SkillCDN Pack
Your marketer, designer and developer in the AI you already use, making the short ad, the card news, the deck, the web app and the meeting minutes itself, checked before you see them. docs/pack/finding-a-skill.md says how to find a skill.
https://skillcdn.ai/gh/skillcdn/skillsConnect this address to your AI to use these skills. How to connect
- Repository
skillcdn/skills - Default branch
main - Commit
9e3fd2c - License
MIT - Searchwords and meaning
Explore this repository
Searches the original text of skills and documents by words and by meaning; display translations are not searched.
Skills
- cloudflare-admin-dashboardBuilds the operator's admin dashboard as a separate Cloudflare Worker that only the operator can open, bound to the project's own database, protected by Cloudflare Access with a one-time email code and verified again inside the Worker so that it fails closed until protected, holding its own least-privilege keys apart from the public site, writing an audit log of every action, confirming anything that moves money or ads, and running a cron that syncs the ledgers and sends a daily digest. Use when the user asks for an admin, an operator dashboard, a back office, a place to see sales and ads, monitoring or alerts for a site, or to replace a password-protected admin page. Payments are stripe-payments, ads are meta-ads-setup, the public site is cloudflare-new-app. It shows today and the week, the funnel to the paid step, orders with refunds and disputes when stripe-payments ran, campaigns with spend, results and controls with the rules' recommendations when meta-ads-setup ran, costs, and the system's health.MIT
- cloudflare-deployPuts a web project live on Cloudflare Workers and makes it deploy itself from then on. Use when the user says to deploy, put live, host, go to production, connect a domain, set up Cloudflare, set the production keys or make deploys automatic for a project on Workers, including a Next.js app. Building the app itself is cloudflare-new-app, which hands over here at its launch phase. Gets access with the user's API token (the exact steps of the day for creating it), creates the database, bucket and namespace the code binds, applies the schema, sets the secrets (signing keys it generates, provider keys the user supplies), deploys, attaches the domain (one the user owns and moves to Cloudflare, a new one bought through the Registrar API with the price confirmed, or a free workers.dev address), connects the repository so that every push to main deploys and every branch gets a preview, turns on logs and analytics, and writes DEPLOY.md into the project.MIT
- cloudflare-new-appBuilds a new web app from an idea and puts it live on Cloudflare. Use when the user wants a new app, site, service or landing page made and put online, with no expertise needed. For a project that exists and only needs to go live, cloudflare-deploy is the skill. Asks a few plain questions anyone can answer (what it does and for whom, which languages, whether people sign in, a domain or not, the look), plans it, proposes a look, then builds a TypeScript app on the path Cloudflare's framework guide recommends that day (Next.js by default), mobile-first, every language designed in from the first commit, ready for search engines and AI engines (metadata, sitemap, hreflang, structured data, llms.txt), with a share image and favicon set made from its brand, sign-in, a database, analytics, tests and one check, and writes the working agreement a team of developers, planners and designers keeps working under (CLAUDE.md, AGENTS.md, README, status, decisions). Hands over to cloudflare-deploy for the launch.MIT
- meta-ads-setupConnects a web project to Meta ads and runs them end to end, with the agent doing every step a token allows. Use when the user says to connect Meta ads, add the pixel or the Conversions API, run a Facebook or Instagram campaign, put a creative on Meta, or set up ad tracking. Making the creative is higgsfield-shorts-ad; the screens that steer the campaigns are cloudflare-admin-dashboard. Wires the measurement first (a dataset per market, the pixel on public pages only, the Conversions API for leads, checkouts and purchases with deduplication, attribution from the first click to the order, privacy signals honored), creates the datasets and the domain's verification with the business's system user token, maps the ad accounts and syncs spend, builds campaigns from finished creatives in the shape a working account runs them, created paused and turned on only after the budget is confirmed, and writes the monitoring and optimization rules the operator panel applies.MIT
- skillcdn-document-answerAnswers a question from a pack of documents served through SkillCDN (a handbook, a manual, a policy set, an archive), with every citation verified against the section it quotes, and says plainly what the pack does not say. Use when a user asks "what does the handbook say about this", "answer this from our documents", "is this true according to the manual", "which document covers this", or puts a question to any document pack, and wants the answer now with its sources rather than a note kept for later. Frames the question in the pack's words, reads the maps, searches by words and by meaning where the deployment does, reads the sections a result names by their offset and limit, drafts the answer, re-reads every cited section to check each quote word for word and drops what does not hold, and answers with the path, the heading, the offset and the limit of each citation. To keep the answer as a note in the pack, or compile a reference, use skillcdn-document-research. Nothing is spent.MIT
- skillcdn-document-packTurns documents a person has (PDF, Word, slides, spreadsheets, HTML, wiki and chat exports, plain text) into a pack of documents in the SkillCDN Format, in a repository they own, so that agents browse, search and read them through SkillCDN. Use when the user wants a body of documents made searchable and readable by agents, wants to add documents to a pack, or asks for a handbook, a manual or an archive as a pack. To work with a pack that exists, use skillcdn-document-research. Surveys the sources, plans the layout with the user, converts each document to Markdown with the tools the agent has, lays them out one file per document or chapter with a title and a description, keeps each original in sources/ beside its documents, writes the map of every set, keeps the figures with their words and transcribes the scans, points out what looks private with the repository's visibility for the user to decide, declares the roots and the language in the manifest, checks it with the indexer's own check and commits it.MIT
- skillcdn-document-researchAnswers a question from a large pack of documents (a handbook, a manual, an archive) through SkillCDN, compiles a reference or checks a claim, and keeps what it learned for the next time. Use when the user asks something of a handbook, a manual, an archive or any pack of documents, wants a summary or a comparison across its documents, or wants a question answered once and kept. To turn documents into a pack, use skillcdn-document-pack. Reads the map of each document set first, searches by the words the documents use in their own language, reads the sections a result names by their offset and limit rather than whole files, walks a long document by its outline, quotes every finding with its path and heading, says plainly what the pack does not say, and writes the answer as a research note committed to the pack's repository when the user owns it.MIT
- skillcdn-skill-authoringTurns work a person and an agent have already done together into a skill in the SkillCDN Format, in a checkout of this repository or a fork of it. Use when the user says to make what was just done into a skill, to add a skill for a tool or a job to the skills repository, or to improve a skill from a run. For a skill that will not live in a repository of this layout, the host's own skill creator is the better choice. Reads the session it runs in first (the request, the steps, the questions, the user's corrections, what was approved, what a draft was rejected for), then earlier transcripts, memory and results where the user points; keeps the method and leaves the product and the people out; designs what is asked, what is derived, where the user is consulted and what makes a result accepted; writes the skill in this layout with discovery in place of values; checks it; has a fresh agent follow the files alone; ships it with its catalog rows. Also folds a run's findings back into an existing skill.MIT
- skillcdn-skill-verificationVerifies a skill in a repository of the SkillCDN Format the way a user's agent will meet it. Use when the user says to verify, test, dry-read or try a skill from a fresh session, to check that a skill still works after a change, to see whether a fix holds, or to bring the skills up to date after a release of SkillCDN or the console. To make a new skill from work already done, use skillcdn-skill-authoring, which verifies its own draft. A fresh agent dry-reads its files for every place it would have to guess, another runs the served skill with its checkpoints answered as the user would, and what both find is folded into the sentences it bears on. Reads what is served, or a local change before it is pushed; compares old and new text after a tool, a model or a shared page changed, and reads a release's changelog and spec against every sentence about the service; checks every quote; keeps the run's subject, lines and outputs out of the repository; pushes only on the user's word and reruns at most once unasked.MIT
- stripe-paymentsTakes payments on a web project with Stripe, from a sandbox to live money, with the agent doing every setup step a key allows. Use when the user says to take payments, add checkout, sell something, charge for a feature, add a subscription, or connect Stripe to a site, on Cloudflare Workers by default. The screens that show the money and refund an order are cloudflare-admin-dashboard; the ads that bring the buyers are meta-ads-setup. Asks what is sold, at what price and who the seller of record is, builds the order ledger, the hosted Checkout, and the return and webhook that settle an order exactly once (refunds, disputes and subscriptions included), registers the products, prices and webhook endpoint through the API, proves the flow in a sandbox with the Stripe CLI and a test card, then switches to the live keys and endpoint, lists the dashboard-only settings a person must set, and writes docs/payments.md with the operator panel's spec.MIT