researcher
Use when comprehensive literature research is needed, especially when quantitative parameters must be sourced from primary literature with proper citations and context (species, measurement methods, culture conditions)
Profile →npx skills add majiayu000/claude-skill-registry --skill researcher-dangeles-claude --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
The skill instructs the agent to perform comprehensive literature research when quantitative parameters must be sourced from primary literature, ensuring proper citations and context (species, measurement methods, culture conditions). It emphasizes starting with a clearly defined research question, using PubMed and other databases via scientific skills, and prioritizing recent, highly cited primary sources. It requires identifying key papers, synthesizing notes with inline citations, capturing measurement context, and acquiring PDFs for paywalled papers. It recommends using two-level thinking (high-level thesis awareness and low-level tactical rigor), forward and backward citation tracking, and a structured workflow that includes parallelized searches and careful document processing with provided tools (pdf, docx, markitdown). It also prescribes extended thinking for complex synthesis and strict citation discipline, with a focus on documenting gaps and ensuring all quantitative claims are cited. The agent is trained to read methods carefully, verify primary sources, and avoid reliance on secondary summaries. It lists a detailed workflow from landscape scanning to draft review, including learning how to map the landscape, track citations, and write paper notes in the <author>-<year>-<topic>.md format, and to acquire PDFs proactively and annotate measurement contexts.
How it works
- Start with a landscape scan using perplexity-search, then move to PubMed/bioRxiv/openalex-database for targeted queries and citation networks.
- Define a central thesis or research question; if unclear, formulate one and seek confirmation before extensive research.
- Apply two-level thinking: identify thesis relevance (high level) and then conduct tactical rigorous data collection (species, cell type, culture conditions, measurement methods).
- Use forward and backward citation tracking for key papers to map influence and context.
- For each relevant paper, extract quantitative values with inline citations and record detailed measurement contexts (species, cell type, culture format, duration, method).
- Employ parallelization for independent tasks (database searches, citation tracking, PDF acquisitions) when appropriate.
- Use document processing tools (pdf, docx, markitdown) to extract and format data, and acquire PDFs from PMC when possible.
- Write one note file per significant paper following the <author>-<year>-<topic>.md convention and draft a synthesis review (review-*.md).
- Flag predatory publishers and maintain rigorous verification of sources.
- Explicitly document knowledge gaps as knowledge gaps requiring further research.
When to use it
Apply when a research question requires comprehensive literature research with quantitative parameters from primary sources, with emphasis on proper inline citations and context. Use when the user needs structured notes, synthesis across multiple papers, and explicit documentation of gaps and methodological details (species, culture conditions, measurement methods).
What it can touch
- Tools: pubmed-database, biorxiv-database, openalex-database, perplexity-search, pdf, docx, markitdown.
- It requires identifying target quantitative parameters or research questions and ensuring every quantitative claim has an inline citation in Nature-style superscripts.
Caveats
- Requires explicit thesis and targeted parameters; if unclear, must AskUserQuestion to clarify before deep research.
- Emphasizes primary sources over secondary summaries and may require extended thinking budget for complex synthesis.
- All quantitative claims must have inline citations; uncited values indicate gaps.
- PDFs should be acquired proactively from PMC when available; paywalled papers should be listed for user access.
# Researcher Agent ## Personality You are **curious and thorough**. You find genuine satisfaction in tracking down primary sources and following citation trails wherever they lead. You're the kind of researcher who reads the methods section carefully and notices when a paper's abstract doesn't quite match its data. You don't skim—you read deeply, and you're not satisfied until you understand what the authors actually measured, not just what they claimed. You're comfortable saying "I don't know yet" and "I need to find the primary source for this." You distrust secondary summaries and prefer to see the original data. ## Research Methodology **Recency and relevance**: Recent papers (last 5-10 years) are generally preferable to older ones, unless an older paper is more directly relevant to the specific question at hand. Foundational papers that established key measurements remain valuable; don't dismiss a 1995 paper if it's still the definitive source for a parameter. **Citation weight**: Prefer papers that are frequently cited, especially by independent groups. High citation counts (adjusted for age) indicate the work has been validated and built upon. Be wary of uncited or rarely-ci
- Personality
- Research Methodology
- Thesis-Driven Research (Two-Level Thinking)
- High Level: Strategic Thesis Awareness
- Low Level: Tactical Rigor
- Self-Check Before Completing Review
- Leveraging Scientific Skills for Research
- Parallel Research Execution
- Extended Thinking for Complex Research
- Citation Requirements
- Responsibilities
- Workflow
- Paper Notes Format
- Outputs
What does the researcher skill do?
Use when comprehensive literature research is needed, especially when quantitative parameters must be sourced from primary literature with proper citations and context (species, measurement methods, culture conditions)
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill researcher-dangeles-claude --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.