$ loading_
Conduct deep multi-source research and synthesize insights on complex topics.
The materials indicate this is an open-source, prompt-only research orchestration skill with no declared secrets, remote endpoints, or direct system privileges. Overall risk is low, but its practical safety still depends on the host agent platform and the boundaries imposed on spawned subagents.
The materials explicitly state that no keys or environment variables are required, and the README does not ask for tokens, accounts, or other sensitive credentials, so credential exposure appears low.
The skill itself declares no remote endpoints, but its core purpose is to delegate research to subagents with web search, web fetch, and GitHub search capabilities; therefore, normal task-driven outbound sharing of query content is possible, though no suspicious or unrelated endpoints are identified.
Per the objective checks, this is a prompt-only skill. The README is primarily workflow guidance and agent-role constraints, and does not show that the skill itself executes code locally, starts processes, or directly invokes shell/system commands.
The README instructs saving the final report to a file and mentions using subagents for local codebase exploration, so when the host platform permits it, the workflow may read local materials and write report files; this is a typical data-access pattern for research tools, with no clear signs of overbroad authorization in the materials.
The source is a GitHub-hosted open-source repository, which improves auditability. Although it has 0 stars, no declared license, and unknown maintenance status—introducing some uncertainty around adoption and governance—there are no high-risk red flags such as closed-source distribution, abandoned binary delivery, or suspicious install payloads.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "research" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/vscode-team-kit/main/research/skills/research/SKILL.md 2. Save it as ~/.claude/skills/research/SKILL.md 3. Reload skills and tell me it's ready
Please conduct deep research on the AI coding assistant market, covering key vendors, core features, pricing models, target users, differentiation, and recent trends, then compile a structured report.
A structured research report with market landscape, competitor comparisons, trend summary, and key conclusions.
Please research vector database architecture, explaining core components, indexing methods, query flow, performance bottlenecks, common optimization strategies, and the pros and cons of leading solutions.
A clear technical deep-dive covering architecture principles, solution comparisons, and optimization recommendations.
Please comprehensively investigate the current use of AI agents in enterprises, analyzing use cases, implementation challenges, representative examples, risks, and future opportunities.
A multi-angle synthesized analysis that helps quickly understand the topic’s current state and future direction.
Multi-source research orchestrator. Decomposes a query into parallel research threads, delegates search to subagents, iterates until quality gates pass, then synthesizes a citation-rich report.
You are a research orchestrator. You plan research, delegate ALL investigation to subagents, evaluate findings, re-dispatch as needed, then synthesize.
This is a completely autonomous research workflow:
You are the orchestrator. You plan, evaluate, and synthesize — subagents do the searching.
Identify the query type to determine research scope, agent selection, and report structure:
| Type | Focus | Subagent preference | Report emphasis |
|---|---|---|---|
| Technical deep-dive | Code, architecture, implementation | research:researcher for GitHub repos/code, explore for local codebase | Component sections, code examples, architecture diagrams |
| Conceptual/explanatory | How things work, design decisions, context | research:researcher for web + code, general-purpose for broad synthesis | Clear explanation, trade-offs, background |
| General research | Trends, comparisons, market analysis | research:researcher for web search, general-purpose for synthesis | Key findings, comparison tables, analysis |
Also determine research depth:
Break the query into 3-7 focused research threads. Each thread becomes one or more subagent dispatches.
Example for "How does VS Code's extension host work?":
Assign each thread to the best subagent type:
research:researcher — the primary workhorse; has web search, web fetch, GitHub search, and code reading tools; use for most research threadsgeneral-purpose — full-capability agent for complex synthesis, reconciliation, or tasks that need reasoning beyond searchexplore — fast, lightweight codebase investigation; file reading, symbol search, local repo analysis onlyFan out 3-5 parallel subagents for broad discovery. Each covers 1-2 focused threads.
Each dispatch must be narrowly focused. Broad dispatches produce truncated, low-quality results.
❌ Bad — too broad:
Investigate the extension host architecture, IPC protocol, activation system, and API surface.
✅ Good — focused:
Dispatch 1: Research extension host process architecture and lifecycle
Dispatch 2: Research extension host IPC protocol and message passing
Dispatch 3: Research extension activation events and dependency resolution
Use this shape for each subagent:
Research the following focused topic:
**Topic**: <specific narrow topic>
**Context**: <what we already know, if anything, from prior rounds>
**Focus areas**:
1. <specific question or area to investigate>
…
Add emoji reactions to GitHub issues or pull requests quickly.
Let AI agents read and write memory with environment-aware storage fallback.
Gather independent multi-model plans and debates for implementation and architecture decisions.
Get high-signal second opinions on plans, designs, and implementations early.
Create and manage AST ban rules to block specific code syntax patterns.
Set up Component Explorer with CLI, MCP, and VS Code tooling.
Conduct multi-source web research and produce cited, source-attributed reports.
Add semantic search and document retrieval to Deep Research with custom knowledge.
Conduct market research and competitive analysis with sourced, decision-ready summaries.
Break down complex research questions and produce structured, credibility-scored reports.
Conduct multi-source web research and synthesize citation-backed findings efficiently.
Automate end-to-end research from web search to structured executive reports.