intake_agent
Conducts the paper configuration interview and produces the Paper Configuration Record for downstream agents
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
238 agents across 675 plugins.
Conducts the paper configuration interview and produces the Paper Configuration Record for downstream agents
Specialized translation and localization agent for blog content. Produces native-quality translations of an entire blog post, optimized for both human readers…
Content generation specialist for blog posts. Writes optimized articles with answer-first formatting, proper heading hierarchy, sourced statistics, and natural…
Writing curator for the Claude Blog Brain. Maintains and answers from the Writing theme of the brain, grounded in the vault and its dated sources. Advisory and…
Principal Investigator (PI) — adversarial quality reviewer that evaluates research progress like a senior professor at a group meeting. Reads project state,…
Dedicated literature-intake agent. Broadly searches academic databases, web, and citation chains; downloads priority papers; spawns readers that write…
Pure implementation sub-agent. Given a tool description (name, purpose, input/output signature, algorithmic logic), writes a working Python module to…
Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch…
Workflow design specialist who maps complete workflow trees for every system, user journey, and agent interaction — covering happy paths, all branch…
选题生成器。当用户没有写作灵感时,从热点、个人资产、竞品分析三个维度生成候选选题。由工作流导演在 Stage 0a 显式调用。
Runs coverage-bounded checks on registered references, citation contexts, data surfaces, and claims before review and after revision
Designs the literature search strategy and manages source selection for the paper
Quantitative synthesis of included studies; computes effect sizes, assesses heterogeneity, and applies GRADE framework
The owner's dedicated Claude Blog agent, grounded in the Claude Blog Brain at <brain-root>. Use for any blog-content work - writing and rewriting for Google…
This matrix maps the claude-blog workflow surface to owned curator agents. It is advisory until the audit gate passes. It is also the curator coverage…
Independent test-author sub-agent. Given a tool description, writes a pytest test file that verifies the description's constraints. Works blind to the impl —…
Document-level layout auditor for the compiled report.pdf. Rasterizes every page via pdftoppm, reads each page image, audits page-level typography and layout…
Lightweight agent for independent tasks — reading papers, extracting data, downloading files, or any batch of independent work. Returns findings concisely.
多平台读者压力测试器(保留 wechat-reader-test 名称以兼容既有工作流)。 从 01_theme.md 读取发布平台,为公众号、今日头条、知乎选择不同的定性测试矩阵; 不伪造 CTR、完读率或推荐量预测。由工作流导演在 Stage 9 显式调用。
写作需求澄清专家。澄清核心写作要素,包括主题、读者画像、风格选择、字数要求等。由工作流导演在 Stage 1 显式调用。
Peer Reviewer 1; assesses methodological soundness, research design validity, and statistical rigor
Post-research literature monitoring; helps users track new publications and developments after a research project is complete
Simulates peer review to identify weaknesses and suggest improvements before submission
Peer Reviewer 3; evaluates cross-disciplinary relevance, broader impact, and alternative interpretations
Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases
Transforms research findings into polished APA 7.0 academic reports; activated in Phase 4 and Phase 6
Designs the methodological blueprint; selects research paradigm, method, data strategy, and analytical framework
Transforms vague topics into precise, FINER-evaluated researchable questions through iterative refinement
Parses reviewer or real-committee comments into source-accounted plans and response skeletons
Assesses risk of bias in included studies using RoB 2 (RCTs) and ROBINS-I (non-randomized studies)
Guides paper authors through Socratic questions to sharpen arguments and surface unstated assumptions
Grades evidence, detects predatory publications, and fact-checks claims entering the research pipeline
Tracks pipeline state and maintains the research session history across multi-phase workflows
Designs the papers section architecture and detailed outline before drafting begins
Integrates findings across sources, resolves evidence conflicts, and maps knowledge gaps
Extracts per-source temporal facts and citation provenance into Phase 2 sidecar artifacts; activated in Phase 2 (Investigation)
Generates publication-quality figure specifications and chart descriptions for inclusion in the paper
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic