Skills de Claude Code · página 104

Use when the user asks for an AWS architecture diagram — VPC/networking, event-driven, landing zone, multi-AZ, serverless pipeline, or any diagram built with AWS service icons. Builds with the declarative layout engine using ground-truth mxgraph.aws4 stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.

Use when the user asks for an Azure architecture diagram — VNet/networking, App Service, AKS, landing zone, multi-region, or any diagram built with Azure service icons. Builds with the declarative layout engine using ground-truth Azure stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.

Use when the user asks for a BPMN diagram, swimlane diagram, business process map, or workflow diagram with roles/lanes and phases. Builds with the declarative layout engine using canonical mxgraph.bpmn stencils (events, gateways, typed tasks) in horizontal swimlanes (pool → lanes × phases), validates (BPMN semantic rules plus geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.

Use when the user asks for a Databricks lakehouse architecture diagram — medallion architecture (Bronze/Silver/Gold), Delta Lake, Unity Catalog, workspace deployment, data-plane/control-plane, or any diagram built with Databricks icons. Builds with the declarative layout engine using ground-truth stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.

Use when the user asks for a GCP or Google Cloud architecture diagram — VPC/networking, GKE, Cloud Run, landing zone, multi-region, or any diagram built with GCP service icons. Builds with the declarative layout engine using ground-truth GCP stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request.

A step-by-step guide to synthesizing research from multiple sources into a coherent summary.

Generates a structured skill template based on provided specifications.

This skill provides a comprehensive context extraction system for large codebases. It intelligently analyzes code structure, dependencies, and relationships to extract relevant context for understanding, debugging, or modifying code.

Compiles comprehensive company product context from PDF documents, web research, and industry knowledge

Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources.

Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.

Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.

Generates Anthropic Skills with complete workflow including GitHub PR creation and local download verification.

Generates complete Anthropic SKILL packages with proper structure, documentation, and automated download verification.

Use whenever the user mentions YouTube, video uploads, channel management, playlists, video SEO, or any YouTube Data API operation. Manages videos, playlists, comments, captions, subscriptions, thumbnails, analytics, and more via the yutu CLI.

Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.

后端代码编写、逻辑强、安全性高、可读性好、版本控制、代码审查。当任务需要写实验代码、模型代码、数据处理代码、可视化代码、后端接口或系统逻辑时使用。要求逻辑清晰、安全、可读、可维护、便于复现/扩展/部署。支持 Git 版本管理、代码审查、注释规范、README、依赖管理、环境配置、运行说明与项目结构整理。

Verify scholarly references and claim-citation support for Light stage 10. Use when auditing a manuscript, claim map, bibliography, DOI/arXiv/PMID/ISBN/URL, BibTeX/CSL, citekeys, chimeric or fabricated citations, retraction/correction alerts, or preparing a canonical citation registry for typesetting. Builds provenance-preserving inventories, confirms metadata with independent authoritative sources, distinguishes CONFIRMED/CONFIRMED-MISSING/UNAVAILABLE/UNRESOLVED, records Crossref update direction, and emits the citation gate plus delivery artifacts.

竞赛与项目申报材料辅助。当用户做统计建模、数学建模、互联网+、挑战杯、大创、创新创业、科研训练等项目时使用。辅助写申报书、项目计划书、商业计划书、路演 PPT、答辩稿、项目摘要、技术路线、创新点、可行性分析、市场分析、研究基础、预期成果、经费预算、团队分工。用于非论文投稿场景，可与论文/软著/专利/PPT 联动。

>-

>-

从顶会大牛角度进行专业绘图与组图。当用户需要把规划好的图实际画出来时使用。按情况用 Python(matplotlib/seaborn/plotly/altair)、R(ggplot2)、MATLAB、Visio、Origin、LaTeX/TikZ、Illustrator、PowerPoint 等。审美统一、专业清晰、配色合理、字体规范、线条清楚、高分辨率，适合直接投稿。不仅画图，还从论文表达角度判断怎么排、怎么组、怎么标注、怎么突出重点。

根据论文内容规划应该做哪些图、哪些表、插在哪里、各起什么作用。当用户需要论文图表规划时使用。图表不限于统计图，也包括数据集真实效果图、模型输出示例、案例展示、可解释性可视化等。规划框架图、技术路线图、数据集示意图、模型结构图、算法流程图、结果对比/消融/敏感性图、真实效果图、统计表/对比表等，以审稿人标准判断哪些必做、哪些冗余。

>-

>-

>-

>-

辅助软件著作权与专利申请。当用户需要做软著或专利材料时使用。软著：软件名称、功能说明、操作说明书、源代码整理、文档撰写、材料清单、流程、界面截图、功能模块说明、版本与完成日期。专利：判断是否可申发明/实用新型/外观，梳理技术问题、技术方案、有益效果、创新点、实施例、权利要求书与说明书草案、附图说明。最终文本须由专业代理人审核。

>-

>-

Coordinate and recover multi-stage Light research projects through the canonical .light/passport.yaml state, stages 1-13, resident overlays, checkpoints, findings, parallel joins, stale propagation, handoffs and user-authorized reroutes. Use for a new/resumed/partial/dirty/failed/stale/delivered research project; when the user says continue, resume, take over, checkpoint, reroute, recover or deliver; or when work crosses two or more Light research stages. Never turn frontend-design/system-design/patent-disclosure/software-copyright or overlays into stages, never execute a suggested back-edge without explicit user authorization, and never declare delivery from file existence alone.

撰写论文初稿与单章节起草、重写、自检。当用户要写论文、写某个章节（标题/摘要/引言/相关工作/方法/实验/结果/讨论/结论/局限/未来工作）、重写某章节、或对草稿做失败模式自检时使用。五种模式 full/outline-only/abstract-only/section-redraft/self-review；以顶刊/顶会审稿人标准打磨，逻辑严谨、创新点突出、结论不夸大、claim 有引用支撑。

对论文分模块润色——语言润色、逻辑重构、结构优化、创新点强化、论证补强、摘要精炼、引言增强、实验分析深化、结论提升。当用户需要改论文、觉得某段不通顺/逻辑弱/创新点不突出时使用。从审稿人角度找逻辑薄弱、论证不足、表达不专业、易被质疑、缺引用、需重组之处，给出具体修改方案与修改后文本。

>-

>-

>-

>-

Build auditable peer-review revision and author-response packages for Light stage 13. Use after receiving reviewer comments, a decision or meta-review; when drafting a rebuttal or response letter; when triaging major/minor revisions; when simulating a pre-submission review; or when a rejection may require a user-chosen 13→3 novelty, 13→5 experiment, or 13→8 writing back-edge. Consumes the selected venue/context and real PDF facts, preserves reviewer wording, atomizes issues, binds claims/evidence/actions/provenance, separates PLANNED from DONE, checks current venue limits without borrowing another venue's rules, and emits the stage-13 gate without changing venue, manuscript, evidence, citations, figures, PDF, or passport automatically.

自动反思与自我审查。每次完成任务后自动检查是否存在逻辑漏洞、事实错误、格式问题、表达不清、创新不足、引用不准、结果夸大、审美不统一、重复内容、结构混乱、不可执行等问题（常驻，所有任务收尾时生效）。不一次性给出粗糙结果，而是先自我审查与迭代后再输出。

制作精美 PPT。当用户需要为论文、项目、竞赛、答辩、汇报、路演做幻灯片时使用。设计封面/目录/过渡/内容/图表/流程/时间线/对比/团队/结论/致谢等页。逻辑清晰、排版高级、审美统一、重点突出，按主题选风格（学术/科技/农业/医学/商务/极简/浅色/深色/数据可视化/竞赛路演）。不仅生成内容，还规划整套叙事逻辑、视觉风格、页面层次与演讲节奏。

>-

工具选择与多工具协同。根据任务自动判断适合用什么工具——搜索、Python、R、MATLAB、LaTeX、Word、Excel、PowerPoint、Visio、Origin、数据库、Git、前端/后端框架、绘图工具、文献管理工具等（常驻，所有任务后台生效）。不盲目用工具，而是按实际任务选最高效、最稳定、最专业的实现方式。

Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11. Use when receiving a paper-writing manuscript, figure delivery, citation delivery.json/references.bib/citekey-audit.json, or a venue/template profile; when selecting pdfLaTeX/XeLaTeX/LuaLaTeX and BibTeX/Biber; when diagnosing LaTeX errors or unresolved references; when checking page limits, double-blind identity, PDF metadata, template, page box, embedded fonts, TODOs, figures, tables, labels and citations; or when producing a reproducible compile manifest, PDF, compliance report, failure bundle and venue-matching handoff. Distinguishes PASS, manuscript ERROR, toolchain UNAVAILABLE and convergence UNRESOLVED without redoing citation authenticity or figure scientific QA.

Build evidence-bound journal or conference shortlists for Light stage 12. Use after typesetting delivers venue-handoff.json/PDF/compliance facts; when an author asks where to submit, journal selection, conference fit, scope or article-type matching, publication strategy, reach/match/safety tiers, transfer order, APC/OA/indexing/deadline constraints, or predatory/hijacked-journal risk. Produces a current-source candidate registry, fit/risk/unknown reports, and an unchosen decision packet; never recompiles the PDF, invents acceptance rates, condemns a venue from soft signals, chooses without a direct user choice or explicit delegation, or submits.

>-

>-

>-

>-

>-

>

>

>

>

Build and review Remix 3 applications using the `remix` npm package and

>

How to run and test kody's multi-worker local dev (origin kody worker +

Generate and maintain the system recap block in a PR description - a

Search and manage private, local document collections (PDF, PPTX, DOCX) offline. Use when you need to find information within your private files, not for web research.

MDA compatibility demonstration skill for Claude Code. Compiled from compat/claude-code/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md loads in Claude Code with the envelope subset of agentskills.io v1 fields honored.

MDA compatibility demonstration skill for Codex CLI. Compiled from compat/codex-cli/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md is discovered and parsed by Codex CLI with the envelope subset of agentskills.io v1 fields honored.

MDA compatibility demonstration skill for Hermes Agent. Compiled from compat/hermes/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md is discovered, parsed, and listed by Hermes Agent under its `~/.hermes/skills/<category>/<name>/SKILL.md` layout.

MDA compatibility demonstration skill for OpenClaw. Compiled from compat/openclaw/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md installs cleanly via `openclaw skills install <local-dir> --global` and is reported as parsed by `openclaw skills info --json`.

MDA compatibility demonstration skill for OpenCode. Compiled from compat/opencode/source.mda. Loading this skill confirms that an MDA-emitted SKILL.md is discovered and parsed by OpenCode with the envelope subset of fields documented at opencode.ai/docs/skills/ honored.

Basic compiler conformance fixture.

Minimal MDA source demonstrating relationship-graph footnotes and metadata.mda.* MDA-extended fields. Use as a reference fixture when learning the MDA source format.

Run a TypeScript script via tsx to fetch an HTTP endpoint and stream the response. Use when you need a small Node.js helper for HTTP calls.

Draft a Changesets file for modified public packages in this repo.

Run the local maintainer release flow for this Changesets-based pnpm monorepo.

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof

Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement

5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance

Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating architecture styles.

Comprehensive architecture patterns, methodologies, quality frameworks, and evaluation methods for solution architects. Load when designing system architecture or selecting patterns.

Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.

Domain-specific authoritative source databases, search strategies by topic category, and source freshness rules

BDD patterns for acceptance test design - Given-When-Then structure, scenario writing rules, pytest-bdd implementation, anti-patterns, and living documentation

BDD requirements discovery methodology - Example Mapping, Three Amigos, conversational patterns, Given-When-Then translation, and collaborative specification

Structured divergent thinking techniques — HMW framing, SCAMPER, Crazy 8s mechanics, and option diversity guarantees. Enforces strict separation of generation and evaluation phases.

All /nw-* commands — what they do, when to use them, which agent they invoke. For the buddy agent to help users pick the right command.

How the nWave buddy agent reads a project to answer questions — detection, order of inspection, and citation discipline.

Single Source of Truth detection — where truth lives in an nWave repo and how to avoid contradicting it.

Wave methodology knowledge for the buddy agent — what each wave does, its inputs and outputs, and how to route questions.

nWave concierge — ask any question about methodology, project state, commands, migration, or troubleshooting. Read-only, contextual answers.

Bug fix workflow: root cause analysis → user review → regression test + fix via TDD

Canary skill for auto-injection detection

CI/CD pipeline design methodology, deployment strategies, GitHub Actions patterns, and branch/release strategies. Load when designing pipelines or deployment workflows.

Cross-agent collaboration protocols, workflow handoff patterns, and commit message formats for TDD/Mikado/refactoring workflows

Documentation collapse anti-patterns - detection rules, bad examples, and remediation strategies for type-mixing violations

Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence

Step-by-step workflow for converting bloated command files to lean declarative definitions

Detects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.

Crafter discipline contract for the ATDD-pure 7-phase workflow — what the slim crafter does in Phase A (GREEN-the-ATs), Phase B (coverage-driven dead-code elimination), and Phase E (batch L1-L6 refactor), plus hard prohibitions and the Phase B common-cuts taxonomy

Data architecture patterns (warehouse, lake, lakehouse, mesh), ETL/ELT pipelines, streaming architectures, scaling strategies, and schema design patterns

Database comparison catalogs, RDBMS vs NoSQL selection criteria, CAP/ACID/BASE theory, OLTP vs OLAP, and technology-specific characteristics

Event Modeling facilitation technique — brainstorm events, identify commands and views, define aggregate boundaries, write Given-When-Then specifications

Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution

Strategic DDD — bounded context discovery, context mapping patterns, subdomain classification, ubiquitous language, and organizational alignment

Tactical DDD — aggregate design rules, entities, value objects, domain events, repositories, domain services, and anti-pattern detection