Cloud-based Blender: render 3D models, generate turntable videos, and convert file formats without local installs.
Publisher
Skills by agentpmt
127 published skills, 323 installs in total.
Extract text, structured entities, and metadata from any PDF, image, or scanned document.
Generate install-ready Minecraft Bedrock add-ons, skin packs, Fabric and NeoForge mods with runtime verification and visual proof.
Search a global news database of 1M+ weekly articles with boolean operators and category filters.
Turn any audio recording into searchable text with speaker labels
Connect to Gmail to send, read, search, and manage emails including labels, drafts, and attachments.
Build multi-step AI agent workflows that chain tools, prompts, and approval gates into reusable pipelines—no code required.
Connect AI agents directly to Stripe — full read/write for customers, subscriptions, invoices, refunds, and payments.
Generate cryptographically secure seeds, UUIDs, tokens, passwords, and prime pairs using quantum or standard randomness.
Sample from probability distributions and run Monte Carlo simulations via remote tool calls.
Fetch any live webpage and get HTML, Markdown, or screenshots through structured tool commands.
Generate charts from data in 9 types with 5 preset themes and 4 export formats.
Connect an agent to Google Docs: create, edit, format documents with tables, images, headers, and export to PDF, DOCX, HTML.
Speak a procedure out loud during a walkthrough and receive a numbered SOP document.
Turn meeting promises in Plaud recordings into Google Calendar events automatically.
Get correct terminology in every Plaud transcript by maintaining your own glossary.
One transcript, multiple summary formats in a single pass.
Dictate field measurements out loud; they land in your spreadsheet as a row without any typing.
Render deterministic PNG icons and pixel-art sprites at any size from drawing instructions
Post, reply, search, and monitor X (Twitter) directly from AI agent workflows — with media upload, DMs, and List management.
Static map images with custom markers, paths, and four map types, delivered as downloadable URLs and inline PNGs.
Instant domain availability checking with brandable suggestions and one-click registration links.
Make a rational buy/defer/reject decision for one machine service call before any payment.
Store, version, and reuse the knowledge your AI agents rely on — brand guidelines, SOPs, product facts, and tone rules — so every agent stays in sync without m…
Reach inbox zero automatically — AI classifies and archives your Gmail every hour, with Telegram alerts for important messages.
Query population totals, growth rates, age structure, fertility, migration, and urban-rural data for any country using World Bank indicators.
Make HTTP requests to any public URL with all standard methods, authentication schemes, and body formats.
Query World Bank climate and environmental data by country name or ISO code.
Query crop yields, food security indicators, and land use data for 200+ countries through natural language.
Query World Bank fiscal and debt data for any country, with debt sustainability ratios included.
Query World Bank governance indicators for any country—corruption control, rule of law, effectiveness, and more.
Discover nearby businesses, search by keyword, and convert addresses to coordinates using Google Maps data.
Find the most efficient order to visit 2-25 stops, with route maps and turn-by-turn directions.
Control a real, logged-in browser in any web account without sharing your password.
Backs up Plaud recordings to Google Drive with transcripts and logs everything in a spreadsheet.
Describe an AI agent in plain language and get a working agent with tools, workflows, and your own context attached.
Inspect a payment endpoint before committing—check x402 or MPP offers without credentials or payment.
Query official AgentPMT resources from any AI agent.
Search and retrieve Pocket recordings, transcripts, and AI summaries through an AI assistant.
Convert between base64, hex, and binary formats, or encode files for cloud storage.
Generate downloadable 3D models from images or text prompts with configurable polygon counts, textures, and PBR outputs.
Generate secure tokens, hash data, compute HMACs, sign messages, and encrypt/decrypt with AES-256-GCM — all from a single toolkit.
Look up US property records, get value and rent estimates with comparable properties, and retrieve aggregated market statistics by zip code.
Ingest OHLCV data to generate trading signals, backtest strategies, and measure risk with MAE/MFE analytics.
Get exact phrase matches with character positions to fix banned content before publishing.
Handles percentages, ratios, rounding, random numbers, aggregates, and GCD—returns both raw values and formatted output.
Connect your own Telegram bot to an AI agent for branded two-way messaging, media sharing, and inbound message handling.
Query World Bank education statistics by country with natural language.
About Ottermind skills
Every published skill from agentpmt. Following a publisher whose work already fits how you operate is often faster than evaluating individual skills one at a time.
Skills cover the full range of what an Ottermind agent does: building editable PowerPoint decks, generating product and brand images, writing and running code on a machine you connect, producing video from a script or a still, and cleaning and analysing spreadsheet data. A skill is what turns a general model into something that handles your specific version of one of those jobs the same way every time.
A skill is a plain Markdown file with a short frontmatter header, which means you can read exactly what it will do before running it, edit it to match your own conventions, and share it with colleagues. Once a skill produces the result you wanted, it can be attached to an agent or scheduled as an automation so the same work happens again without anyone rewriting the prompt.
- What is an Ottermind skill?
- A reusable instruction package written in Markdown. It gives an agent the context, steps, and constraints for one kind of task, so results stay consistent instead of depending on how well you phrased the prompt that day.
- How do I install and use a skill?
- Open any skill's detail page, read the full document, and install it into your workspace. From then on the agent can use it automatically when the task matches, or you can invoke it by name.
- Can I create my own skill?
- Yes. A skill is a Markdown file with frontmatter naming it and describing when it should be used. If you have a workflow you keep re-explaining to an agent, writing it down once as a skill is usually the shortest path to making it repeatable.
- Do skills cost extra?
- Browsing and installing skills from this library does not cost anything on its own. Running one consumes the same credits as any other agent task, depending on the model you choose and how much work the task involves.