Skills 199-biotechnologies claude-deep-research-skill
deep-research
- Use it when:
- A question needs many sources weighed, such as a technology comparison, market analysis or state-of-the-art review, not a quick lookup.
- It does:
- Scopes and plans the question, searches in parallel with 3 to 5 subagents, triangulates sources, drafts section by section and verifies each claim.
- Modes:
- Quick (3 phases), standard (6, the default), deep (8) and ultradeep (8 or more), from a few minutes to about 45.
- You get:
- A folder in ~/Documents with the report as Markdown, McKinsey-style HTML and PDF, both opened for you, plus source, evidence and claim ledgers and a run manifest.
- Report:
- Executive summary, 4 to 8 cited findings, synthesis, limitations, recommendations, a complete bibliography and a methodology appendix.
- Needs:
- Subagents for parallel retrieval and WeasyPrint for the PDF; its makers' search-cli is optional, with the agent's web search as fallback.
Writes its report folder to ~/Documents and opens the HTML and PDF itself; it runs without asking questions unless something critical fails.
TL;DR
A research pipeline that works on its own: it infers assumptions from context and states the important ones in the report's introduction instead of asking. Simple lookups and debugging are sent elsewhere. Retrieval, outlining, drafting and claim checks run as a loop per section: each source gets a stable ID in sources.jsonl, each quote and its location is appended to evidence.jsonl, and each factual claim in claims.jsonl must be supported before delivery. It aims for 10 or more sources and 3 independent ones per major claim, cites every factual claim inline, writes at least 80% prose and allows no placeholders or invented citations. Deep and ultradeep modes add a critique and a refinement pass. Bundled Python scripts validate the report and its citations and convert Markdown to HTML. Reports over 18,000 words follow a continuation procedure.
Summarizes the skill at f2f2c0f.
npx skills add https://github.com/199-biotechnologies/claude-deep-research-skill --skill deep-research skills.sh pageSource on GitHubAll skills from 199-biotechnologies/claude-deep-research-skill
- Total Downloads
- 10,400 on skills.sh, Nov 9, 2026
- Repo stars
- 1,211 199-biotechnologies/claude-deep-research-skill
- First seen
- Jan 21, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 79 |
| Sep 28 | 72 |
| Oct 5 | 63 |
| Oct 12 | 77 |
| Oct 19 | 65 |
| Oct 26 | 67 |
| Nov 2 | 72 |
| Nov 9 | 94 |
| Category |
Articles, docs, internal comms, research write-ups and prose that doesn't read as generated. Drive browsers, scrape pages and search the web. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills. |
|---|---|
| Type |
A multi-step process the agent follows: interview, debug, run a TDD loop, review. |
| Effect |
Its own steps create or change files, git state or local tools. |
| Needs |
Relies on the agent being able to spawn subagents. A specific command-line tool or desktop app must be installed, such as gh, agent-browser, LibreOffice, Obsidian or a vendor CLI. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics |
SKILL.md
From 199-biotechnologies/claude-deep-research-skill at f2f2c0f. Checked daily, last changed Nov 6, 2026.
Frontmatter
name: deep-research
description: Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.Deep Research
Core Purpose
Deliver citation-tracked research reports through a structured pipeline with evidence persistence, source identity management, claim-level verification, and progressive context management.
Autonomy Principle: Operate independently. Infer assumptions from context. Only stop for critical errors or incomprehensible queries. Surface high-materiality assumptions explicitly in the Introduction and Methodology rather than silently defaulting.
Decision Tree
Request Analysis
+-- Simple lookup? --> STOP: Use WebSearch
+-- Debugging? --> STOP: Use standard tools
+-- 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)
+-- Comprehensive review --> ultradeep (8+ phases, 20-45 min)
Default assumptions: Technical query = technical audience. Comparison = balanced perspective. Trend = recent 1-2 years.
Workflow Overview
| Phase | Name | Quick | Std | Deep | Ultra |
|---|---|---|---|---|---|
| 1 | SCOPE | Y | Y | Y | Y |
| 2 | PLAN | - | Y | Y | Y |
| 3 | RETRIEVE | Y | Y | Y | Y |
| 4 | TRIANGULATE | - | Y | Y | Y |
| 4.5 | OUTLINE REFINEMENT | - | Y | Y | Y |
| 5 | SYNTHESIZE | - | Y | Y | Y |
| 6 | CRITIQUE | - | - | Y | Y |
| 7 | REFINE | - | - | Y | Y |
| 8 | PACKAGE | Y | Y | Y | Y |
Note: Phases 3-5 operate as an evidence loop per section (retrieve → evidence store → refine outline → draft → verify claims → delta-retrieve if needed), not as strict sequential gates.
Execution
On invocation, load relevant reference files:
- Phase 1-7: Load methodology.md for detailed phase instructions
- Phase 8 (Report): Load report-assembly.md for progressive generation
- HTML/PDF output: Load html-generation.md
- Quality checks: Load quality-gates.md
- Long reports (>18K words): Load continuation.md
Templates:
- Report structure: report_template.md
- HTML styling: mckinsey_report_template.html
Scripts:
python scripts/validate_report.py --report [path]python scripts/verify_citations.py --report [path]python scripts/md_to_html.py [markdown_path]
Output Contract
Required sections:
- Executive Summary (200-400 words)
- Introduction (scope, methodology, assumptions)
- Main Analysis (4-8 findings, 600-2,000 words each, cited)
- Synthesis & Insights (patterns, implications)
- Limitations & Caveats
- Recommendations
- Bibliography (COMPLETE - every citation, no placeholders)
- Methodology Appendix
Output files (all to ~/Documents/[Topic]_Research_[YYYYMMDD]/):
- Markdown (primary source of truth)
sources.jsonl— stable source registry with canonical IDsevidence.jsonl— append-only evidence store with quotes and locatorsclaims.jsonl— atomic claim ledger with support statusrun_manifest.json— query, mode, assumptions, provider config- HTML (McKinsey style, auto-opened)
- PDF (professional print, auto-opened)
Quality standards:
- 10+ sources, 3+ per major claim (cluster-independent, not just count)
- All factual claims cited immediately [N] with evidence backing in
evidence.jsonl - Claim-support verification mandatory: no unsupported factual claims pass delivery
- No placeholders, no fabricated citations
- Prose-first (>=80%), bullets sparingly
When to Use / NOT Use
Use: Comprehensive analysis, technology comparisons, state-of-the-art reviews, multi-perspective investigation, market analysis.
Do NOT use: Simple lookups, debugging, 1-2 search answers, quick time-sensitive queries.