fixer
Lightweight LaTeX compile-error fixer. Uses haiku for fast, mechanical error diagnosis and single-edit fixes. The brain should delegate to this agent when…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
238 agents across 675 plugins.
Lightweight LaTeX compile-error fixer. Uses haiku for fast, mechanical error diagnosis and single-edit fixes. The brain should delegate to this agent when…
Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — covering topology selection, context management,…
Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — covering topology selection, context management,…
[Subagent] 在表达修订与可选配图之后核查全文、最终标题和分发文案;用输入快照和结构化清单拦截无来源、矛盾及版本变化,再由脚本计算交付结论。
`quality-gatekeeper-agent` 是 PaperFit 的最终门禁。它不负责修复,也不负责发现新问题;它负责判断当前结果是否真的可以对外宣称“完成”。
你是 **Rule Engine Agent**(规则引擎),是 PaperFit 系统中专门负责 **解析编译日志、识别确定性错误与警告** 的智能体。你的核心职责是:
`semantic-polish-agent` 只负责受控语义修改,而且只能在排版手段已经用尽后出场。它不是常规修复主路径,而是最后阶段的受限补充能力。
Entry point for the 9 slash commands + agent routing + publish gate + ADAPT escalation counter + log operation + invoking the deterministic tools…
Owner of L2-1 source · L2-2 stub authoring and broad external exploration. raw input (.md/PDF) → auto-generates an atomic source page + entity/concept stubs,…
Use this agent when you need to optimize content for SEO, adapt it for social media, or format it for newsletters. This agent consolidates publishing…
Use this agent when you need to research sources, analyze audiences, or study competitor content for writing projects. This agent consolidates research,…
Use this agent when you need to create outlines, analyze content flow, or generate hooks for written content. This agent consolidates outlining, flow analysis,…
Identifies visual opportunities in content, generates data charts from verified research, optionally generates AI images (feature images, contextual…
Universal draft-vs-research hallucination and citation-integrity audit — runs on ALL content types, not just scientific or technical pieces. Diffs every…
Optimizes content structure for readability and engagement, and catches grammar, spelling, and formatting errors.
Senior research advisor for project-level strategic decisions. Handles the harder questions: Should I keep going? Am I working on the right thing? What am I…
정책연구과제의 착수 단계를 책임지는 연구설계 전문가. 본격 조사·집필 전에 (1) 연구 의도·범위·숨은 요구를 분석해 모호성을 걷어내고 사용자에게 되물을 질문을 만들고, (2) 핵심 연구질문(RQ)·분석틀·보고서 목차·연구방법을 설계한다. READ-ONLY 자문가로, 잘못된 방향으로…
정책연구보고서의 근거를 마련하는 리서치 전문가. 설계자의 조사 우선순위에 따라 문헌·선행연구, 정부 통계·지표, 국내외 정책사례, 법·제도·정책 배경을 외부 웹과 사용자 제공 자료에서 조사하고 모든 사실에 출처를 병기한다. 정책연구의 '현황'과 '대안'을 떠받치는 검증 가능한 팩트를…
You are a specialized **Web Asset Producer** agent with deep expertise in generating production-ready visual assets for web development projects. Your role is…
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page…
Sub-agent that performs exhaustive multi-source academic search (paper-search MCP across 22 platforms + optional NotebookLM + optional WebSearch). Returns…
Sub-agent that decides what to do with incomplete textbook references in the registry. Takes a JSON list of candidates (refs with year=0000 or title=empty,…
Runs PRISMA-trAIce + RAISE compliance checks at Stage 2.5 / 4.5 integrity gates and emits Schema 12 compliance_report
Challenges assumptions, tests logical chains, and stress-tests research arguments at mandatory checkpoints
Challenges core arguments and logical coherence as the devils advocate reviewer in the editorial panel
신규 분류 체계 v2.0과 metrics·playbook 패치를 quick-rules.md(monolith 전용 슬림 룰북, 126줄 → ≤180줄)에 안착하고 monolith 도구 호출 3회 캡(v1.6.1) 회귀를 검증한 뒤, GitHub PR 초안과 CHANGELOG를 작성하는…
Humanize KR 본진 v1.6 분류 체계(10대 카테고리·61+ 패턴)와 외부 학술 보고서 후보 풀(translationese-research-distiller 산출물)을 3-축 매트릭스(이미 본진·보강·신규)로 매핑해 분류학자에게 승격 결정 입력을 제공하는 갭 분석가. 사실…
한국어 번역투(translationese) 학술 보고서를 8유형·15항목 PE 체크리스트·post-editese 3축·학술 인용 계보·예문 코퍼스로 분해해 후속 분류·승격 단계가 직접 소비할 수 있는 구조화 JSON으로 증류하는 도메인 추출가. 보고서 본문에 명시된 사실만 추출하고…
Monitoring curator for the Claude Blog Brain. Maintains and answers from the Monitoring theme of the brain, grounded in the vault and its dated sources.…
Multilingual curator for the Claude Blog Brain. Maintains and answers from the Multilingual theme of the brain, grounded in the vault and its dated sources.…
Voice and Style curator for the Claude Blog Brain. Maintains and answers from the Voice and Style theme of the brain, grounded in the vault and its dated…
Visual designer with ZERO domain expertise. Two task patterns, inferred from the task text: (a) audit existing figures for style consistency + render bugs only…
Makes ONE figure from ONE brief. Data figures are figspec JSON (rendered by `figspec`), energy-level diagrams are levelspec JSON (rendered by `levelspec`),…
Single-pass writer that turns an experiment's computed facts (results.json + acceptance criterion + limitations) into the L2 section of notes/experiments.md.…
Specialist in crafting, testing, and systematically optimizing prompts for LLMs — turning vague instructions into reliable, production-grade AI behaviors.
Specialist in crafting, testing, and systematically optimizing prompts for LLMs — turning vague instructions into reliable, production-grade AI behaviors.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic