deep-research
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, verified claims, or comparison of approaches. Triggers include "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". Do NOT use for simple lookups, debugging, or questions answerable with 1-2 searches.
npx skills add majiayu000/claude-skill-registry --skill deep-research-maxmiksa-auto-company --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Deep Research performs enterprise-grade analysis that synthesizes information from multiple sources, tracks citations, and verifies claims. It is intended for use when a user needs comprehensive analysis that typically involves 10+ sources, verified claims, or comparisons of approaches. It is triggered by phrases such as "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". It should not be used for simple lookups, debugging, or questions answerable with 1-2 searches.
How it works
The skill operates through an 8-phase pipeline: Scope, Plan, Retrieve, Triangulate, Synthesize, Critique, Refine, Package. It uses a structured workflow: clarify autonomously, plan a mode (Quick, Standard, Deep, UltraDeep), then execute phase tasks including SCOPE, PLAN, RETRIEVE (parallel searches with multiple agents), TRIANGULATE, OUTLINE REFINEMENT, SYNTHESIZE, CRITIQUE, and REFINE, followed by PACKAGE to produce a comprehensive report. It enforces an anti-hallucination protocol: every factual claim must cite a source, distinguish fact from synthesis, and include explicit sources. It performs parallel retrieval with 5-10 independent search angles and 3-5 parallel task agents, updating progress and validating outputs via Python scripts. The final report is generated using a template and packaged into Markdown, HTML, and PDF formats, saved to a dated folder, and opened automatically.
When to use it
Use when the query requires complex, verification-heavy analysis and multiple sources. Triggers include phrases like "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". Do not use for simple lookups or questions that can be answered with 1-2 searches.
What it can touch
The skill relies on the claude-code tool for automation and parallel task execution. It references external scripts for validation and citation verification, including: python scripts/verify_citations.py --report [path] and python scripts/validate_report.py --report [path]. It also uses a report template at ./templates/report_template.md and a McKinsey-style HTML template at ./templates/mckinsey_report_template.html and a generation process that saves outputs to a designated folder structure under ~/Documents/[TopicName]_Research_[YYYYMMDD]/.
Caveats
The workflow enforces explicit source-backed claims with citations in every factual statement. It operates with a constrained output token limit (approximately 32,000 tokens per skill execution) and recommends progressive file assembly for ultra-long reports. If any verification checks fail (citation validation or structure/quality checks), sections are regenerated and may require user intervention after repeated failures.
# Deep Research <!-- STATIC CONTEXT BLOCK START - Optimized for prompt caching --> <!-- All static instructions, methodology, and templates below this line --> <!-- Dynamic content (user queries, results) added after this block --> ## Core System Instructions **Purpose:** Deliver citation-backed, verified research reports through 8-phase pipeline (Scope → Plan → Retrieve → Triangulate → Synthesize → Critique → Refine → Package) with source credibility scoring and progressive context management. **Context Strategy:** This skill uses 2025 context engineering best practices: - Static instructions cached (this section) - Progressive disclosure (load references only when needed) - Avoid "loss in the middle" (critical info at start/end, not buried) - Explicit section markers for context navigation --- ## Decision Tree (Execute First) ``` Request Analysis ├─ Simple lookup? → STOP: Use WebSearch, not this skill ├─ Debugging? → STOP: Use standard tools, not this skill └─ Complex analysis needed? → CONTINUE Mode Selection ├─ Initial exploration? → quick (3 phases, 2-5 min) ├─ Standard research? → standard (6 phases, 5-10 min) [DEFAULT] ├─ Critical decision? → deep (8 phases, 10-20 min) └─ Co
- Core System Instructions
- Decision Tree (Execute First)
- Workflow (Clarify → Plan → Act → Verify → Report)
- 1. Clarify (Rarely Needed - Prefer Autonomy)
- 2. Plan
- 3. Act (Phase Execution)
- 4. Verify (Always Execute)
- 5. Report
- Output Contract
- Error Handling & Stop Rules
- Quality Standards (Always Enforce)
- Inputs & Assumptions
- When to Use / NOT Use
- Scripts (Offline, Python stdlib only)
python scripts/verify_citations.py --report [path] python scripts/validate_report.py --report [path] Extract topic slug from research question Create folder: ~/Documents/[TopicName]_Research_[YYYYMMDD]/ mkdir -p ~/Documents/[folder_name] Create initial markdown file with frontmatter File path: [folder]/research_report_[YYYYMMDD]_[slug].md cd ~/.claude/skills/deep-research python scripts/md_to_html.py [markdown_report_path] python scripts/verify_html.py --html [html_path] --md [md_path]
What does the deep-research skill do?
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, verified claims, or comparison of approaches. Triggers include "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". Do NOT use for simple lookups, debugging, or questions answerable with 1-2 searches.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill deep-research-maxmiksa-auto-company --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.