research-agent
Deep research with structured reports and charts. ONLY use when the user explicitly requests research/analysis, or needs data visualization with charts, or quantitative/comparative analysis across multiple sources. Do NOT use for simple questions or quick lookups.
What this skill does
# Research Agent
Autonomous research agent that plans, searches across the web, synthesizes findings, and returns a structured markdown report with citations and charts.
## When to use — ALL of these require explicit user intent or clear analytical need
- The user explicitly asks for "research", "report", "analysis", "deep dive", or "investigate"
- The user needs data visualization — charts, graphs, trend plots
- Quantitative or comparative analysis across multiple data points (market sizing, benchmarking, statistical comparisons)
- Multi-section structured reports (literature reviews, competitive analyses, technology surveys)
## When NOT to use — default to simpler tools first
- General conversation, Q&A, or factual questions — answer directly
- A single lookup that `wikipedia_search` or `google_web_search` can resolve
- Summarizing a single article or URL — use `fetch_url_content` instead
- Code-related tasks — use the `code-agent` skill
- Browser automation — use the `browser-automation` skill
- Email, calendar, or other tool-based tasks — use the appropriate skill directly
**Important**: When in doubt, do NOT delegate to research-agent. Use `google_web_search` or other tools directly. Only escalate to research-agent when the task clearly requires multi-source synthesis, structured reporting, or chart generation.
## How to invoke
Call the `research_agent` tool with a single `plan` argument. The plan is free-form prose; include:
- **Objectives** — what the user is trying to learn or decide
- **Topics** — the specific angles / subtopics to cover
- **Structure** — the section layout you want in the final report
Example:
```
research_agent(plan="""
Research Plan: AI Code Assistant Market 2026
Objectives:
- Current market size and growth trends
- Leading products and differentiators
- Enterprise adoption barriers
Topics:
1. Global market statistics and forecasts
2. Top products (Copilot, Cursor, Claude Code, etc.) and positioning
3. Pricing models and enterprise SKUs
4. Security/compliance concerns raised by buyers
Structure:
- Executive Summary (3-5 bullets)
- Market Overview
- Product Landscape
- Enterprise Adoption
- Outlook
""")
```
The agent streams `research_step` progress events as it works. The final result is a markdown report saved as a research artifact in the canvas.
## Output
- Markdown report with `#`/`##` headings, bullet lists, and inline citations
- Any charts the agent generated are embedded in the markdown
- The full report is also persisted as an `artifacts` entry so the user can open it from the canvas
## Guidelines for the orchestrator
- Don't fabricate the plan — use the user's own words and just structure them into objectives/topics/structure. If the user only gave a one-line request, expand it into 2-3 objectives but stay true to intent.
- One research_agent call per user request. Don't fan out multiple parallel calls.
- If the user asks a follow-up ("add a section on X", "dig deeper into Y"), call `research_agent` again with an updated plan — the agent itself does not have persistent memory across calls.
- After the tool returns, do NOT restate the whole report in chat. The report is already rendered as an artifact; a 1-2 sentence summary pointing the user to the canvas is enough.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.