Productivity AI agent skills

4,613 skills in the archive. Read a skill’s instructions or open its original repository.

• Atlas Recon

  by @tonone-ai

  Documentation reconnaissance for takeover — find all docs, assess accuracy, freshness, coverage, and discoverability, and identify critical knowledge gaps. Use when asked "what docs exist", "documentation assessment", or…

• Clone Website

  by @JasonxzWen

  Load when the user explicitly asks to clone, reverse-engineer, or rebuild a website they own or are authorized to reproduce; do not load for generic redesign, inspiration, scraping, phishing, impersonation, or copying…

• Source Post

  by @JasonxzWen

  Load when turning an external article, blog, release note, interview, or report into a source-backed public post with Chinese fidelity, media references, an effective-interact summary layer, and project-iteration review; do not…

• Tailwind 4 Docs

  by @Lombiq

  Comprehensive Tailwind CSS v4 documentation snapshot and workflow guidance. Use when answering Tailwind v4 questions, selecting utilities/variants, configuring Tailwind v4, or migrating projects from v3 to v4 with official docs…

• Design Taste Frontend

  by @JasonxzWen

  Load when a task needs anti-template frontend visual direction, design-read calibration, or pre-flight critique for landing pages, portfolios, marketing pages, or redesigns; do not load for dashboards, data tables, multi-step…

• Docs Review Pr

  by @elastic

  Run a full review of an Elastic documentation PR against the docs team review checklist — user focus, technical accuracy, applicability, maintainability, language, and style. Runs the companion review skills and merges…

• Docs Fix Changelog

  by @elastic

  Suggest improved text for changelog YAML files against current Elastic standards. Mirrors the pattern catalog from docs-review-changelog to provide consistent fixes. Includes type-title alignment, product/surface context for…

• Docs Stack Release

  by @elastic

  Coordinate Elastic Stack docs releases: classify versions, route 8.x vs 9.x PRs, edit elastic/dev tracking issues, handle same-GA supersession, draft Slack #docs reminders, and watch docs-internal-workflows deploys. Use when the…

• Docs Check Kibana Oas

  by @elastic

  Review a Kibana PR for OpenAPI Spec (OAS) and API docs compliance against the Elastic API docs checklist, core guidelines, and Kibana quickstart. Checks availability, summaries, descriptions, parameters, examples, tags, links,…

• Capgo Release Management

  by @Cap-go

  Guides the agent through Capgo OTA release workflows including bundle uploads, compatibility checks, channels, cleanup, and encryption key setup. Use when managing Capgo bundle and channel operations. Do not use for native build…

• Capgo Organization Management

  by @Cap-go

  Guides the agent through Capgo account lookup and organization administration. Use when listing organizations, managing members, changing security settings, or working with organization-level CLI commands. Do not use for OTA…

• Agent Introspection Debugging

  by @JasonxzWen

  Load when a task needs agent run, tool loop, context drift, or recoverable harness/tool failure debugging; use diagnose for product/runtime bugs.

• Decision Ui

  by @JasonxzWen

  Load when Codex 即将要求用户在 2-3 个互斥方案中做真实决定、准备询问阻塞性澄清问题或需要确认高影响取舍；将选择转换为宿主原生可点击 UI，并在工具不可用时诚实文本回退。不要用于低风险实现细节、只有一个合理答案的问题、普通信息采集或不需要用户决策的完成汇报。

• Openspec Archive Change

  by @JasonxzWen

  Load when a task needs to archive a completed OpenSpec change after implementation and spec sync decisions are resolved.

• Azure Kubernetes

  by @seaworld008

  Plan and configure Azure Kubernetes Service clusters, including SKU, networking, identity, deployment readiness, and operational constraints.

• Crest

  by @seaworld008

  Building engineer self-branding by turning technical contributions into a professional brand. Use for GitHub/LinkedIn/blog/conference positioning or content strategy.

• Arena

  by @seaworld008

  Specialist orchestrating codex exec / Antigravity CLI through dual paradigms — COMPETE (multi-variant comparison, select best) and COLLABORATE (decompose tasks across engines, integrate). Supports Solo/Team/Quick execution modes.

• Content Creator

  by @seaworld008

  Create or revise marketing content with a consistent brand voice, audience intent, SEO structure, and publishing requirements.

• Deep Research

  by @seaworld008

  Produce source-backed research reports, literature reviews, or technical and market briefs when evidence tracking and a defined report format matter.

• Develop Web Game

  by @seaworld008

  Build or iterate on HTML/JS web games with Playwright input bursts, gameplay screenshots, state inspection, and console checks.

• Wp Plugin Review

  by @wpacademy

  Comprehensive WordPress plugin review covering security vulnerabilities, WordPress Coding Standards (WPCS) compliance, plugin repository guidelines, unit test coverage, and accessibility. Runs automated tools (PHPCS with WPCS,…

• Agile Product Owner

  by @seaworld008

  Manage product backlogs and sprints: user stories, acceptance criteria, epic breakdown, prioritization, estimates, and delivery tracking.

• Database Schema Designer

  by @seaworld008

  Design relational database schemas from requirements and generate migrations, TypeScript/Python types, seed data, RLS policies, and indexes. Handles multi-tenancy, soft deletes, audit trails, versioning, and polymorphic…

• Docs Cleaner

  by @seaworld008

  Consolidate overlapping documentation and remove repetition while preserving useful content, references, and ownership.

• Sculpture 3d

  by @Tibsfox

  Three-dimensional art and sculptural thinking for art education. Covers additive and subtractive sculptural processes, armature construction, modeling in clay, carving principles, casting and moldmaking, assemblage and…

• Digital Art

  by @Tibsfox

  Digital art tools, techniques, and workflows for art education. Covers raster and vector workflows, digital painting, photo manipulation, generative and procedural art, 3D modeling and rendering, pixel art, the relationship…

• Organizational Strategy

  by @Tibsfox

  Organizational strategy and management theory for business decision-making. Covers objectives-based management, the knowledge-worker firm, decentralization, the five management tasks, strategy-as-practice, managerial roles, and…

• Brainstorming

  by @seaworld008

  Use before creative product or engineering work when the user wants to design a feature, component, workflow, behavior change, or other solution whose goals, constraints, and tradeoffs need exploration before implementation.

• Dawn

  by @seaworld008

  Propose one personal side-project idea scoped to a 1-3 day MVP when the user requests daily inspiration or weekend project ideation.

• Antigravity Workflows

  by @SamarthaKV29

  Orchestrate multiple Antigravity skills through guided workflows for SaaS MVP delivery, security audits, AI agent builds, and browser QA.

• 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.

• 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…

• Contract Review Pro

  by @lovstudio

  Professional-grade contract review skill that adds comment-based issue annotations without changing original text. Enforces a four-layer review (entity verification, basic, business, legal), writes structured comments (issue…

• Writing Skills

  by @zenobi-us

  Teaches test-driven skill authoring and validation, when creating/editing/verifying skills, resulting in robust reusable skills that pass pressure-tested scenarios

• Lov Icp Filing

  by @lovstudio

  协助提交和跟进中国大陆网站 ICP 备案，覆盖接入商审核、域名实名同步、补充材料、工信部短信核验和管局结果；用户说“继续 ICP 备案”或 "submit and track an ICP filing" 时使用。

• Lov Filing Readiness

  by @lovstudio

  在提交中国大陆网站备案前核验主体、域名实名、服务类型、接入资源和材料缺口；用户说“备案前检查”“ICP 需要什么材料”或 "check ICP filing readiness" 时使用，并给出可执行准备清单。

• Lov Public Security Filing

  by @lovstudio

  协助已取得 ICP 并开放的网站办理公安联网备案，核验主体账号、网站与接入信息、材料、属地审核和公安备案号，并分流舆论属性安全评估；触发词包括“公安备案”与 "public security filing"。

• Hunter

  by @GadaaLabs

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

• Architect

  by @GadaaLabs

  You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

• Release Please

  by @zenobi-us

  Use when adopting or operating Release Please for automated versioning, changelog generation, and GitHub releases in single-package or manifest-mode repositories

• 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

• Nexus

  by @GadaaLabs

  RAG architectures, agent design patterns, prompt engineering, and LLM evaluation — domain expertise for AI application engineers

• Sgc Electron Delta Updater

  by @lovstudio

  为 Electron 桌面应用设计、实现和验证增量自动更新，覆盖 macOS Sparkle、签名、appcast、发布产物与失败拦截。用户提到增量更新、Sparkle、检查更新、appcast、DMG 更新或 delta updater 时使用。

• Browser Acceptance Evidence

  by @zenobi-us

  Writes manual test steps, drives them in a real browser with surf or Playwright, captures screenshots and element selectors as evidence, and publishes an HTML report to shared context. Use when a change must be proved in a…

• Dsh Plugin Creator

  by @lovstudio

  Create a @deepseek-ai/dsh-* plugin package end-to-end — choose the extension point or capability seam, scaffold the package, implement the tool/hook/service, and run the repo gates. 触发：新增插件 / 加工具 / 开发 capability。

• Ascend

  by @GadaaLabs

  Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

• Sgc Electron App Relaunch

  by @lovstudio

  为 Electron 桌面应用实现并验证完整重启，区分 renderer 刷新、用户主动重启、开发态重启和更新安装交接。用户提到重启 App、菜单重启、Cmd+R、app.relaunch 或 restart Electron 时使用。

• Phantom

  by @GadaaLabs

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

• Twg Responsibility Routing

  by @zenobi-us

  Use with root `twg` to route owners, subject-matter experts, maintainers, reviewers, approvers, decision authorities, Heads of Engineering, or escalation paths for a topic, area, ask, project, service, or component.

• Sculptor

  by @GadaaLabs

  Use when creating new skills, editing existing skills, or verifying skills work before deployment — applies TDD to process documentation with the same Iron Law as FORGE

• Blueprint

  by @GadaaLabs

  Use when you have a spec or requirements for a multi-step task, before touching code

• Forge

  by @GadaaLabs

  Use when implementing any feature or bugfix, before writing implementation code

• Portless Cli

  by @zenobi-us

  Guides correct usage of the Portless CLI for local named URLs, monorepo workflows, HTTPS/LAN/Tailscale modes, and proxy routing pitfalls, when developers need stable local domains instead of port juggling, resulting in…

• Sentinel

  by @GadaaLabs

  Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

• Vault

  by @GadaaLabs

  Use when starting feature work that needs isolation from the current workspace, or before executing implementation plans — creates isolated git worktrees with smart directory selection and safety verification

• Dumbzone

  by @zenobi-us

  Evaluate whether a model entered the context dumb zone using a long-context contradiction test, when testing long-context retrieval and rule priority, resulting in a PASS, PARTIAL_FAIL, or TOTAL_FAIL report

• Oracle

  by @GadaaLabs

  Pre-task intelligence layer — classify complexity, select skill chain, search patterns, assign model tier. Run BEFORE any non-trivial task begins. Turns the system from reactive to proactive.

• Pathfinder

  by @GadaaLabs

  Structured first-pass exploration of an unfamiliar codebase — what to read, in what order, what to map, what traps to find. Use when entering any new or inherited project before writing code.

• Arbiter

  by @GadaaLabs

  Use when receiving code review feedback, before implementing any suggestion — requires technical verification and reasoned evaluation, not performative agreement or blind implementation

• Seal

  by @GadaaLabs

  Use when implementation is complete and all tests pass — guides branch completion through four structured options (merge, PR, keep, discard) with verification and worktree cleanup

• Horizon

  by @GadaaLabs

  Manage context window budget across long sessions — when to compress, what to give subagents, when to start fresh. Prevents silent quality degradation as conversations grow.

• Exodus

  by @GadaaLabs

  Use when you have a written implementation plan to execute in a completely fresh isolated session — no context inheritance, clean slate execution with review checkpoints

• Install Skill

  by @zenobi-us

  Install a skill from GitHub or another source, when the user explicitly requests skill installation, resulting in files stored in the configured skills directory

• Chronicle

  by @GadaaLabs

  Store and retrieve patterns from past work using semantic search; adds self-learning capability to Superpowers

• Commander

  by @GadaaLabs

  Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

• Bmad Enhance Initiatives Backlog

  by @amalik

  Manage lane-aware initiative lifecycle backlog — triage findings into intakes and qualify into Bug/Fast/Initiative lanes, rescore lane items, or bootstrap a new lifecycle backlog. Use when the user says triage findings, qualify…

• Prisma Mongodb Upgrade

  by @prisma

  Decision and migration guide for Prisma ORM MongoDB projects on v6, which have no upgrade path to v7. Use when a MongoDB project asks about upgrading Prisma, when "upgrade to prisma 7" comes up in a project with provider =…

• Bmad Migrate Artifacts

  by @amalik

  Migrate artifact governance metadata to conform to taxonomy. Use when the user says "run artifact migration" or "migrate artifacts".

• Vps Docker Traefik Deploy

  by @thienanblog

  Prepare or operate production Docker Compose deployments on a VPS with Traefik, DNS, registries, persistent storage, backups, and rollback. Use for production infrastructure and releases, rather than local development.

• Bmad Portfolio Status

  by @amalik

  Show a portfolio view of all initiatives with phase, status, and next actions through a guided 3-step conversation. Use when the user says "show portfolio" or "portfolio status".

• Project Development Mindset

  by @thienanblog

  Plan and carry repository changes through implementation, verification, and handoff. Use for project work that needs a general development workflow; select specialist guidance when it adds task-specific value.

• Bmad Seed Catalog

  by @amalik

  Seed the complete catalog repository staging directory with all exportable skills, adapters, and catalog README. Use when the user says "seed catalog", "seed the repo", "create catalog repo", or "generate catalog repo".

• Bmad Validate Exports

  by @amalik

  Validate an exported skill staging directory for structural correctness and BMAD-internal leaks. Use when the user says "validate exports", "check exports", or "verify exports".

• Bmad Generate Catalog

  by @amalik

  Generate the decision-tree skill catalog README from manifest data. Use when the user says "generate catalog", "create catalog", or "build catalog".

• Bkend Cookbook

  by @ww-w-ai

  bkend.ai practical project tutorials and troubleshooting guide. Covers 4 full-guide projects (blog, recipe-app, shopping-mall, social-network) with step-by-step implementation patterns including schema design, architecture…

• Pdca

  by @ww-w-ai

  Unified skill for managing the entire PDCA cycle. Supports Plan → Design → Do → Check → Act workflow with automatic phase progression. Use proactively when user mentions PDCA cycle, planning, design documents, gap analysis,…

• Deploy

  by @ww-w-ai

  Deployment guidance and checklist for dev, staging, and production environments. Creates a checkpoint before deploy and provides a structured pre-deploy checklist. Use proactively when user mentions deploying, releasing, or…

• Plan Plus

  by @ww-w-ai

  Plan Plus — Brainstorming-Enhanced PDCA Planning. Combines intent discovery from brainstorming methodology with PDCA's structured planning. Produces higher-quality Plan documents by exploring user intent, comparing alternatives,…

• Phase 8 Review

  by @ww-w-ai

  Skill for verifying codebase quality and gap analysis. Covers architecture consistency and convention compliance. Use proactively when implementation is complete and quality verification is needed. Triggers: code review,…

• Production Intelligence Specialist

  by @amalik

  Production Intelligence Specialist

• Discovery Empathy Expert

  by @amalik

  Discovery & Empathy Expert

• Learning Decision Expert

  by @amalik

  Learning & Decision Expert

• Agenticflow Skills

  by @viralcode

  Comprehensive guide for building AI workflows, agents, and workforce systems with AgenticFlow. Use when designing workflows with various node types, configuring single agents, or orchestrating workforce collaboration patterns.

• Ai Sdk 7

  by @laguagu

  Vercel AI SDK v7 development and migration. Use when building or upgrading AI SDK 7 apps, especially ToolLoopAgent, WorkflowAgent, HarnessAgent, Claude Code/Codex/Pi harnesses, runtimeContext, toolsContext, toolApproval,…

• Badi Enhancement

  by @likweitan

  Help with BAdI (Business Add-In) development, the ABAP enhancement framework, and the clean core level classification of enhancement techniques. Covers new BAdIs, fallback classes, filter-based BAdIs, enhancement spots,…

• Atc Cloudification

  by @likweitan

  Configure ATC clean core and Cloud Readiness checks using the SAP Cloudification Repository, and map ATC findings to clean core levels (A, B, C, D). Use when users ask about ATC check variants for cloud readiness, clean core…

• Odata

  by @likweitan

  Help with OData service development in ABAP including OData V2 and V4 services via RAP service bindings, SEGW-based services, service definitions, service bindings, OData annotations, consumption of external OData services, and…

• Convex Add

  by @get-convex

  Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search.…

• Data Machine

  by @Sarai-Chinwag

  Self-scheduling execution layer for autonomous task orchestration. Use for queuing tasks, chaining pipeline executions, scheduling recurring work, and 24/7 autonomous operation via Agent Ping webhooks.

• Convex Reviewer

  by @get-convex

  Convex code reviewer — security, auth, validators, performance, and pattern checks for code in a convex/ directory. Use to review or audit Convex functions before shipping.

• Stake Game Developer

  by @egorfedorov

  End-to-end Stake game development workflow for math, RGS contract, frontend playback, and compliance gating. Use when building or updating Stake games, defining game modes and RTP targets, validating generated books/index…

• Turbo Spin Designer

  by @egorfedorov

  Define turbo/quick spin behavior, timings, and UI rules for slot games. Invoke when implementing fast spin modes, stop/skip behavior, or spin-speed UX standards.

• Autoplay System Designer

  by @egorfedorov

  Define auto-play UX, stop conditions, and safeguards for slot games. Invoke when implementing autoplay controls, confirmations, or stop-on-event rules.

• Plan With Team

  by @DanielKerridge

  Spawns an Agent Team to collaboratively plan Power Platform / Dataverse applications. Three specialists (Data Architect, UX Designer, The Skeptic) debate and refine the plan before any code is written. Falls back to structured…

• Book Generator

  by @egorfedorov

  Generate, package, and validate weighted outcome books for slot/casino game modes. Use when defining mode book schemas, producing `books_*.jsonl(.zst)` files, generating `lookUpTable_*.csv` weights, assembling `index.json`, or…

• Multi Agent Orchestrator

  by @egorfedorov

  Coordinate multi-agent execution plans with explicit dependencies, ownership boundaries, and completion gates. Use when orchestrating multiple autonomous workstreams, sequencing inter-agent tasks, resolving dependency conflicts,…

• Stake Platform Architect

  by @egorfedorov

  Architect Stake platform integration layers across services, contracts, and release workflows. Use when defining platform boundaries, service contracts, compliance-aware architecture decisions, or validating integration…

• Provider Integration

  by @egorfedorov

  Integrate external/internal providers through stable adapter contracts and resilience controls. Use when adding or auditing provider APIs, normalizing data contracts, defining fallback behavior, or validating provider…

• Slot Ui Studio

  by @egorfedorov

  Build scalable slot UI production systems with shared components, state patterns, and release quality controls. Use when structuring slot UI architecture, component libraries, interaction contracts, or validating production UI…