Fewer subscriptions.
– More vibe coding.
Open-source tools & agent skills to build the things you’re paying for.
+-----------+ / /| +-----------+ | | build | + | your own |/ | thing | +-----------+
Cut, resize, compress, convert, and add timed zooms to videos with code.
Added 2026-10-07
Cut, resize, compress, convert, and add timed zooms to videos with code.
Added 2026-10-07What you can build
- Build a video export app that turns one recording into landscape, square, and vertical versions using your own crop presets.
- Watch a folder for new recordings, compress each file, and save a thumbnail beside the finished video for easy browsing.
- Create a demo editor where you choose zoom areas and timing, then render those movements into an uploaded screen recording.
- Combine videos with corrected subtitle files and export a folder of captioned clips with consistent fonts, colors, and placement.
- Turn a folder of video recordings into smaller audio files for transcription, with consistent formats and filenames for the next step.
Try this prompt
Build a local video batch tool using FFmpeg. Let me choose an input folder and export preset, preview the operations, and process files one at a time. Preserve originals, show progress and failures, and save exports separately. Support MP4 conversion, resized exports, and a timed zoom where I choose the target area and start/end times. Use the documented zoompan or crop/scale filters and preserve audio synchronization. Do not assume automatic cursor tracking. Detect available codecs and include setup instructions for my operating system.
Get started
Get FFmpeg
Use the official download page to choose a package or linked build for your operating system. Make sure ffmpeg is available in your terminal.
ffmpeg -versionConvert one file
Place an input.avi file in your working folder and convert it to an MP4. Use a fresh output filename.
ffmpeg -i input.avi output.mp4Save the recipe
Ask your coding agent to wrap a working command in a small script with an input picker, progress output, and a separate export folder.
License & notes
LGPL-2.1-or-later; optional components use GPLNo software fee. Rendering uses your computer or a paid server.
- You supply the editing rules and zoom timing; automatic cursor tracking and choosing highlights require extra code.
- Long videos and complex filters can require substantial CPU or GPU time.
- License obligations depend on the build and codecs. Check the official licensing page before distributing FFmpeg inside a product.
Create videos, animations, and motion graphics with React code.
Added 2026-10-07
Create videos, animations, and motion graphics with React code.
Added 2026-10-07What you can build
- Turn product names, screenshots, and prices into short promotional videos using one reusable React template and assets you provide.
- Create a weekly video report that animates charts from a fresh dataset while keeping the same timing, colors, and layout.
- Build a captioned video template that applies your branding and corrected subtitle timings to a batch of your own clips.
- Generate versions of a product announcement from supplied translations, changing on-screen text while keeping the same images and animation.
- Create a video workflow that renders the same composition in landscape, square, and vertical layouts with format-specific text sizing.
Try this prompt
Use the Remotion skills to build a reusable 15-second product video from a JSON file containing a title, three screenshots, and a call to action. Use only my supplied assets. Make the dimensions configurable, show me the preview, and add a documented MP4 render command.
Get started
Install the skills
Run inside your project and choose your coding agent.
npx skills add remotion-dev/skillsCreate a video project
Use the official starter, then ask the agent to use remotion-best-practices.
bun create videoPreview and export
Review the Studio preview. Ask the agent to render an MP4 when ready.
npx remotion studio
License & notes
Remotion License / see notesSkills have no download fee. Your agent and rendering compute may cost money. Remotion is free for eligible individuals and small organizations; larger companies need a license.Source available
- The standalone skills repository does not publish a separate license grant; the linked license belongs to the upstream Remotion project.
- Remotion is source-available, with free-use eligibility limits. Internal use does not automatically exempt larger companies.
- You supply media, an AI agent, and rendering resources. This does not capture your screen or replace every video-editor feature.
Store app data, handle logins, and accept file uploads on your own server.
Added 2026-10-07
Store app data, handle logins, and accept file uploads on your own server.
Added 2026-10-07What you can build
- Build a customer portal where people sign in, upload documents, and see only the records your access rules allow.
- Create a shared inventory app with item records, stock updates, and an editing screen backed by your own Postgres database.
- Add user accounts and a booking database to a scheduling app, with your own rules for availability and duplicate reservations.
- Store job results, approval decisions, and error messages in a database that your scripts and internal dashboard can both update.
- Make a team workspace with login, file uploads, and project records, keeping storage access tied to each signed-in user.
Try this prompt
Build a small inventory app using my self-hosted Supabase instance. Create SQL migrations for items, locations, and stock movements, plus a simple authenticated interface. Add row-level security so users only see their organization's records. Use the public client key in the browser and keep privileged credentials server-side. Include a test with two organizations proving they cannot read or modify each other's data, and document backups and environment variables.
Get started
Get the self-hosted stack
Install Docker and follow the official Docker guide's manual installation steps to copy a tagged self-hosted release into a new project folder.
Configure the instance
Follow the guide to generate secrets and signing keys, set your app and API URLs, and configure email. Replace all example passwords before startup.
Start and connect
From the configured project folder, start the stack. Open Studio, create a table, enable row-level security, and connect your app with the appropriate client key.
sh run.sh start
License & notes
Apache-2.0 repository; components have their own licensesSelf-hosted software is free. Budget for a server, backups, storage, and email delivery.
- You are responsible for security patches, backups, monitoring, and recovery.
- Self-hosted services do not provide the full managed Cloud platform or its support guarantees.
- Email delivery and SMS authentication need separately configured providers and may add costs.
Fill forms, extract web data, and take screenshots with your AI agent.
Added 2026-10-07
Fill forms, extract web data, and take screenshots with your AI agent.
Added 2026-10-07What you can build
- Collect product names and visible prices from permitted pages into a CSV, preserving source URLs and flagging missing values for review.
- Automate a repeat visit to your own dashboard, apply the required filters, and download the resulting report to a local folder.
- Fill a browser form from reviewed spreadsheet rows, checking each field before submission and recording which rows completed successfully.
- Capture screenshots of a defined list of pages at the same viewport size, saving dated files for a visual review.
- Open your admin app, exercise its search and filtering controls, and record screenshots and results for a repeatable manual review.
Try this prompt
Use agent-browser to visit the public URLs in pages.csv and collect each page title, visible product name, and listed price into a new CSV. Record the source URL, flag missing values, and stop at any login or access restriction. Keep the script so I can rerun it.
Get started
Install the browser CLI
Install the CLI and its browser runtime.
npm install -g agent-browser && agent-browser installInstall the skill
Choose your coding agent in the installer.
npx skills add vercel-labs/agent-browserLoad current instructions
The skill asks the agent to read this before using the browser.
agent-browser skills get core --full
License & notes
Apache-2.0No skill or local browser license fee. Agent/model usage and any cloud browser, proxy, or hosting service cost extra.
- Local execution needs a running computer; scheduling, retries, and monitoring are your responsibility.
- Logins, changing page layouts, and site restrictions can interrupt automation.
- It provides browser control, not a hosted crawler network or guaranteed extraction accuracy.
Record your screen and voice, draw annotations, and export the video for free.
Added 2026-10-07
Record your screen and voice, draw annotations, and export the video for free.
Added 2026-10-07What you can build
- Record a browser bug with narration and drawn annotations, then attach the exported video to a ticket with reproduction steps.
- Build an uploader for exported screen recordings that sorts videos by project and presents them on a simple playback page.
- Pair recorded tutorials with a separate transcription tool, then build a search page that finds instructions inside the resulting text.
- Record a short walkthrough for each completed project, trim the start and end, and save the export beside its handoff documents.
- Create a local organizer for exported training videos, with topic tags, filenames, and links to the documents each recording explains.
Try this prompt
Build a local library for videos I export from Screenity. Let me import a recording, add a title and project tag, and browse recordings with video playback. Keep originals untouched and store metadata in SQLite. Add an optional FFmpeg thumbnail job. Do not assume Screenity has an automation API or upload anything automatically. Document how to import files from its export screen.
Get started
Get the local extension
Download Build.zip from the repository's releases page and unzip it.
Load it in Chrome
Open chrome://extensions, enable Developer mode, and choose Load unpacked. Select the extracted build folder.
Record and export
Record a short walkthrough, review it in the editor, and export a video. Start your custom workflow from that file.
License & notes
GPL-3.0The open-source extension is free. Your own sharing or storage service may cost money.
- The extension depends on Chrome's capture permissions and browser capabilities.
- Self-hosted builds are local-only. Hosted link sharing and Screenity Pro features are separate.
- It is not a complete replacement for Screen Studio's automatic presentation effects or a full video editor.
Design and build landing pages, dashboards, and web interfaces.
Added 2026-10-07
Design and build landing pages, dashboards, and web interfaces.
Added 2026-10-07What you can build
- Build a responsive product landing page using your real copy and screenshots, with a clear download link and mobile layout.
- Redesign an invoice dashboard so overdue items are easy to find, with useful table filters and an obvious next action.
- Add a small web interface around an existing command-line workflow, with file selection, understandable options, and a clear results screen.
- Create the frontend for a searchable catalog, including category filters, readable result rows, and helpful empty states around your existing backend.
- Build a simple team resource site that organizes existing guides, useful links, and contact details into a clear, responsive layout.
Try this prompt
Use frontend-design to build a one-page site for my internal invoice tool in the existing project. Use my supplied copy and logo. Show outstanding invoices first, make the main action obvious, and keep the layout usable on a phone and with a keyboard. Implement and review the result.
Get started
Install the skill
Choose the agent you use for the project.
npx skills add anthropics/skills --skill frontend-designProvide a real brief
Share the audience, page goal, copy, assets, and framework. Ask for frontend-design explicitly.
Build and review
Have the agent implement the page, then inspect mobile layout, focus states, and the main interaction.
License & notes
Apache-2.0Free skill. Your coding agent, model usage, domain, and hosting may have separate costs.
- The skill is guidance, not a drag-and-drop editor, CMS, or hosting platform.
- Generated designs and code still need review; accessibility and responsive behavior are not guaranteed.
- Stock assets, fonts, third-party packages, and hosting have their own terms.
Transcribe recorded audio into text and subtitles on your own computer.
Added 2026-10-07
Transcribe recorded audio into text and subtitles on your own computer.
Added 2026-10-07What you can build
- Build an interview inbox that processes uploaded recordings in a queue and opens each transcript for a person to correct.
- Create timed subtitle drafts from your videos, review names and unclear speech, then send corrected files to your video editor.
- Index transcripts with timestamps so teammates can search an archive of recordings and jump back to the matching source audio.
- Turn recorded voice notes into editable text files, keeping the original audio attached so you can check uncertain words later.
- Add a local transcription step to your podcast workflow, producing a text draft for editing alongside each finished episode.
Try this prompt
Build a local batch transcription app around whisper.cpp. Accept audio files, convert copies to the supported WAV format with FFmpeg when necessary, and save text plus subtitle output beside a source reference. Keep processing on this machine. Provide model and language selection, a queue, progress, and retry controls. Never overwrite recordings. Add a review screen because model transcripts can contain mistakes, and document the required compiler, CMake, and model setup.
Get started
Get the source
Install Git, CMake, and a C/C++ compiler, then clone the project and enter its directory.
git clone https://github.com/ggml-org/whisper.cpp.git cd whisper.cppDownload a model and build
This small English model is a useful first test. Use a multilingual model for other languages.
sh ./models/download-ggml-model.sh base.en cmake -B build cmake --build build -j --config ReleaseTranscribe the sample
Run the included sample, then check the CLI help before processing your own audio. Start with a short WAV file and check which input formats your build supports.
./build/bin/whisper-cli -m models/ggml-base.en.bin -f samples/jfk.wav
License & notes
MITNo per-minute software fee. You provide the computer, model storage, and processing time.
- Transcripts need review, especially for names, accents, noisy audio, and silence.
- Larger models need more memory and can run slowly without suitable acceleration.
- Meeting bots, reliable speaker identification, and summaries are separate features to build or add.
Test forms, buttons, and checkout flows in a real browser.
Added 2026-10-07
Test forms, buttons, and checkout flows in a real browser.
Added 2026-10-07What you can build
- Create a reusable browser test that checks signup validation, submits a test account, and confirms the expected success screen.
- Exercise a checkout in your test environment, checking cart totals, required fields, and the confirmation page using test payment details.
- Test your search interface with known queries, filters, and empty results, saving screenshots and browser logs when an assertion fails.
- Turn a reported interface bug into a short Playwright script that repeats the steps and captures evidence of the failure.
- Build a small release check that starts your app and runs the critical browser journeys you have explicitly defined.
Try this prompt
Use webapp-testing to test the signup form in this local project. Start the dev server, inspect the rendered page, verify empty-field and invalid-email errors, and complete signup with the test account. Save a reusable Python Playwright script and capture evidence of any failure.
Get started
Install the skill
Add the upstream testing instructions to your coding agent.
npx skills add anthropics/skills --skill webapp-testingPrepare Playwright
Use a Python environment, install Playwright, then download Chromium.
python -m pip install playwright && python -m playwright install chromiumTest one flow
Give the agent your dev-server command and a specific journey; ask it to use the bundled server helper and keep the test.
License & notes
Apache-2.0Free skill and local Playwright execution. Agent/model usage and CI machines may cost money.
- It runs the browsers and environment you provide, without a hosted device farm.
- Tests still need stable fixtures, sensible assertions, and maintenance when the UI changes.
- Agent-generated coverage is limited to the flows you request and verify.
Run AI models on your computer to summarize documents and draft text.
Added 2026-10-07
Run AI models on your computer to summarize documents and draft text.
Added 2026-10-07What you can build
- Build a local support assistant that turns ticket notes into draft replies using your templates, with a person approving each response.
- Create a document reader that splits imported text into sections and asks a local model for a short summary of each.
- Suggest categories for incoming notes with a local model, then let a person accept or correct the proposed tags.
- Add a rewrite panel to an internal editor that turns rough paragraphs into shorter drafts while preserving the original text.
- Group pasted customer feedback into suggested themes, show the supporting comments, and let your team correct the model before using the results.
Try this prompt
Build a local notes-to-summary app using Ollama's local API at http://localhost:11434. Let me choose an installed model, paste text, and get a draft summary with the original text alongside it. Split long inputs according to a configurable limit and make failures retryable. Keep every request local, never silently switch to a cloud model, and do not claim the output is factual without review. Include setup, model-license checks, and a small quality evaluation using example notes.
Get started
Install the local app
Download Ollama for your operating system from the official site and start it. Choose a local model rather than a cloud model.
Try a suitable model
Choose a model from the official library that fits your available memory. Read its model card and license, then run a short task in the app.
Connect your tool
Use the documented local API at http://localhost:11434. Keep the chosen model name in configuration and check the server is available before submitting jobs.
License & notes
MIT runtime; model licenses varyLocal inference has no Ollama per-token fee. Hardware and electricity cost money; cloud models are separate.
- The MIT license covers Ollama, not every model you download. Check the selected model's terms.
- Model quality and speed depend on hardware and model size; local models may struggle with complex tasks.
- Local processing applies only when you select local models. Cloud features send requests off the machine.
Create posters, social graphics, and report covers as PNGs or PDFs.
Added 2026-10-07
Create posters, social graphics, and report covers as PNGs or PDFs.
Added 2026-10-07What you can build
- Create an event poster from a title, venue, date, and supplied logo, keeping the generating code for your next monthly update.
- Produce branded report covers from a document title, author, and date, exporting consistent PNG or PDF files for each edition.
- Generate social announcement graphics at your chosen dimensions using approved copy, brand colors, and your own images for each post.
- Design a one-page product information sheet with supplied photos, essential specifications, and contact details, then export a readable PDF.
- Build a repeatable layout for approved customer quotes, with consistent typography, attribution, and spacing across a set of exported images.
Try this prompt
Use canvas-design to create a 1080 by 1350 event poster using my supplied logo, exact event details, and two brand colors. Keep the text readable at phone size. Export a PNG, inspect it for clipping, and preserve a script that lets me update the date next month.
Get started
Install the skill
Select the coding agent that can create and inspect local files.
npx skills add anthropics/skills --skill canvas-designDefine the output
Supply dimensions, exact text, brand colors, and images you can use.
Export and inspect
Ask for a PNG or PDF plus reusable source, then check the final render for clipped text and margins.
License & notes
Apache-2.0Free skill. Agent/model usage and any external images or fonts may cost money.
- This produces files through an agent, not an interactive collaborative design editor.
- The skill does not include a stock-image library; supplied assets and fonts retain their own licenses.
- Check print dimensions, color requirements, and text legibility yourself before production.
Add a search box that handles typos and filters products, pages, or documents.
Added 2026-10-07
Add a search box that handles typos and filters products, pages, or documents.
Added 2026-10-07What you can build
- Add search to a product catalog with category filters, price sorting, and forgiving matching when someone misspells an item name.
- Build a search page for extracted document text, showing matching titles and links back to files your team can access.
- Create a directory search box with category filters and custom synonyms so visitors can find entries using different names.
- Index your help articles and add a search interface that returns relevant guides while a customer types their question.
- Combine transcripts from a separate transcription tool with a searchable index, returning matching passages and links to the original recordings.
Try this prompt
Build a product search interface backed by self-hosted Meilisearch Community Edition. Import a sample JSON catalog with id, name, description, category, and price. Configure searchable, filterable, and sortable attributes, wait for indexing tasks to finish, and show useful empty and error states. Keep the master key server-side and use a limited search key in the browser. Include a repeatable sync job and a test that deleted source records disappear from search.
Get started
Install Community Edition
Use the official self-hosting guide to get the Community Edition binary for your operating system. Pin a stable release when deploying.
Configure and start
Set a strong master key and persistent data location, then start the engine using the self-hosting guide. Keep administrative credentials out of browser code.
Index a small dataset
Import a JSON document list through the API. Wait for indexing to finish, test a few searches, and connect a search-only key to your interface.
License & notes
MIT Community Edition; Enterprise code uses BUSL-1.1Community Edition has no software fee. You pay for hosting, storage, and any external AI services.
- You must build and maintain synchronization from your source database to the search index.
- Enterprise capabilities such as sharding are outside the MIT Community Edition scope.
- Self-hosting requires capacity planning, backups, access controls, and upgrades.
Create animated GIFs, reaction emojis, and short branded loops.
Added 2026-10-07
Create animated GIFs, reaction emojis, and short branded loops.
Added 2026-10-07What you can build
- Animate your original mascot with a small bounce and export a compact GIF that you can check before uploading to Slack.
- Create matching animated checkmarks, warning symbols, and celebration reactions from simple shapes, using the same colors and short looping timing.
- Turn supplied before-and-after interface images into a short looping GIF that shows one product change clearly inside a message.
- Keep one GIF-generating script and produce approved color variants of an animated logo or icon without rebuilding each animation manually.
- Create a short countdown GIF with large readable numbers and a final message, keeping the dimensions and file size suitable for chat.
Try this prompt
Use slack-gif-creator to animate my supplied icon with one gentle bounce. Make a short, seamless 128 by 128 GIF for a team emoji. Keep the file compact, run the bundled validation, and retain the Python script so I can reuse it with another icon.
Get started
Install the skill
Install the complete folder so the Python utilities are included.
npx skills add anthropics/skills --skill slack-gif-creatorInstall its dependencies
In a Python environment, install the packages listed by upstream.
python -m pip install pillow imageio imageio-ffmpeg numpyGenerate and validate
Give the agent an asset and motion brief; ask it to use GIFBuilder and the bundled validator.
License & notes
Apache-2.0Free skill and local GIF generation. Agent/model usage may cost money; supplied assets keep their own licensing.
- Best suited to small, short animations; GIF has limited color and compression quality.
- Slack upload limits can change, so verify the actual upload as well as the bundled checks.
- Python dependencies and image assets have their own licenses; the skill does not provide an asset library.
Build shared tables for leads, inventory, and content, then update them by API.
Added 2026-10-07
Build shared tables for leads, inventory, and content, then update them by API.
Added 2026-10-07What you can build
- Create a content queue with article titles, owners, deadlines, and status fields that teammates edit while scripts import new ideas.
- Track equipment, locations, and responsible people in shared tables, then build a simple lookup page using the database API.
- Let people review imported records in a browser table before a script copies approved rows into your main application.
- Build a small lead tracker with contact details, next actions, and follow-up dates, plus scripts that import your existing contacts.
- Collect research links, notes, categories, and review status in one editable table, then export selected records into a report.
Try this prompt
Build a small content-pipeline integration using the API of my self-hosted Baserow Open Source Edition. Use a table with title, owner, status, and source URL. Import records from a CSV, detect duplicates by source URL, and let a reviewer approve rows in Baserow before a separate dry-run export. Keep the database token server-side. Use only features available in the open-source edition and document the table setup and backup requirements.
Get started
Start a local instance
With Docker installed, run the official all-in-one image with persistent storage. This example binds the web interface to this machine only.
docker run -d --name baserow -e BASEROW_PUBLIC_URL=http://localhost -v baserow_data:/baserow/data -p 127.0.0.1:80:80 baserow/baserow:2.4.0Create a working table
Open http://localhost, create your account and workspace, and import a small CSV or define the fields for one workflow.
Connect an automation
Create a database token with only the required table permissions. Use the generated API documentation to read a row before adding write operations.
License & notes
MIT Open Source Edition; paid editions have separate licensesOpen Source Edition is free to self-host. Hosting and paid edition features cost extra.
- Premium and Enterprise features are separately licensed; self-hosting does not unlock them.
- Moving from another table tool may require rebuilding formulas, views, and integrations.
- You manage the database, file storage, upgrades, and backups.
Build custom connectors that let your AI agent use your APIs.
Added 2026-10-07
Build custom connectors that let your AI agent use your APIs.
Added 2026-10-07What you can build
- Expose product search and stock lookup from your inventory API as read-only tools that your agent can call during a conversation.
- Connect an order API so your agent can retrieve shipment details and order status when helping draft a customer response.
- Wrap an existing document search API with clear tool inputs and source links so your agent can find relevant internal material.
- Build a connector for your issue tracker API that lists assigned tickets and retrieves details for an agent-written daily briefing.
- Expose selected reporting endpoints from your own service so an agent can combine their results into an on-demand operations summary.
Try this prompt
Use mcp-builder to create a local TypeScript MCP server for our documented inventory API. Implement read-only product search and stock lookup, validate inputs, paginate results, and keep credentials in environment variables. Test the tools with MCP Inspector and provide client setup instructions.
Get started
Install the skill
Add the server-building workflow to your coding agent.
npx skills add anthropics/skills --skill mcp-builderScope the connector
Provide the API documentation and start with a few read-only operations. Have the agent follow the TypeScript or Python reference.
Verify the server
Use MCP Inspector to exercise the generated tools before connecting your agent.
npx @modelcontextprotocol/inspector
License & notes
Apache-2.0Free skill. Agent/model usage, hosting, and the APIs you connect may have separate charges.
- MCP supplies agent-facing tools; it does not provide scheduling or a no-code workflow dashboard.
- External APIs still require permission, credentials, and any applicable paid plan.
- You maintain authentication, deployment, monitoring, and safeguards for any write operations.
Build admin pages with tables, forms, and buttons connected to your database.
Added 2026-10-07
Build admin pages with tables, forms, and buttons connected to your database.
Added 2026-10-07What you can build
- Combine customer details from a database and an API into one support screen with search, order history, and internal notes.
- Build a review screen that shows pending records, displays the supporting details, and saves an approval decision to your database.
- Create an inventory admin page with filtered tables and validated forms for updating stock counts, item details, and supplier references.
- Show automation job results from your database in a dashboard, with filters for failures and links to the relevant logs.
- Give operators a table of rejected imports and an editing form so they can correct fields before your backend retries processing.
Try this prompt
Help me build a customer lookup app in self-hosted Appsmith Community Edition. Use a read-only query to search customer records, a detail panel, and a narrowly scoped form for updating an internal note. Provide the SQL, widget bindings, and JavaScript needed. Parameterize queries, handle loading and error states, and require confirmation before writes. Keep credentials in Appsmith's datasource configuration and do not depend on commercial edition features.
Get started
Choose Community Edition
Follow the official Docker guide. Use the appsmith-ce image in its Compose example and pin a release tag; the default example uses the separate commercial edition.
Run and connect
Start the configured Docker Compose stack, create an administrator account, and add a read-only database or API connection first.
docker compose up -dBuild one screen
Add a table widget and connect it to a query. Introduce a form and a confirmed update action only after the read path works.
License & notes
Apache-2.0 Community EditionCommunity Edition has no software fee. Hosting, connected services, and commercial features may cost money.
- Commercial features such as advanced governance are outside Community Edition; check your requirements first.
- It is optimized for internal tools, so a highly custom consumer interface may need a separate frontend.
- The all-in-one deployment includes supporting services and needs more server resources than a static site.
Create slide decks with diagrams, code examples, and speaker notes.
Added 2026-10-07
Create slide decks with diagrams, code examples, and speaker notes.
Added 2026-10-07What you can build
- Generate a monthly update deck from supplied numbers and notes, reusing the same theme and exporting a PDF after review.
- Create a technical workshop deck with highlighted code, diagrams, and speaker notes, keeping live examples interactive in the browser version.
- Turn a product brief and your screenshots into a demo presentation with controlled reveals and notes for the presenter.
- Build training slides from your existing guides, then export a PDF handout while retaining editable Markdown for the next revision.
- Create a presentation template with shared product slides and customer-specific sections that your agent updates from an approved briefing document.
Try this prompt
Use the Slidev skill to turn the supplied product brief into an eight-slide internal demo. Use our screenshots, include speaker notes, and keep all claims grounded in the brief. Make the theme reusable, preview every slide, and export a PDF after checking for clipped content.
Get started
Install the official skill
Select your coding agent in the installer.
npx skills add slidevjs/slidevCreate a slide project
Use a current Node.js environment and follow the starter prompts.
npm init slidev@latestBuild and preview
Ask your agent to edit slides.md using the skill, then review the deck in the browser.
npm run dev
License & notes
MITFree skill and Slidev runtime. Agent/model usage and optional hosting or third-party assets may cost money.
- Requires a JavaScript project and agent; it does not include a managed collaborative deck workspace.
- Standard PPTX export uses slide images. Editable PPTX export has layout limits and can fall back to images for unsupported content.
- Interactive browser features do not fully survive file export; CLI exports also require playwright-chromium.
Count website visits, see traffic sources, and track signups and button clicks.
Added 2026-10-07
Count website visits, see traffic sources, and track signups and button clicks.
Added 2026-10-07What you can build
- Track several websites in one self-hosted instance and compare visits, popular pages, and traffic sources from a dashboard you control.
- Add events to download buttons so you can compare which pages and calls to action generate interest in your product.
- Use tagged links for launches and newsletters, then review the traffic they bring to your site alongside recorded signup events.
- Instrument your directory search with a few carefully chosen events to see how often visitors search and open a result.
- Record visits and key actions on your internal tool, then review which pages people use and which features receive little activity.
Try this prompt
Add my self-hosted Umami instance to this website. Make the script URL and website ID configurable, load the tracker once, and track three agreed actions with clear event names. Do not send names, email addresses, or free-text form contents as event properties. Verify one visit and one test event in the receiving instance, explain how to exclude development traffic, and document where the script is configured.
Get started
Get the Docker configuration
Install Docker and Git, then clone the official repository. Review the supplied Compose configuration and use a stable release for deployment.
git clone https://github.com/umami-software/umami.git cd umamiStart your local instance
The supplied Compose file runs Umami with PostgreSQL. Open http://localhost:3000 and change the default administrator password immediately.
docker compose up -dTrack one site
Add your website in the dashboard and install its generated tracking script. Trigger one test visit and one named event, then verify both appear.
License & notes
MITSelf-hosted software is free. The application server, database, storage, and backups are your costs.
- You maintain the server and PostgreSQL database, including backups and retention.
- Browser blocking and failed network requests can make analytics counts incomplete.
- Complex product analytics or attribution workflows need their own evaluation; basic event tracking is the comparison here.
Create editable mind maps, flowcharts, and visual project boards.
Added 2026-10-07
Create editable mind maps, flowcharts, and visual project boards.
Added 2026-10-07What you can build
- Turn research notes and source links into a visual map, grouping related findings and labeling connections between the main ideas.
- Convert a written onboarding process into an editable flowchart with owner groups, decision branches, and links to the relevant instructions.
- Generate a project board that connects milestones, supporting documents, and task dependencies in a canvas you can rearrange in a compatible app.
- Arrange article ideas into topic groups, connect related pieces, and attach links to drafts so a team can review the structure.
- Map the main parts of an internal system as connected cards, with short explanations and links to existing documentation for each component.
Try this prompt
Use json-canvas to turn the supplied onboarding process into an editable .canvas file. Group steps by owner, label decision branches, and link each step to its source document when available. Keep the layout readable, validate all IDs and edge references, and preserve the original wording.
Get started
Install the skill
Choose your coding agent and add the JSON Canvas instructions.
npx skills add kepano/obsidian-skills --skill json-canvasGenerate a canvas
Supply your notes or process. Ask for a .canvas file with groups, labeled connections, and validated node IDs.
Open and review
Place the file in an Obsidian vault, or open it in another JSON Canvas-compatible app. Check spacing, references, and connections.
License & notes
MITFree skill and open file format. Agent/model usage and any paid viewer, sync, or collaboration service are separate.
- The skill and JSON Canvas format are open; Obsidian is a separate application with its own license.
- This does not include real-time collaboration, team permissions, or a hosted board-sharing service.
- A compatible viewer is required. Linked files and embedded content must remain accessible when you move or share the board.
Run scheduled jobs, connect app APIs, and trigger actions when new data arrives.
Added 2026-10-07
Run scheduled jobs, connect app APIs, and trigger actions when new data arrives.
Added 2026-10-07What you can build
- Fetch data from several APIs on a schedule, combine the results, and save a daily report for your team to review.
- Receive a webhook, validate its fields, transform the payload, and forward the information another service needs with your own error handling.
- React to messages from local devices and call your own services when readings meet conditions you define in the workflow.
- Build a scheduled sync between two systems with APIs, mapping fields and adding checks to avoid creating duplicate records.
- Check an API for inventory levels or service status and send an alert through your configured provider when a threshold is crossed.
Try this prompt
Create an importable Node-RED flow for a daily report from two configurable HTTP APIs. Use an Inject node for scheduling, transform the responses into one JSON report, and write it to a local file. Add timeouts, a Catch path, bounded retries, and a manual test trigger. Store credentials outside exported flow JSON. Explain every node and how to configure editor authentication before remote access. Avoid paid or unmaintained community nodes when core nodes can do the job.
Get started
Install Node-RED
Install a supported Node.js version and use the official local installation guide. With a user-owned npm global directory, install the package below.
npm install -g node-redStart the editor
Start the runtime and open http://localhost:1880. Keep it on a trusted local network until you configure the documented access controls.
node-redBuild a first flow
Connect an Inject node to a Function node and then a Debug node. Deploy, inspect the output, and replace the sample logic with one real API call.
License & notes
Apache-2.0No per-task Node-RED fee. Always-on hosting and connected paid APIs can still cost money.
- The editor is not secured by default; configure authentication and HTTPS before exposing it remotely.
- Third-party nodes vary in maintenance, and API connectors may need custom configuration or code.
- Retries, duplicate prevention, monitoring, and external API limits remain your responsibility.
Find broken links, missing page titles, and other SEO problems.
Added 2026-10-07
Find broken links, missing page titles, and other SEO problems.
Added 2026-10-07What you can build
- Review a new website for indexing blocks, missing titles, and broken internal links, producing a prioritized checklist with evidence for each finding.
- Check a website after a domain or URL change, reviewing redirects, canonical links, and crawlability against your intended page mapping.
- Create an inventory of titles and descriptions across selected pages, identify missing or repeated wording, and draft improvements for review.
- Inspect links across your important pages, flag broken destinations, and suggest relevant connections between related content that already exists.
- Combine supplied Search Console reports with page checks to build a repair queue, separating verified indexing problems from hypotheses needing investigation.
Try this prompt
Use seo-audit to review these ten pages and the site source. Check crawlability, canonicals, page titles, internal links, and rendered structured data. List only issues you can demonstrate, include the affected URL and evidence, and prioritize three fixes. Separate observations from hypotheses.
Get started
Install the skill
Select SEO Audit and your coding agent.
npx skills add coreyhaines31/marketingskills --skill seo-auditSupply the evidence
Provide the site URL, business goal, target pages, and any Search Console or crawler exports.
Audit and verify
Ask for evidence-linked findings; verify each issue before changing the site and recheck affected pages afterward.
License & notes
MITFree skill. Agent/model usage may cost money. Search-volume, backlink, and rank-tracking data are separate services.
- It does not provide proprietary search-volume, backlink, or ranking datasets.
- Rendered pages and Search Console evidence may be needed; static HTML alone can miss client-side behavior.
- Findings depend on the evidence supplied, and recommendations do not guarantee rankings.
Prepare localized App Store metadata and assets from Claude Code.
Added 2026-10-07
Prepare localized App Store metadata and assets from Claude Code.
Added 2026-10-07What you can build
- Use the skill to explore keywords by market. Connect an ASO data provider for popularity and difficulty data, or expect degraded research without one.
- Generate keyword-led names, subtitles, keyword fields, and descriptions for selected locales, then review the output before publishing.
- Add translated headings to supplied screenshot mockups using the bundled renderer; the workflow supports right-to-left layout and auto-fitting text.
- Choose a pricing model and apply prices through the App Store Connect API, with read-back verification.
- Translate UI strings with checks for issues such as format-specifier drift, then produce a checklist that identifies steps requiring manual completion.
Try this prompt
Review the Vibe ASO skill and implement one focused improvement: add a validation step for localized App Store metadata that checks required fields and reports locale-specific issues before upload. Follow the project’s existing conventions, avoid exposing credentials, document the behavior and any prerequisites, and add tests for valid and invalid metadata without making unsupported claims about data-provider coverage.
Get started
Install the skill
In Claude Code, register the Vibe ASO marketplace and install its plugin, following the README’s instruction to wait for the first step to succeed before proceeding. Alternatively, the README documents a direct-clone installation into your Claude skills directory.
Open your iOS app project
Start Claude Code in your app’s repository and ask it to do the ASO or request a specific workflow, such as keyword research or screenshot localization.
Complete the setup wizard
Provide an App Store Connect API key if needed, choose a translation engine, and select a keyword data source. The README says keyword research works best with an ASO tool and supports a degraded mode without one.
License & notes
MITMIT-licensed, with no Vibe ASO subscription stated. Bring your own App Store Connect API key and pay any applicable model/API usage; the README estimates about $0.50 per app for a full in-app localization cascade using DeepSeek. Claude usage may incur charges. Optional phase-specific requirements include fastlane, Node and Playwright, fonts, Ruby, and Xcode command-line tools.
- Designed for macOS and iOS app workflows.
- Keyword research depends on an external ASO data source for popularity and difficulty metrics; without one, the README describes degraded mode.
- Requires an App Store Connect API key for relevant API operations. Uploading uses fastlane; rendering and in-app localization have additional phase-specific tool requirements.
- Screenshot localization renders translated headings onto user-supplied mockups; it is not a screenshot research or creative-testing suite.
- The submission checklist calls out API-inaccessible tasks for manual completion; it does not automate every publishing step.
No matches.
Try another project or subscription.