An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
238 agents across 675 plugins.
[Subagent] 记忆装载器。 扫描历史写作复盘(99_episode.md),提炼跨项目的稳定写作偏好规则, 生成当前项目的 00_memory_packet.md 供下游 Agent 读取。 由工作流导演调度;具体阶段顺序以工作流 JSON 为准,本代理不自行定义顺序。
Use this agent when you need to ensure voice consistency, calibrate tone, or match a specific writing style in content. This agent guards the voice profile and…
Optimizes content for search engine visibility and AI engine discoverability with keyword placement, meta content, and structured data.
Adds natural voice, storytelling elements, and human authenticity to content, reducing AI-sounding patterns.
Reviews content against quality standards, brief requirements, and brand guidelines before final output.
Peer Reviewer 2; assesses domain expertise, substantive accuracy, and field-specific adequacy
Writes the full paper draft section by section from the structured outline and Paper Configuration Record
Q1 journal editorial review; delivers Accept/Reject verdict with actionable feedback on research reports
Quality curator for the Claude Blog Brain. Maintains and answers from the Quality theme of the brain, grounded in the vault and its dated sources. Advisory and…
Research specialist for blog content. Finds current statistics (2025-2026), verifies sources against tier 1-3 quality standards, discovers…
Quality assessment specialist for blog posts. Runs the full 5-category, 100-point scoring system, identifies issues by severity, checks for AI editorial style…
Mathematical derivation agent using OpenAI's flagship reasoning model (o3). Derives formulas, performs symbolic calculations, verifies analytical results. Has…
Sidecar research monitor. Runs as its own short-lived process next to a live (or paused) `luxas run`, driven from the studio's bottom chat panel. Answers…
Pre-finish prior-art positioning for the report's contribution claims. Receives ONLY the contribution sentences (not brain's framing, not the ledger),…
[Optional Subagent] 发布后表现复盘器。 只在用户明确要求“复盘上一篇数据”等场景运行;读取 append-only 指标账本, 区分观察、假设和跨样本验证规则,不把单篇流量归因成稳定写作规律。
Handles final content formatting, delivery to output channels, and tracking sheet updates.
Orchestrates multi-content production as a sequential, checkpointed queue of full ContentForge pipeline runs.
Extracts key points from content and adapts for social media platforms.
Synthesizes all reviewer reports into a unified editorial decision letter and revision roadmap
Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is…
Research ethics self-check (before a human committee/IRB, not a replacement); confirms Critical integrity concerns before delivery — stops the user once,…
Schema curator for the Claude Blog Brain. Maintains and answers from the Schema theme of the brain, grounded in the vault and its dated sources. Advisory and…
SEO optimization specialist for blog posts. Validates on-page SEO elements post-writing: title tag, meta description, heading hierarchy, internal/external…
Strategy curator for the Claude Blog Brain. Maintains and answers from the Strategy theme of the brain, grounded in the vault and its dated sources. Advisory…
Read ONE paper (PDF or LaTeX source) and produce two per-paper fragments: methodology coverage → notes/methodology.d/<paper_id>.md (A/B/C/D buckets, for PI…
Blind estimator / replicator for ONE declared quantity (claims-first design §3.5–§3.6). Receives the quantity's observable sentence and the input VALUES the…
Fresh-context prose writer for report.tex. Exists because the report-synthesis turn is the mirror image of the ledger_writer turn (interpretation-fidelity…
Expert software architect specializing in system design, domain-driven design, architectural patterns, and technical decision-making for scalable, maintainable…
Expert software architect specializing in system design, domain-driven design, architectural patterns, and technical decision-making for scalable, maintainable…
论证假说专家。在核心主题确定后,选择合适的论证模式并提出可被研究推翻的假说。由工作流导演在 Stage 1.5 显式调用。
Translates content while preserving brand voice, citations, and SEO across languages.
Identifies the papers field and dynamically configures the reviewer teams identities and expertise
Formats the final manuscript output to target journal style requirements
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic