Skills de Claude Code · página 34

当用户明确要求"更新项目指南""同步指南""沉淀洞见到指南"时使用。将对话中新产生的可复用写作洞见实时沉淀到项目指南文件，保持术语口径一致、结构稳定、可检验与可复现。调用时必须指定指南文件路径。

当用户明确要求“LaTeX 模板优化”“样式参数对齐”“像素级比对”“make-latex-model”或旧写法“make_latex_model”，或要把 ChineseResearchLaTeX 里的某个项目做成高质量模板时使用。适配 NSFC / paper / thesis / cv 四条产品线；先依据 packages/ 与 projects/ 的真实分层判断改项目层还是公共包，再用各产品线官方构建入口验收。若必须修改 packages 下公共包，需先生成受影响模板回归计划并完成相关回归；NSFC 专项工具仅在明确属于 NSFC 参数对齐场景时按需使用。

当用户明确要求"写/润色 NSFC 标书摘要""生成中文摘要和英文摘要""把中文摘要翻译成英文摘要"时使用。输出中文、英文两个版本（英文必须是中文的忠实翻译版），同时输出标题建议（1个推荐标题+5个候选标题及理由）。中文摘要默认≤400字符，英文摘要默认≤4000字符。输出方式：将结果写入工作目录下的 `NSFC-ABSTRACTS.md`。⚠️ 不适用：用户只想翻译一段与标书无关的通用文本（应直接翻译）；用户只想写立项依据/研究内容/研究基础正文（应使用对应 nsfc 系列 skill）。

当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料，输出一份可提交的预算说明书 LaTeX 项目并渲染 `budget.pdf`。若用户未指定工作目录，必须暂停并先要求其指定。⚠️ 不适用：用户只是想了解预算原则；用户仅要预算表数字而不写说明书；或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。

根据 NSFC 标书正文内容，结合申请代码推荐库，为你给出 5 组申请代码1/2（主/次）推荐与理由；输出到 NSFC-CODE-vYYYYMMDDHHmm.md（只读，不修改标书）

去除 NSFC 标书中的 AI 机器味，使文本读起来像资深领域专家亲笔撰写（不适用：非标书内容/需修改格式/需补充新内容）

当用户明确要求"写/改 NSFC 立项依据""立项依据写作/重构"时使用。基于最小信息表输出价值与必要性、现状不足、科学问题/假说与项目切入点，并保持模板结构不被破坏。适用于 NSFC 及各类科研基金申请书的立项依据写作场景。

基于国自然标书篇幅预算标准；检查目标标书篇幅并总结差距；给出针对性优化建议；在尽量不改变原意的前提下扩写/压缩到达标。

当用户明确要求"标书QC/质量控制/润色前质检/引用真伪核查/篇幅与结构检查"时使用。对 NSFC 标书进行只读质量控制：并行多线程独立检查文风生硬、引用假引/错引风险、篇幅与章节分布、逻辑清晰度等，最终输出标准化 QC 报告；中间文件默认归档到“交付目录内的隐藏工作区（.nsfc-qc/）”，并兼容 legacy `.nsfc-qc/`。

检查 NSFC 标书正文引用与参考文献的一致性与真实性风险（只读）：核查 bibkey 是否存在、BibTeX 字段与 DOI 等格式问题，并生成结构化输入供宿主 AI 逐条评估“正文表述是否真的在引用该文献”；默认仅输出审核报告，不直接修改标书或 .bib（除非用户明确要求）。

当用户明确要求"写/改研究内容""研究内容+创新+年度计划编排"时使用。为 NSFC 正文"（二）研究内容"写作/重构，并同步编排"特色与创新"和"三年年度研究计划"，输出可直接落到 LaTeX 模板的三个 extraTex 文件。

当用户明确要求"写/改研究基础""研究基础+工作条件+风险应对编排"时使用。为 NSFC 正文"（三）研究基础"写作/重构，并同步编排"工作条件"和"研究风险应对"，用证据链证明项目可行、资源条件对位研究内容、风险预案可执行。

当用户明确要求"评审国自然标书"、"模拟专家评审"、"审阅 NSFC 申请书"时使用。模拟领域专家视角对 NSFC 标书进行多维度评审，输出分级问题与可执行修改建议。⚠️ 不适用：用户只是想写/改标书某个章节（应使用 nsfc-*-writer 系列技能）、只是想了解评审标准（应直接回答）、没有明确"评审/审阅"意图。

当用户明确要求"生成 NSFC 技术路线图/技术路线图绘制/roadmap/flowchart"或需要把标书研究内容转成"可打印、A4 可读"的技术路线图时使用。默认输出可编辑源文件（`.drawio`）与可嵌入文档的渲染结果（`.svg`/`.png`/`.pdf`）；当用户主动提及 Nano Banana 图片模型时，可切换为 PNG-only 模式，并兼容 Gemini 与 OpenAI `gpt-image-2`。⚠️ 不适用：用户只是想修改某张已有图片的格式/尺寸（应使用图片处理技能）、只是想润色技术路线文字描述（应直接改写正文）。

当用户明确要求"生成 NSFC 原理图/机制图/schematic diagram/mechanism diagram"或需要把标书中的研究机制、算法架构、模块关系转成"可编辑 + 可嵌入文档"的图示时使用。默认输出可编辑源文件（`.drawio`）与渲染文件（`.pdf`/`.svg`/`.png`）；当用户主动提及 Nano Banana 图片模型时，可切换为 PNG-only 模式，并兼容 Gemini 与 OpenAI `gpt-image-2`。⚠️ 不适用：用户只是想润色正文文本（应直接改写文本）、只是想改已有图片格式/尺寸（应使用图片处理技能）、没有明确"原理图/机制图"意图。

解读论文 Figure 的含义并输出一份“教会人类如何读图”的高可读性 Markdown 报告；支持输入 1 个或多个 figure 文件绝对路径与人工解读，自动尝试从图附近检索生成该图的源代码，并采用类似 parallel-vibe 的方式通过 `codex exec`/`claude -p` 以进程级隔离解读每张图（并发上限默认 3，可在 config.yaml 调整）。⚠️ 不适用：用户只是想改图尺寸/裁剪/改格式；或要求直接修改图片/源代码（本 skill 对图片与源代码全程只读，严禁修改）。

当用户明确要求“推荐投稿期刊”“帮我的论文选 SCI 杂志”“这篇 manuscript 适合投哪些 journal”“期刊匹配/选刊/投稿建议”时必须使用。适用于用户提供全文、摘要、Markdown、LaTeX、PDF、Word 或混合材料的场景；本 skill 会基于 manuscript 与用户偏好，先用内置 `2023IF.xlsx` 做最小硬过滤生成候选池，再由宿主模型自主规划 Set1/Set2/Set3，并联网核验 scope / 质量 / 近 3 个月 PubMed 论文，最后输出 1 份按推荐度排序的 Markdown 选刊报告。⚠️ 不适用：用户只是想润色论文、只想翻译摘要、或只问某个单一期刊的官网信息而不需要系统选刊。

根据 LaTeX 论文项目撰写、修订和润色 SCI 期刊论文，默认 AI 自主模式，也支持人机协作仅输出审查计划；提供作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环。⚠️ 不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务。

当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词，多源检索→去重→AI 逐篇阅读并评分（1–10分语义相关性与子主题分组）→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作（固定摘要/引言/子主题/讨论/展望/结论），保留正文字数与参考文献数硬校验，强制导出 PDF 与 Word。支持多语言翻译与智能编译（en/zh/ja/de/fr/es）。

当用户明确要求“迁移 LaTeX 模板”“把旧项目接入 ChineseResearchLaTeX”“把旧标书/论文/毕业论文/简历套进当前模板”“把 Word/PDF/Markdown/零散 tex 整理进现有项目”，或直接提到 `transfer-old-latex-to-new` 时使用。旧别名 `migrating-latex-templates` 可兼容理解。该 skill 只负责把正文内容迁移到当前仓库现有模板的内容层；绝不能修改 `packages/` 内公共包源码、也绝不能修改 `projects/` 内模板样式或入口骨架，只能写入目标项目允许承载正文的内容文件。

Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.

Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.

Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.

Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.

Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.

Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.

Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.

Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.

Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.

Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".

Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.

Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.

Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, and strips defensive code. Use when cleaning up code, simplifying, removing boilerplate, or before committing.

Configure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to set up reactive workflows.

Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics. Computes stats from project memory and session history. Use when asking for stats, statistics, progress, how am I doing, coding history, or dashboard.

Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".

Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provider config from env (OPENAI/ANTHROPIC/FIREWORKS/OPENROUTER/custom OpenAI-compatible base URL). Persists transcript to a wiki page when --wiki <slug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the "LLM Council" approach for high-stakes reviews, plan critique, or contested learning rules.

LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.

Produce a one-screen map of an unfamiliar area of the codebase: entry points, modules, data flow, callers. Designed to be read in fifteen seconds. Use when the user says "I do not know this area", "give me the map", "zoom out", "orient me".

Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.

Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.

Stress-test a plan by walking its decision tree one question at a time. Use when the user wants to pressure-test a design before implementation.

Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.

Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about".

Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work. Use when ending a session, saying "continue later", "save progress", "session summary", or "pick up where I left off".

SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.

Run quality gates, review staged changes for issues, and create a well-crafted conventional commit. Use when saying "commit", "git commit", "save my changes", or ready to commit after making changes.

Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in `<wiki>/derived/surveys/<slug>.md` with full bibliography rows in `sources.md`. Provider-agnostic (Anthropic/OpenAI/OpenRouter/Fireworks/custom OpenAI-compat). Use when the user asks for a "survey", "literature review", "lit review", or "deep dive" on a technical topic.

Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.

Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.

Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base. Each wiki is a folder of markdown pages with provenance, plus a shadow FTS5 index so any session can recall it. Use when the user says "start a wiki", "add to wiki", "compile a page", "wiki on X", or wants a long-lived knowledge base on a topic, paper, product, person, project, or codebase.

Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis already covers, when the user says "what does the wiki say about X", "ask wiki", "search wikis", or before drafting a new wiki page (to avoid duplication).

Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from the queue, fetches sources, drafts a wiki page, dedupes claims against existing pages, enqueues follow-up seeds. Halts on budget cap, depth cap, or convergence. Use when the user says "research <topic>", "grow the <slug> wiki", "auto-research", or wants a knowledge base that builds itself overnight.

Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's "Unreasonable Effectiveness of HTML" — favors information density and shareability over markdown-only outputs.

End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.

Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".

Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".

Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".

Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".

Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".

Use when a task asks why code is built a certain way, proposes architectural changes, compares implementation approaches, or mentions decision markers such as WHY, DECISION, TRADEOFF, or ADR in a Repowise-indexed repository.

>

>

Use when exploring, understanding, or answering questions about a Repowise-indexed codebase, including architecture, where code is implemented, how a module works, or which files are relevant before reading source.

Use when the user asks about unused code, cleanup, deleting files or exports, refactoring old areas, reducing bundle size, code hygiene, technical debt, or maintenance in a Repowise-indexed repository.

Use before modifying, refactoring, moving, or deleting files in a Repowise-indexed repository, especially shared utilities, core modules, public APIs, or files the user did not explicitly identify.

Vibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, plans XL-first execution, and enforces verification and phase cleanup.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

|

Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market news/sentiment, insider transactions, GDP, CPI, treasury yields, gold/silver/oil prices, Bitcoin/crypto prices, forex exchange rates, or calculating technical indicators (SMA, EMA, MACD, RSI, Bollinger Bands). Requires a free API key from alphavantage.co.

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.

Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.

Full-stack software development agent for design, implementation, testing, and deployment. Use when the user explicitly asks for end-to-end project creation, feature development, bug fixing, or code refactoring.

Unified biological database evidence owner. Use for gene annotation, variant clinical significance, cancer mutation evidence, GWAS trait associations, pathway mapping, target-disease evidence, protein structures, protein interaction networks, reference single-cell census queries, and cross-database biological ID mapping. Do not use for full single-cell analysis, bulk RNA-seq differential expression, BAM/VCF processing, protein embedding models, metabolic flux modeling, genomic interval ML, or flow-cytometry file parsing.

Primary retained Python toolkit for molecular biology sequence work. Preferred for sequence manipulation, FASTA/FASTQ/GenBank parsing, Bio.Entrez, BLAST workflows, alignments, structures, and phylogenetics. For biological database evidence lookup, use bio-database-evidence. For single-cell workflows use scanpy. For direct literature REST API, use pubmed-database.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Codex-compatible cancel command for Ralph loop state, preserving the original command name.

Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.

Comprehensive citation management for academic research. Resolve bibliographic identifiers, extract accurate metadata, validate citations, deduplicate references, and generate properly formatted BibTeX entries. This skill should be used when you need to verify citation information, convert DOIs/PMIDs/arXiv IDs to BibTeX, or ensure reference accuracy in scientific writing.

Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.

Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.

Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.

Default code-quality route for broad code review, PR review, maintainability, correctness, and regression-risk checks. Do not use as the primary route for dedicated OWASP/security audits, review-feedback handling, completion verification, AI-code cleanup, or TDD/test-first work.

Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.

Git提交与调试反思报告生成技能。用于分析开发过程中的错误、调试步骤和解决方案,生成结构化的中文反思报告,并创建包含报告引用的Git提交。显式请求词:反思提交、智能提交、生成调试报告、commit with reflection。

Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

Discover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixing bugs, or refactoring code.

Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.

|

Master discrete mathematics, logic, formal proofs, and computational thinking. Build the mathematical foundation for all computer science.

Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.