Research

Automated generation of journal article drafts from HTA systematic review reports. Use when users want to (1) convert an HTA/systematic review report into a journal submission, (2) extract clinical and cost-effectiveness data from HTA reports, (3) generate first drafts following specific journal guidelines, or (4) process NICE, ICER, CADTH, or similar HTA agency reports for publication. Triggers include phrases like "convert this report to a journal article", "draft a manuscript from this systematic review", "prepare for journal submission", "extract data for publication", "ingest HTA report", "start drafting".

Architecture rules and validation patterns for Claude Code marketplace components ensuring self-contained skills, proper skill usage, and clean reference patterns

Establish or analyze brand identity guidelines. Creates comprehensive brand documentation that frontend-design, testing, and other skills automatically reference for consistent execution.

Comprehensive documentation suite for generating READMEs, API references, and internal guides based on code analysis.

Overlay images, videos, and animated GIFs on maps using MediaLayer. Use for historical imagery, plan overlays, and georeferenced media content.

Use when exploring unknown technology, assessing feasibility, or before Complex (C) tier work - time-boxed technical research with structured output

Manage Google Tasks and task lists. Load when user mentions 'google tasks', 'tasks', 'todo list', 'create task', 'complete task', or references task/todo management.

Stress-test book concepts against existing research before committing to architecture. Use when the user has a Book Concept Document ready for validation, wants to verify their thesis is defensible, needs to understand the competitive intellectual landscape, or wants honest assessment of their idea's strengths and weaknesses. Produces a Validation Report that informs the Go/No-Go decision. Nonfiction only.

Deep competitive keyword research and SEO strategy. Takes a primary keyword and researches supporting keywords, competitor analysis, search intent, and per-page keyword mapping. Outputs docs/seo-analysis.md. Triggers on "keyword research", "SEO research", "SEO strategy", "competitive analysis", "rank for keyword".

Build searchable knowledge bases from document collections (PDFs, Word, text files). Use for creating technical libraries, standards repositories, research databases, or any large document collection requiring full-text search.

Research-backed prompting techniques for improved AI response quality

Create complete Claude Code agents for the Traycer enforcement framework. This skill should be used when creating new agents or updating existing agents. Creates all agent components including system prompt, hooks, skills, commands, scripts, and reference docs. Also updates coordination documents that list available agents. Based on Anthropic's official agent development best practices.

Design the structural and emotional architecture for nonfiction books. Use when an author has a validated book concept and needs to create the blueprint before drafting. Triggers include requests to structure a book, create a chapter outline, design a table of contents, map the reader's journey, or plan book organization. Requires upstream documents from book-ideation (Book Concept Document) and optionally from idea-validator (Validation Report) and market-research (Market Research Report).

Context and reference for building UI with shadcn-vue components. Load when adding, modifying, or debugging UI components.

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

Do experiment-driven research (hypotheses → minimal repros → evidence) and continuously improve research skills + tooling. Use when behavior is uncertain, contested, or performance-sensitive.

PROACTIVELY use when exploring unfamiliar codebases, analyzing remote repositories, generating reference skills from code, or needing AI-optimized context for code review. Triggers on "analyze repo", "explore codebase", "pack repository", "generate skill from", "understand this codebase", "code context".

Execute GraphQL queries against Sonar ISP API.Use when querying customer data, services, billing, invoices, payments, tickets, jobs, or network info from Sonar.Supports live mode via fetch_customer_live(). Reference: src/apis/sonar_client.py

Generates design token documentation with visual swatches and code examples. Use when documenting token values, creating token reference guides, or building searchable design system documentation.

Delegates research to Google Gemini. Use when user says "이거 좀 찾아봐", "Gemini한테 물어봐", "문서 검색해줘", "best practice 알려줘", "리서치해줘", "최신 정보 찾아줘", or needs web search, documentation lookup.