

  by @blazickjp

  Use when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or literature reviews.

• Vibe Techdesign

  by @KhazP

  Write an MVP technical design from agreed requirements, including architecture choices and relevant tradeoffs.

• Vibe Prd

  by @KhazP

  Write or revise an MVP product requirements document with scope and observable acceptance criteria.

• Vibe Research

  by @KhazP

  Research an app idea or resolve product and technical uncertainties before committing to a design.

• Vibe Debug

  by @KhazP

  Diagnose and fix a reproducible failure in an existing project. Use for crashes, broken behavior, or failing checks, not greenfield planning.

• Vibe Change

  by @KhazP

  Add one bounded feature to an existing app while preserving current behavior. Do not restart the full new-project workflow.

• Vibe Verify

  by @KhazP

  Exercise a running product against acceptance criteria and report evidence. Build success alone does not verify behavior.

• Vibe Handoff

  by @KhazP

  Prepare compact factual project context for another session or coding tool without copying transcripts or secrets.

• Vibe Review

  by @KhazP

  Review a proposed change against requirements, regressions, verification evidence, and relevant security risks.

• Vibe Agents

  by @KhazP

  Create project agent instructions and tool configuration from agreed product and technical decisions.

• Vibe Workflow

  by @KhazP

  Select the appropriate planning, implementation, or debugging workflow for an app project.

• Vibe Build

  by @KhazP

  Implement a new-project slice through the relevant checks and working user journey.

• Canary Project Skill

  by @snyk

  A committed project-scope skill used by the agent-scan canary to verify that inspect detects skills under <project>/.claude/skills. No claude CLI creates a standalone project skill, so this fixture is the only way to give the…

• Terracotta

  by @bergside

  A sun-baked, clay-toned editorial interface built on warm cream surfaces, ink-brown headlines set in a display serif, and a single terracotta accent.

• Stitch

  by @bergside

  Clean, high-contrast enterprise design for data-driven workflows with intuitive drag-and-drop patterns and structured layouts.

• Storytelling

  by @bergside

  Narrative-driven design using visuals, copy, and interaction to guide users through engaging, emotionally resonant journeys.

• Square

  by @bergside

  Graceful, refined aesthetic with delicate typography, minimal palettes, and polished layouts that exude sophistication.

• Vintage

  by @bergside

  1950s-1990s nostalgia with skeuomorphic touches, grainy textures, retro color palettes, and pixel-style typography.

• Tetris

  by @bergside

  Classic block-game inspired design with playful colors, bold display fonts, and compact, high-energy layouts.

• Vibrant

  by @bergside

  Lively, colorful design with bold playful typography, warm accents, and dynamic visual energy.

• Dingtalk Misc

  by @DingTalk-Real-AI

  长尾产品集合技能，覆盖低频钉钉产品：OA审批查询与处理/法务智能合同/考勤/直播/DING紧急消息/开放平台应用与MCP开发/Agoal目标管理/日志日报周报/电子表格/开放平台文档搜索与OpenAPI逃生舱/独立及文档内嵌白板/钉钉招聘/DWS技能市场安装/组织大脑Hrbrain/原生Markdown/原生HTML/PAT行为授权/多组织profile。Use when 用户提到上述任一产品，尤其是…

• Devops

  by @MaxMiksa

  Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.

• Deep Research

  by @MaxMiksa

  Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, verified claims, or comparison of approaches. Triggers include…

• Tailwind V4 Shadcn

  by @MaxMiksa

  Production-tested setup for Tailwind CSS v4 with shadcn/ui, Vite, and React. Use when: initializing React projects with Tailwind v4, setting up shadcn/ui, implementing dark mode, debugging CSS variable issues, fixing theme…

• Deep Reading Analyst

  by @MaxMiksa

  Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems thinking, six thinking hats). Use…

• Seo Content Strategist

  by @MaxMiksa

  Expert SEO content strategy for SaaS and B2B sites. Use when doing keyword research, planning content clusters, creating pillar pages, optimizing on-page SEO, fixing technical SEO issues, building links, refreshing content,…

• Senior Qa

  by @MaxMiksa

  Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications. Includes test suite generation, coverage analysis, E2E testing setup, and quality…

• Websh

  by @MaxMiksa

  A shell for the web. Navigate URLs like directories, query pages with Unix-like commands. Activate on `websh` command, shell-style web navigation, or when treating URLs as a filesystem.

• Security Audit

  by @MaxMiksa

  Use when reviewing code security, auditing dependencies for CVEs, checking configuration or secret security, assessing authentication and authorization patterns, identifying OWASP vulnerabilities (injection, XSS, CSRF), or…

• Community Led Growth

  by @MaxMiksa

  Expert in community-led growth (CLG) - leveraging user communities to drive acquisition, retention, and expansion. Covers building developer communities, user groups, ambassador programs, and turning customers into advocates.…

• Email Sequence

  by @MaxMiksa

  When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding…

• Market Sizing Analysis

  by @MaxMiksa

  This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a…

• Competitive Intelligence Analyst

  by @MaxMiksa

  Use this skill when users need to analyze competitors, monitor market movements, benchmark features/pricing, identify market gaps, or understand competitive positioning. Activates for "what are competitors doing," market…

• Github Explorer

  by @MaxMiksa

  Deep-dive analysis of GitHub projects. Use when the user mentions a GitHub repo/project name and wants to understand it — triggered by phrases like "help me look at this project", "learn about XXX", "what is this project like",…