Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access."..." for exact phrases · Try typography, debugging or spreadsheetBuilds, publishes, and verifies a Deepline Play as a durable state machine over Customer DB tables. Includes a small paid pilot and is intended for explicit requests to build an engine.
Supports reporting feedback, bugs, and session details to the Deepline team. Also covers reporting unusually slow or stuck Plays and unnecessary product steps.
Handles go-to-market prospecting, data enrichment, outreach, and Deepline Play work or audits. Supports a broad range of data, CRM, outreach, and workflow providers.
Covers beta event feeds for job posts, email replies, funding, and intent signals. Streams events into a warehouse and triggers Plays, subject to a monitor-access check.
Supports finding companies and people, enriching CSVs, locating contact details, comparing providers, and creating Plays, webhooks, or cron workflows. Uses small provider experiments to guide live information gathering and revisit misses.
Supports human review loops for Deepline Play results, including spreadsheet-based feedback, run comparisons, evaluation, and bounded iteration. Returns feedback, labels, or approvals to the agent and supports standing rules or regression cases.
Redirects legacy deepline-pre-research requests to deepline-research. Covers discovery of providers, social sources, public and private datasets, CRM data, and customer messaging or pain language.
Introduces Deepline through a quick demonstration recipe showing how the product works.
Generates a polished Markdown reading note for a single paper identified by title, DOI, URL, arXiv ID, Zotero item, or local PDF. Includes structured analysis and figure placeholders, and writes the note into an Obsidian-style vault.
Provides expertise in DeepSeek-OCR, a vision-language model for optical character recognition. It covers context optical compression and processing documents, PDFs, and images.
Develops DeepStream pipelines for video analytics and GStreamer-based processing using Python pyservicemaker. Covers TensorRT inference, object detection and tracking, and Kafka or message broker integration.
Brings supported object detection models from HuggingFace or NVIDIA NGC into DeepStream. Automates ONNX downloads, SafeTensors export, TensorRT engine builds, custom bounding-box parsers, multi-stream benchmarks, and PDF reporting.
A growing collection of real, public skills. Descriptions and instructions indexed 25 Sept 2026.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name