Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.
Autonomous RLHF feedback capture - Claude self-captures mistakes and successes
読み取り専用で差分をレビューし、ルール違反・リスク・最小修正案を提示する
Expert developer in 24+ programming languages that generates production-ready code leveraging unique language features and idiomatic patterns.
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
Navigate and understand the innozverse repository structure, file organization, naming conventions, and module boundaries. Use when creating new files, organizing code, or understanding where to add features.
QA Tester Agent. 테스트 작성, 실행, 검증을 담당합니다. 테스트, 검증, 단위테스트, 통합테스트, E2E 관련 요청 시 사용됩니다.
[22] UNDERSTAND. Deep research from all sources — internal (code, git, logs) AND external (web, docs, best practices). Use when choosing libraries, investigating solutions, understanding legal/technical questions, comparing approaches, or anytime you need comprehensive knowledge from both project context and world knowledge. Triggers on "research", "investigate", "find best approach", "what do others do", "compare options", or complex questions requiring multiple sources.
Execute FireCrawl primary workflow: Core Workflow A. Use when implementing primary use case, building main features, or core integration tasks. Trigger with phrases like "firecrawl main workflow", "primary task with firecrawl".
Use when documenting Python research code usage, setup, and experiment reproduction.
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Pytest test development for Python microservices. Use when writing unit tests, integration tests, fixtures, mocking external services, or setting up test infrastructure. Triggers on requests to create tests, debug failing tests, test organization, factory fixtures, parametrization, or testcontainers.
Diagnose and fix CI/CD pipeline failures, test errors, GitHub Actions issues, and code scanning alerts. Use when: - CI pipeline fails (red build) - GitHub Actions workflow errors - Test failures in CI (Vitest, Playwright) - TypeScript/lint errors blocking builds - GitHub notifications about failed checks - "CI is red" or "build failed" or "tests failing" - Supabase/OpenAPI type generation failures - Pre-commit hook failures - GitHub Code Scanning alerts (CodeQL) - Security vulnerabilities in code - /security/code-scanning alerts Triggers: "fix ci", "ci failed", "build broken", "tests failing in ci", "github actions error", "pipeline red", "check failed", "code scanning", "codeql", "security alert", "vulnerability"
Vercel CLIのインストール・認証・設定を行う。「Vercel設定」「vercel設定」「Vercelセットアップ」を依頼されたときに使用する。
Creates Features following the T-Minus-15 process template. Features represent significant deliverables that contain multiple User Stories. Includes proper metadata, MoSCoW prioritization, effort estimates, deliverables, and benefit hypothesis.
當完成任務、實作主要功能或在合併前驗證工作符合需求時使用
Iteratively improve an existing skill or command based on feedback
Convert Notion pages or drafts into Hugo content for this repo, including front matter, shortcodes, glossary terms, and asset placement, and publish/preview with the Hugo CLI. Use when asked to import from Notion, format content to match FORMATTING.md, or create/update posts in content/.
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
**Status:** Completed