Research

Evaluates scientific research rigor using systematic frameworks. Assesses methodology, statistics, biases, and evidence quality. Use when reviewing papers, critiquing claims, designing studies, rating evidence strength (GRADE/Cochrane ROB), checking study design, statistical critique, or risk of bias assessment.

Workflow for acquiring historical Ethereum blockchain data using Google BigQuery free tier. Empirically validated for cost estimation, streaming downloads, and DuckDB integration. Use when planning bulk historical data acquisition or comparing data source options for blockchain network metrics.

Generate formatted bibliography and citations in various academic styles.

Query the Sequence Read Archive (SRA), retrieve scientific publications, and analyze genomics metadata using the SRAgent toolkit. Supports accession conversion (GSE→SRX→SRR), BigQuery metadata queries, manuscript downloads from multiple sources, and scRNA-seq technology identification. Use when working with SRA/GEO datasets, finding publications, or analyzing single-cell sequencing experiments.

Analyze user/customer feedback and produce a User Feedback Analysis Pack (source inventory, normalized feedback table, taxonomy/codebook, themes + evidence, recommendations, and feedback loop). Use for voice of customer, feature request analysis, support ticket synthesis, churn reason synthesis, and survey open-ends.

Root cause analysis with 5 Whys methodology. Triggers: root cause, 5 Whys, なぜなぜ分析, 根本原因, 原因分析, symptom fix, 対症療法.

Expert methodology for analyzing and summarizing research papers, extracting key contributions, methodological details, and contextualizing findings. Use when reading papers from PDFs, DOIs, or URLs to create structured summaries for researchers.

需求分析阶段详细规则；进入需求分析时读取；包含需求评分、追问逻辑、代码分析步骤

Interpret GA4, GSC, and SE Ranking data for content optimization. Provides benchmarks, status indicators, and actionable insights.

Investigate codebase, debug issues, or analyze patterns

Research and analyze competitors with STRUCTURED output: feature comparison matrix, strengths/weaknesses analysis, and actionable recommendations. UNIQUE VALUE: Creates standardized competitor analysis document with feature matrix and strategic recommendations. Use this skill when: - User asks "what do competitors do?", "who are our competitors?" - User mentions competitor names or asks for product comparison - User asks for "competitor analysis", "market research", "competitive landscape" ...

'balancing accuracy with token efficiency. Use when: source, cite, reference,

Expert market researcher specializing in market analysis, consumer insights, and competitive intelligence. Masters market sizing, segmentation, and trend analysis with focus on identifying opportunities and informing strategic business decisions.

Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvement. One agent at a time, with due care.

Writing self-loop for surveys: run the strict section-quality gate, then rewrite only the failing `sections/*.md` files until the report is PASS.

Define evidence-first table schemas for a survey: what each table must answer, row unit, columns, and which evidence-pack fields are required to fill it.

Use when `evidence-review` has completed extraction and needs a bounded narrative synthesis.

Draft non-prose visuals artifacts (timeline, figure specs) for a survey, grounded in evidence and using citation keys from `citations/ref.bib`.

Write survey prose into per-section files under `sections/` so each unit can be QA'd independently before merging.

Use when a `research-brief` workspace has a small paper set plus outline and needs a compact reader-facing briefing instead of a full survey.

Deterministically merge the final fingerprinted section snapshot into `output/DRAFT.md`, preserving outline order and inserting transitions only when explicitly enabled.

Normalize cross-skill JSONL interfaces (ids + titles + citation key formats) so downstream skills do not rely on best-effort joins.

Use when `paper-review` has claims plus evidence gaps and needs the final referee-style report.

Remove repeated boilerplate across sections (methodology disclaimers, generic transitions, repeated summaries) while preserving citations and meaning.