Deep Research
Skill Verified ActiveRun autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.
To automate in-depth research and information synthesis, providing users with comprehensive, cited reports for tasks like market analysis, competitive landscaping, and literature reviews without manual effort.
Features
- Autonomous research planning, searching, and reading
- Information synthesis into comprehensive reports
- Support for multiple output formats (Markdown, JSON, Raw)
- Real-time progress streaming and status monitoring
- Continuation of previous research tasks
Use Cases
- Performing in-depth market analysis and competitive landscaping
- Creating detailed literature reviews for academic or technical purposes
- Conducting technical research and due diligence on specific topics
- Generating cited research reports on demand
Non-Goals
- Performing real-time conversational chat
- Executing arbitrary code or system commands
- Providing a generic web scraping tool
- Replacing direct user interaction with APIs for simple data retrieval
Workflow
- User requests research via `--query`
- Skill provides estimated time and streams progress
- User monitors progress with `--stream` or polls with `--status`
- Skill returns formatted results (Markdown, JSON, or Raw)
- User can continue research with `--continue` or list past tasks with `--list`
Prerequisites
- Python 3.8+
- httpx: `pip install -r requirements.txt`
- GEMINI_API_KEY environment variable
Protocol
- info:Idempotent retry & timeoutsThe script mentions timeouts and a risk of API errors, but explicit details on idempotency for mutations or hard per-call timeouts are not detailed.
Installation
npx skills add davila7/claude-code-templatesRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedTrust Signals
Similar Extensions
Chat Format
100Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
Recursive Research
100Investigación recursiva profunda con loop auto-regulado hasta nivel PhD. Aplicable a cualquier dominio (ciencia, tecnología, negocio, arte, humanidades). Usa WDM + Inversión Munger para decisiones autónomas, tiering de fuentes confiables, y checkpointing a disco para sobrevivir límites de contexto.
Researchers Journalism
100Researches investigative articles, interviews, and news coverage. Use when research needs journalistic sources for cross-referencing or additional context.
Notion Research Documentation
100Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Turns scattered information into structured reports with proper citations and actionable insights.
Ccg
99Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results
Survey Theoretical Literature
99Survey and synthesize theoretical literature on a specific topic, identifying seminal papers, key results, open problems, and cross-domain connections. Use when starting research on an unfamiliar theoretical topic, writing a literature review for a paper or thesis, identifying open problems and research gaps, finding cross-domain connections, or evaluating the novelty of a proposed theoretical contribution against existing work.