deep-research
Organizes academic literature review into six phases. Produces phase-specific notes, a curated paper database, and a final synthesis report.
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 spreadsheetOrganizes academic literature review into six phases. Produces phase-specific notes, a curated paper database, and a final synthesis report.
Assists with literature and systematic reviews, research question formulation, methodology design, and evidence synthesis. Supports fact-checking, Socratic research dialogue, and APA 7.0 research reports.
Combines parallel web searches, multi-source validation, and confidence tracking into thorough cited reports. Covers market, technical, competitive, academic, financial, legal, organizational, trend, product, domain, and community research.
Searches for skills that match a task and provide practical guidance. Supports explicit skill discovery requests and agent-initiated searches when a task is unfamiliar, attempts have failed, or suitable tools are missing.
Orchestrate one or more thinking frameworks to work through any problem, decision, document, or idea rigorously. Diagnoses which frameworks fit — inversion, pre-mortem, assumption-mapping, socratic, adversarial-hat — then guides the user through them in the right sequence. Load when the user asks for deep thinking, says "help me think through this properly", "apply your best thinking frameworks", …
Builds a minimal local Deep Agent in Python using the official quickstart. Uses provider-native web search instead of Tavily.
Builds a minimal local Deep Agent in TypeScript using the official quickstart. Uses provider-native web search instead of Tavily.
Supports molecular property prediction, including ADMET and toxicity, using traditional machine learning or graph neural networks. Provides extensive molecular representations, pretrained models, and MoleculeNet benchmarks for experimentation.
Supports DeepEval evaluation of agents, chatbots, RAG pipelines, and LLM applications. Covers dataset generation, Python SDK and pytest suites, CLI runs, traced and online evaluations, Confident AI reporting, and improving prompts, tools, retrieval, or behavior based on failures.
Analyze and detect synthetic media, including deepfake videos, AI-generated images, and cloned voice audio. Use this skill when investigating potential disinformation campaigns, verifying the authenticity of digital evidence, or assessing social engineering attacks leveraging synthetic media (e.g., vishing with voice clones, spear-phishing with deepfake video calls). Covers artifact analysis, freq…
Transforms CRM, customer, and contact data into B2B paid advertising audience lists. Covers enrichment, auditing, and uploads to Google Customer Match, Meta Custom Audiences, and LinkedIn Matched Audiences.
Analyzes RevOps, GTM metrics, revenue, funnels, customers, and pipelines with Deepline. Supports Snowflake queries and semantic-layer analysis, while routing prospecting and outreach to deepline-gtm.
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