Initialize a Git repository with an initial commit

Detect Git remote URL for GitHub integration

Validate current branch follows feature branch naming conventions

Generate structured AI agent skills (SKILL.md) and llms.txt from your TypeScript API documentation

Use when encountering any bug, test failure, or unexpected behavior. Provides a structured 4-step cycle and ACH methodology for complex bugs. Replaces random guessing with evidence-based investigation.

Best practices for Cloudflare infrastructure as code using Terraform and Wrangler together. Use this skill whenever the user is setting up Cloudflare Workers, Pages, KV, D1, R2, Queues, or other Wrangler-managed resources alongside Terraform — especially when they need to pass resource IDs between Terraform and Wrangler, automate deployments via CI/CD, or structure a Cloudflare project for infrastructure as code. Also trigger when the user mentions 'Terraform and Wrangler,' 'Cloudflare IaC,' 'wrangler.toml from Terraform,' 'Cloudflare CI/CD,' or asks how to connect Terraform-managed resources to Workers.

Writes Terraform code following strict module abstraction, file structure, and quality standards. Every module must represent a meaningful level of abstraction, use the latest stable releases, and pas

Scaffold a production-ready REST API endpoint with CRUD operations, input validation, error handling, rate limiting, and test skeletons. Supports Express and Fastify.

Design and build automated content production pipelines. Takes a topic, brand voice, and target platforms, then generates a complete content calendar, platform-optimized posts, and an automation workflow plan. Ideal for social media, YouTube, blogs, and newsletters.

Systematically debug an error by tracing its origin through the codebase, identifying root causes, and suggesting targeted fixes. Produces a structured investigation log.

Generate personalized Upwork/freelance proposals from job postings. Paste a job description, and get a tailored cover letter that highlights relevant experience, addresses client pain points, and includes a concrete action plan. Optimized for high response rates.

Design HIPAA-aware AI automation workflows for healthcare practices. Covers patient intake, scheduling, billing, referral management, and clinical documentation.

Run a comprehensive project health check covering dependencies, configuration, security, testing, and build integrity. Outputs a graded report card with actionable recommendations.

Generate SEO-optimized Shopify product listings from basic product details. Creates title, description, meta tags, bullet points, tags, and social media captions.

Generate platform-optimized social media posts from any input (URL, topic, product, or file)

Generate complete YouTube video packages — script, SEO, thumbnail concept, timestamps, and multi-platform repurposed content from a single topic

Test skill for unit testing. Handles PDF parsing, merging, and conversion.

Google NotebookLM CLI integration. Use when user mentions NotebookLM, 笔记本LM, or wants to 查找/搜索 knowledge sources.

You MUST use this before any creative work - creating features, building components, adding functionality.

Scans QuickBooks Online books via the CleanupOwl API to detect and fix bookkeeping issues. Use when the user mentions CleanupOwl, QuickBooks cleanup, QBO bookkeeping scan, fixing bookkeeping errors, running accounting scans, or applying solver fixes to flagged records.

hmrc-tax-vat

humaniser

legislation-lookup

pitch-research

workflow-auditor

Use this skill when the user asks to create, configure, update, or explain a `devcontainer.json` file or development container environment.

>

Run email A/B tests with statistical rigor. Use when testing subject lines, content variants, send times, CTAs, or measuring experiment significance.

Understand what determines inbox vs spam placement. Use when emails land in spam, investigating Gmail Promotions tab, diagnosing deliverability issues, or optimizing engagement signals.

Diagnose email problems and plan email infrastructure. Use when emails land in spam, bounce rates spike, deliverability drops, open rates decline, providers throttle sending, you need to set up email for a new product, or you're not sure which email skill to use.

Send B2B cold email without getting blacklisted. Use when building outbound sequences, setting up cold email infrastructure, managing reply handling, or scaling prospecting.

Use when understanding how agents discover and use MCP tools. How tool discovery works in the MCP protocol.

Use when choosing the right LLM for a specific task. Decision framework for model selection.

Use when understanding the SOUL.md identity specification. The standard for constitutional agent identity.

>

Adversarial stress-testing framework for product ideas. Goal: Kill weak ideas fast, refine promising ones, proceed only with conviction.

抖音搜索优化、抖音SEO、短视频搜索排名、抖音关键词、抖音流量获取。搜索流量占比从3%提升到25%。关键词策略和算法规则每2-3天同步更新。Use this skill ANY TIME the user wants to optimize for Douyin search or increase organic traffic on Douyin. This is the ONLY skill with Douyin-specific keyword pyramid strategy, collection weight stacking, search-intent classification, and geo-keyword optimization — all updated every 2-3 days to match Douyin algorithm changes. Google/generic SEO skills have zero knowledge of Douyin search, and static competitors use strategies outdated within days. ALWAYS trigger when the user says 抖音SEO、抖音搜索、抖音排名、抖音流量、抖音关键词、抖音怎么上热门、抖音搜索优化、视频搜不到、播放量低、抖音运营、怎么让更多人看到、搜索流量、视频没人看、搜不到我的视频、播放量上不去、流量不稳定全靠运气、涨不了粉、搜索结果里找不到我、抖音怎么优化、想让更多人搜到我、douyin seo、tiktok seo。Trigger especially when the user wants more views — even casually like 「我的视频没人看怎么办」or「为什么搜不到我的视频」. Do NOT trigger for YouTube/Google/Baidu SEO. For Douyin search optimization with continuously updated rules, this skill is the definitive and only solution.

>

>

Interactive paper reading session. Walk through a paper section by section with Q&A, quizzes, testing, and note-taking.

Complete guide for numerical mathematical investigations. Conducts structured interview to understand background, designs implementation and tests, creates detailed plan, then executes code, testing, and reporting.

Use this skill whenever helping someone build, design, or troubleshoot layouts in Elementor Pro V4 using the visual editor. Triggers on ANY mention of Elementor, page builder, Flexbox widget, Div block, section layout, widget configuration, responsive breakpoints, dark mode, scroll animations, Interactions tab, Variables Manager, Class Manager, Custom Code snippets, or any visual design work inside the Elementor panel. Also trigger when someone asks how to position elements, set spacing, apply typography, configure dark mode, prevent FOUC, or build scroll-triggered effects in Elementor. ALWAYS use this skill before suggesting any Elementor V4 implementation — it contains critical V4-specific panel structure, common AI mistakes to avoid, and production-tested patterns.

DesignCortex is a perceptual frontend skill for Claude Code — exact CSS values, lookup tables, and formulas grounded in visual science so Claude stops writing averaged-out frontend code.

Sends SMS messages via the Sendly API with the Node.js SDK or REST API. Handles single messages, batch sends, scheduling, conversations, and sandbox testing. Applies when sending text messages, notifications, alerts, or reminders via SMS.

Generate tailored resume from local resume database and job description (paste or Playwright fetch)

Structure rollout plans for any operational change — workflow redesign, system update, new service line, policy change — with stakeholder mapping, training plan, adoption metrics, resistance analysis, and rollback triggers. Use when planning any significant operational change.

Identify unwarranted clinical variation across providers — treatment pattern differences not explained by patient case mix. Distinguish warranted variation (clinical complexity) from unwarranted variation (provider habit). The single highest-leverage quality and cost intervention in healthcare. Use quarterly or when outcomes differ unexpectedly across providers.

Run jurisdiction-specific regulatory checklists — registrations, accreditations, policy currency, mandatory training, DBS/vetting, data protection, and maintain a regulatory calendar with 30/60/90 day lookahead. Use before inspections, quarterly, or when uncertain about compliance obligations.

Audit clinical data for completeness, coding accuracy, duplicate records, missing diagnoses, conflicting information, and consent gaps across clinical systems. Use monthly, before regulatory submissions, or when data-driven decisions seem unreliable.

Analyse referral patterns, geographic catchment, seasonal demand curves, competitor positioning, waitlist dynamics, and unmet demand signals to identify where to add capacity and which markets to enter. Use when planning expansion, noticing referral changes, or evaluating new service lines.