Plantilles
Plantilles de projectes i de codi
skill-creator
ericpzh
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
x-create
kangarooking
Create viral X (Twitter) posts including short tweets, threads, and replies. Use when user wants to write X content, create posts, or mentions "create tweet", "write thread", "x-create", "写推文", "创作推文". Supports 5 post styles with customizable templates, plus a mandatory humanize pass to reduce AI-sounding phrasing. First-time users go through onboarding to set up profile.
oss-ready
Montimage
Transform projects into professional open-source repositories with standard components. Use when users ask to "make this open source", "add open source files", "setup OSS standards", "create contributing guide", "add license", or want to prepare a project for public release with README, CONTRIBUTING, LICENSE, and GitHub templates.
causal-inference-mixtape
Jill0099
This skill should be used when the user asks to "implement a DiD regression", "run a staggered difference-in-differences", "set up an event study", "implement IV / 2SLS", "run a regression discontinuity design", "build synthetic control", "do propensity score matching", "test parallel trends", "run Honest DiD", "wild cluster bootstrap", "Callaway-Sant'Anna", "Sun-Abraham", "Bacon decomposition", "double machine learning", "debiased machine learning", "DML / DoubleML", "cross-fitting", "causal forest", "heterogeneous treatment effects", "ATE with ML controls", "which causal design fits my data", or needs causal-inference code, diagnostics, or identification writing in Python (StatsPAI), R, or Stata. Based on Scott Cunningham's Causal Inference: The Mixtape, with runnable validated templates, ML-based causal inference patterns, and Journal of Finance applications.
coding-agent-harness
FairladyZ625
Coding Agent Harness 工程方法论。为使用 Coding Agent（Codex、Claude Code、Gemini CLI 等） 做长程项目开发的团队，在用户的项目上构建一套完整的 harness 工程体系。 包括：项目诊断、AGENTS.md + CLAUDE.md 入口文件生成、coding-agent-harness/ 目录搭建、Planning Loop、SSoT 治理、 Delivery Operating Model、Repository Governance、CI/CD、Long-Running Task Protocol、Adversarial Review Report、Review Routing、Worktree 并行开发、 Regression SSoT 与 Evidence Depth 分级回归、Walkthrough / Closeout Index 收口、Cadence Ledger、任务本地 lesson 候选与 promoted lesson 详情文档、 Harness Ledger 全局上下文回写总账。 当用户要求设置 coding agent 的开发流程、建立回归测试体系、设计 AGENTS.md / CLAUDE.md、 规划长程 agent 任务的执行框架、子代理审查循环、对抗性 review 报告、搭建 harness、或者提到 harness engineering 时，使用此技能。 也适用于"帮我搭一套 agent 开发规范"、"怎么让 AI 在长任务上不跑偏"、 "怎么做 agent 的回归测试"、"帮我初始化项目的 harness"等场景。
obliteratus
magnusthovsland
"OBLITERATUS: abliterate LLM refusals (diff-in-means)."
baoyu-infographic
magnusthovsland
"Infographics: 21 layouts x 21 styles (信息图, 可视化)."
PO Story Overview
itzikiusa
Summarize and assess a product story (Jira/Confluence) from a Product Owner lens — value, clarity, scope, and acceptance-criteria completeness. Stay at product altitude, not implementation.
Jira Story Writer
itzikiusa
Guidelines (not strict rules) for writing an excellent Jira story. Use to suggest a rewrite and to review an existing story. PO-level — frame value and acceptance, stay out of technical implementation.
RFC Writer
itzikiusa
Guidelines (not strict rules) for writing an excellent RFC / proposal. Use to suggest a rewrite and to review one. Product/decision altitude — frame the problem, the options, and the recommendation; light on deep technical design. Audience is decision-makers and stakeholders.
Pull request
itzikiusa
Use BEFORE opening or drafting ANY pull request — when asked to "open a PR", "create a pull request", "draft a PR", or to write a PR title/description. Covers summarizing the whole branch, the Jira key as title prefix (never in the body), GitHub vs Bitbucket creation, and the rule that a PR carries NO AI attribution.
gateway-credential-setup
magnusthovsland
Set up messaging gateway credentials for Hermes or similar agent gateways without reusing legacy tokens or confusing templates with active secrets.
docx-format-replicator
iamzhihuix
Extract formatting from existing Word documents and generate new documents with the same format but different content. Use this skill when users need to create multiple documents with consistent formatting, replicate document templates, or maintain corporate document standards across different content.
Story Test Cases
itzikiusa
Draft readable, right-sized test cases for a story — happy path plus meaningful validations and realistic errors. Not over-defensive. Plain language a PO can approve and a dev can implement against.
Story Architecture Overview
itzikiusa
Map a product story to the actual codebase — related repos/modules, functionalities touched, integration/contract points, data impact, and technical risks. Inspect the working directory; cite real file paths and line numbers.
architecture-decision-record
ArieGoldkin
Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Helps teams maintain architectural memory and rationale for backend systems, API designs, database choices, and infrastructure decisions.
cloudflare-mcp-server
jackspace
Use this skill when building Model Context Protocol (MCP) servers on Cloudflare Workers. This skill should be used when deploying remote MCP servers with TypeScript, implementing OAuth authentication (GitHub, Google, Azure, etc.), using Durable Objects for stateful MCP servers, implementing WebSocket hibernation for cost optimization, or configuring dual transport methods (SSE + Streamable HTTP). The skill prevents 15+ common errors including McpAgent class export issues, OAuth redirect URI mismatches, WebSocket state loss, Durable Objects binding errors, and CORS configuration mistakes. Includes production-tested templates for basic MCP servers, OAuth proxy integration, stateful servers with Durable Objects, and complete wrangler.jsonc configurations. Covers all 4 authentication patterns: token validation, remote OAuth with DCR, OAuth proxy (workers-oauth-provider), and full OAuth provider implementation. Self-contained with Worker and Durable Objects basics. Token efficiency: ~87% savings (40k → 5k tokens). Production tested on Cloudflare's official MCP servers. Keywords: MCP server, Model Context Protocol, cloudflare mcp, mcp workers, remote mcp server, mcp typescript, @modelcontextprotocol/sdk, mcp oauth, mcp authentication, github oauth mcp, durable objects mcp, websocket hibernation, mcp sse, streamable http, McpAgent class, mcp tools, mcp resources, mcp prompts, oauth proxy, workers-oauth-provider, mcp deployment, McpAgent export error, OAuth redirect URI, WebSocket state loss, mcp cors, mcp dcr
better-chatbot
jackspace
This skill provides project-specific coding conventions, architectural principles, repository structure standards, testing patterns, and contribution guidelines for the better-chatbot project (https://github.com/cgoinglove/better-chatbot). Use this skill when contributing to or working with better-chatbot to understand the design philosophy and ensure code follows established patterns. Includes: API architecture deep-dive, three-tier tool system (MCP/Workflow/Default), component design patterns, database repository patterns, architectural principles (progressive enhancement, defensive programming, streaming-first), practical templates for adding features (tools, routes, repositories). Use when: working in better-chatbot repository, contributing features/fixes, understanding architectural decisions, following server action validators, implementing tools/workflows, setting up Playwright tests, adding API routes, designing database queries, building UI components, handling multi-AI provider integration Keywords: better-chatbot, chatbot contribution, better-chatbot standards, chatbot development, AI chatbot patterns, API architecture, three-tier tool system, repository pattern, progressive enhancement, defensive programming, streaming-first, compound component pattern, Next.js chatbot, Vercel AI SDK chatbot, MCP tools, workflow builder, server action validators, tool abstraction, DAG workflows, shared business logic, safe() wrapper, tool lifecycle
cloudflare-full-stack-scaffold
jackspace
Production-ready starter project for React + Cloudflare Workers + Hono with core services (D1, KV, R2, Workers AI) and optional advanced features (Clerk Auth, AI Chat, Queues, Vectorize). Complete with planning docs, session handoff protocol, and enable scripts for opt-in features. Use when: starting new full-stack project, creating Cloudflare app, scaffolding web app, AI-powered application, chat interface, RAG application, need complete starter, avoid setup time, production-ready template, full-stack boilerplate, React Cloudflare starter. Prevents: service configuration errors, binding setup mistakes, frontend-backend connection issues, CORS errors, auth integration problems, AI SDK setup confusion, missing planning docs, incomplete project structure, hours of initial setup. Keywords: cloudflare scaffold, full-stack starter, react cloudflare, hono template, production boilerplate, AI SDK integration, workers AI, complete starter project, D1 KV R2 setup, web app template, chat application scaffold, RAG starter, planning docs included, session handoff, tailwind v4 shadcn, typescript starter, vite cloudflare plugin, all services configured
clerk-auth
jackspace
This skill provides comprehensive knowledge for integrating Clerk authentication in React, Next.js, and Cloudflare Workers applications. It should be used when setting up user authentication, implementing protected routes, verifying JWT tokens, creating custom JWT templates with user metadata and organization claims, configuring Clerk middleware, integrating with shadcn/ui components, testing authentication flows, or troubleshooting Clerk authentication errors. Use when: adding Clerk to React/Vite projects, setting up Clerk in Next.js App Router, implementing Clerk authentication in Cloudflare Workers, configuring clerkMiddleware for route protection, creating custom JWT templates with shortcodes (user.id, user.email, user.public_metadata.role), accessing session claims for RBAC, integrating with Supabase/Grafbase, verifying tokens with @clerk/backend, integrating Clerk with Hono, using Clerk shadcn/ui components, writing E2E tests with Playwright, generating test session tokens, using test email addresses and phone numbers, or encountering authentication errors. Prevents 11 documented issues: missing secret key errors, API key migration failures, JWKS cache race conditions, CSRF vulnerabilities from missing authorizedParties, import path errors after Core 2 upgrade, JWT size limit issues, deprecated API version warnings, ClerkProvider JSX component errors, async auth() helper confusion, environment variable misconfiguration, and Vite dev mode 431 header errors. Keywords: clerk, clerk auth, clerk authentication, @clerk/nextjs, @clerk/backend, @clerk/clerk-react, clerkMiddleware, createRouteMatcher, verifyToken, useUser, useAuth, useClerk, JWT template, JWT claims, JWT shortcodes, custom JWT, session claims, getToken template, user.public_metadata, org_id, org_slug, org_role, CustomJwtSessionClaims, sessionClaims metadata, clerk webhook, clerk secret key, clerk publishable key, protected routes, Cloudflare Workers auth, Next.js auth, shadcn/ui auth, @hono/clerk-auth, "Missing Clerk Secret Key", "cannot be used as a JSX component", JWKS error, authorizedParties, clerk middleware, ClerkProvider, UserButton, SignIn, SignUp, clerk testing, test emails, test phone numbers, +clerk_test, 424242 OTP, session token, testing token, @clerk/testing, playwright testing, E2E testing, clerk test mode, bot detection, generate session token, test users
media-relations
liqiongyu
"Plan and execute earned media outreach and journalist relationships by producing a Media Relations Pack (newsworthiness brief, media list, exclusive/embargo plan, pitch templates, outreach tracker, interview prep, press materials checklist). Use for PR, media outreach, press pitch, embargo, exclusive, press release, and journalist pitching. Category: Marketing."
pptx
samhvw8
"PowerPoint presentation processing. Format: .pptx (ZIP/XML structure). Capabilities: create presentations, edit slides, layouts/masters, speaker notes, comments, shapes, images, charts, text extraction, template preservation. Actions: create, edit, analyze, extract from presentations. Keywords: PowerPoint, pptx, presentation, slide, layout, master slide, speaker notes, comments, shapes, images, charts, text extraction, template, slide deck, bullet points, title slide, content slide, animation. Use when: creating presentations, editing PowerPoint files, extracting slide content, modifying layouts, adding speaker notes, working with presentation templates."
conducting-user-interviews
liqiongyu
"Plan, conduct, and synthesize high-signal user interviews and produce a User Interview Pack (recruiting plan, screener, discussion guide, notes template, synthesis report). Use for user interview, customer interview, discovery interview, JTBD switch interview, concept interview."
mcp
samhvw8
"Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents."