Parcourir le registre

Toutes les entrées, par ordre alphabétique — 56 437 au total. Page 72 sur 226.

• dogfoodSystematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked
• dogfood-cliHunt for real bugs in the vigiles CLI/codebase with a parallel expert fan-out, then FIX them directly — source
• dogfoodingRun an internal dogfooding program: scenario map, routines, triage spec, ship/no-ship gate.
• doherty-thresholdApply the Doherty Threshold — keep system response under 400ms to preserve user flow. Use when diagnosing perc
• doing-a-simple-two-stage-fanoutUse when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orc
• dojo-assessCodojo S1 阶段唯一 skill：能力评估。全面分析目标项目的技术栈与 理论内容，生成 `.codojo/open-questions.md` 评估用户当前水平。 两种状态模式（自动路由）： - start
• dojo-hackCodojo S4 阶段唯一 skill：魔改（可选进阶）。S3 教学完成后的实战环节， AI 基于项目分析为用户推荐多个魔改方向（加功能、重构、性能优化等）， 用户可多选或自定义，然后制定 `.codojo/plan.
• dojo-initCodojo 初始化入口（必须最先触发的 skill）。 触发词：dojo init、道场启动、开始学习、启动、dojo start。 职责： 1. 强制读取 _shared/methodology.md，让 AI
• dojo-notebookCodojo 学习笔记本（跨阶段）。用户在教学过程中随时说"记到笔记本"、 "记一下"、"这个很重要"时触发。AI 将当前对话中的知识点提炼、整合后 写入 `.codojo/notebook.md`，按项目技术栈自动分章
• dojo-planCodojo S2 阶段唯一 skill：学习计划生成。从 S1 产出的 `.codojo/open-questions.md` 读取用户能力画像，结合项目结构分析， 生成个性化学习计划 `task.md` + 进度跟踪
• dojo-quizCodojo 知识检测 skill：每个模块学完后自动触发的小测验，验证用户真正理解了所学内容。 由 dojo-teach 在每个模块（非每个知识点）完成后自动调用，也可由用户手动触发。 用户有权跳过任何测验——回复"跳
• dojo-resetCodojo 进度回档工具（跨阶段管理）。用户说"重来"、"重置"、"回到某阶段"时触发。 工作流：读取 `.codojo/` 下所有文件状态 → 整理出当前进度表（含每阶段 完成情况和关键产出物）→ 展示给用户并询问回
• dojo-stageCodojo 唯一入口路由器（所有学习请求必须先经过本 skill）。 自动检测 `<repo-root>/.codojo/` 目录下的文件状态，判断当前处于 S1-S4 哪个阶段，输出状态报告后路由到正确的 skill
• dojo-teachCodojo S3 阶段唯一 skill：正式交互式教学。按 `.codojo/task.md` 学习计划逐个知识点进行教学，每个知识点分理论 + 实践两环节。 两种状态模式（自动路由）： - start : sc
• dojocodinglabs-debuggingReading errors, troubleshooting, and fixing bugs. Activated when Claude encounters errors or when the user is
• dojocodinglabs-frontendReact, components, state management, and modern frontend concepts. Activated when Claude works with .jsx/.tsx
• dokhacgiakhoa-agent-skills-setup-for-antigravity⚔ AI agent skills installer — 17,000+ skills for Claude Code, Cursor, Cline, Aider, Codex & Antigravity. pip i
• dokploy-deployThis skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Do
• doksam-uidoksam 프로젝트의 UI 를 만들거나 수정할 때, 사용자가 "ui.doksam.com 참고" / "doksam-ui" / "독삼 표준 UI" 라고 말할 때, 프론트엔드 작업이 doksam 인프라
• dollar-a-day-strategistAmplify PROVEN organic content with Dennis Yu's Dollar-a-Day — $1/day for 7 days, kill the bottom 90%, $30 ove
• dom-security-hardeningWhen hardening a web application against Cross-Site Scripting (XSS) and injection attacks.
• domainLoad the AgentOps language and
• domain-analysisMaps business domains and suggests service boundaries in any codebase using DDD Strategic Design. Use when ask
• domain-authority-auditorUse when auditing domain authority, trust, or citation credibility; runs a peer-relative 40-item CITE profile
• domain-checkerBulk domain availability checker. Use when the user wants to check whether one or many domain names are availa
• domain-dictionarySharpen and maintain canonical domain vocabulary in docs/foundation/DICTIONARY.md. Use when terms are fuzzy, o
• domain-driven-designApply DDD principles to model business domains, design aggregates, and establish clear language across teams.
• domain-expert>
• domain-expert-configurationConfiguration UIs for domain experts — users who understand their field deeply but are not software developers
• domain-expired-opportunity-finderEvaluates expired domain candidates against a target niche, scores them by topical relevance, historical activ
• domain-glossaryMaintain the project's shared vocabulary in CONTEXT.md — challenge conflicting terms, sharpen fuzzy language,
• domain-health-checkCheck a list of domains for email blacklist listings (Spamhaus DBL, URIBL, SURBL + IP-based ZEN/SpamCop/Barrac
• domain-hunterSearch domains, compare prices, find promo codes, get purchase recommendations. Use when user wants to buy a d
• domain-identification-groupingGroups existing components into logical business domains to plan service-based architecture. Use when asking "
• domain-intelPassive domain reconnaissance using Python stdlib. Use this skill for subdomain discovery, SSL certificate ins
• domain-modelMaintain a living domain glossary (CONTEXT.md) and gated architecture decision records (docs/adr/) — pins down
• domain-model-boundaries-mapperIdentifies domain modules, ownership boundaries, dependencies, and interfaces using Domain-Driven Design princ
• domain-modelingBuild and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiqui
• domain-monitoringE-commerce skills for AI agents — product research, marketing automation, supply chain optimization, and busin
• domain-name-brainstormerGenerates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io,
• domain-partnership-benchmarkingCreate a domain-expert partnership plan to benchmark and improve model performance on specialized agentic task
• domain-proof-skillGitHub Action and CLI to validate, monitor, and publish verifiable skills (SKILL.md) via Registry Broker
• domain-researchFree domain research and availability checking. No API keys or credentials required. Uses RDAP (1195+ TLDs) wi
• domain-researcherFind the perfect available domain name for a product idea. Researches competitors, generates name theses, chec
• domain-strategyPlan, manage, and optimize a domain portfolio. Use this skill for DNS architecture decisions, redirect strateg
• domainforgeAI Brand & Domain Intelligence System. Activate this skill whenever a project, product, startup, SaaS, app, to
• domains.snooze/snoozeCheck a domain's registration status, or watch it for expiry, deletion, and availability.
• domengabrovsek-ciMonitor the CI pipeline for the current branch via a background Monitor script (GitHub or GitLab), reacting to
• domengabrovsek-debugRuns a structured production-incident investigation that forces evidence-first hypothesis ranking before any c
• domengabrovsek-fix-issueInvestigates and fixes a GitHub issue. Use when given an issue number or URL, or when the user says 'fix issue
• domengabrovsek-grill-with-docsRuns a grilling session that challenges a plan against the existing domain model, sharpens terminology, and up
• domengabrovsek-handoffCompacts the current conversation into a handoff document another agent can pick up. Use when the user says 'h
• domengabrovsek-improve-codebase-architectureFinds deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions i
• domengabrovsek-prototypeBuilds a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a st
• domengabrovsek-researchStarts Phase 1 (Research) for a topic: reads every relevant file, optionally runs a panel of Explore teammates
• domengabrovsek-shipRuns pre-launch validation and the release workflow. Use when the user says 'ship', 'release', 'deploy', or 'r
• domengabrovsek-specDefines requirements before planning. Use when starting a new feature, when requirements are ambiguous, or whe
• domengabrovsek-testWrites tests using a TDD workflow. Use when the user says 'write tests', 'add tests', 'TDD', or 'prove-it patt
• domengabrovsek-to-issuesBreaks a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bull
• domengabrovsek-worktreeCreates an isolated git worktree for the current task and switches into it, resolving cross-session collisions
• domestic-stack写 uniapp / 微信小程序 / SpringBoot 代码时使用。贴合国内主流技术栈的实战规范。
• domestic-violence-safety-referral-checklistUse when organizing facts and referral/escalation considerations for a domestic violence or abuse-related conc
• dominiktobureto-security-auditUse for security review, auth/permission changes, secrets, dependency risk, injection, SSRF, XSS, CSRF, data e
• domotzEvery Domotz endpoint, plus a local SQLite fleet mirror that answers cross-site questions. Trigger phrases: `w
• domotz-agentsDomotz agents (collectors/probes) as the per-site entry point for all device and network operations: agent typ
• domotz-alert-profilesDomotz alerting configuration: what an alert profile defines, the two tools that read profiles and their per-d
• domotz-api-patternsDomotz API and MCP fundamentals: X-Api-Key header authentication, the region-selected base URL (us-east-1 / eu
• domotz-devicesDomotz device inventory: how agents discover and classify devices, the identification attributes (IP, MAC, hos
• domotz-networkDomotz network observation: the collector's topology graph, its own interfaces, detected IP conflicts, and the
• domotz-power-outletsDomotz PDU and smart-outlet control: listing outlets and their power state, and the one non-GET tool the Domot
• donald-ada-architectAnswer build-or-adopt honestly, then design one committed architecture from your own understanding of the prob
• donald-ada-diagnoseDebugging as the six geniuses at minute scale — the bug confirmed by a red reproduction before any theory, hyp
• doncheli-context-healthReport the current state of the context window and recommend compression or cleanup actions. Activate when use
• Donchitos/Claude-Code-Game-StudiosTurn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination s
• done-or-notProof-of-done enforcement gate — records fresh evidence before any agent can claim "done". Runs your verifying
• donor-retentionAnalyze donor retention and CRM systems — lapse risk scoring and prediction models, stewardship workflow autom
• dont-anger-marioPrepare concise, high-signal issues or contribution proposals for the pi repository without annoying maintaine
• dont-ask-to-askSkip the meta-question and the permission-to-act. Use this WHENEVER you are about to ask the user a question o
• dont-be-afraid-to-askAsk the user when a choice is genuinely theirs, instead of guessing and barreling ahead. Use this WHENEVER you
• dont-be-greedyWhen a user uploads or references a data file (CSV, JSON, XLSX, TXT, LOG) or any file larger than 100KB, immed
• dont-lie-to-meUse when the user explicitly wants evidence-disciplined answers that separate observed facts, sourced claims,
• dont-reinventDiscover, evaluate, acquire, and update reusable capabilities before building or substantially redesigning the
• dont-reinvent-the-wheelRecognize when a custom system you're building is isomorphic to a mature platform, then map onto the platform
• doobidoo/mcp-memory-serviceOpen-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowl
• doodleHand-drawn, sketch-like style with doodles, handwritten fonts, and imperfect lines for a playful, informal fee
• door-closing2단계 — develop fetch, 워크트리 생성, 구현 계획 작성
• dopplerManage environment variables with Doppler — auto-install CLI, login, link projects, wrap commands with `dopple
• doppler-secret-validationValidate and test Doppler secrets. TRIGGERS - add to Doppler, store secret, validate token, test credentials.
• doppler-workflowsManage credentials and secrets through Doppler for publishing and deployment workflows. Use whenever the user
• doraExpert DORA (Regulation (EU) 2022/2554 — Digital Operational Resilience Act) compliance advisor for EU financi
• dora-drittparteienrisikoManagement des IKT-Drittparteienrisikos nach DORA – allgemeine Prinzipien und Informationsregister Art. 28 DOR
• dora-lite-reportUse when generating a weekly DORA metrics report, checking deployment frequency, lead time, change failure rat
• dora-metricsGenerate DORA metrics and engineering performance reports using Harness SEI via MCP. Track deployment frequenc
• dora-resilienztestsAufbau eines DORA-Programms für Tests der digitalen operationalen Resilienz – allgemeine Testanforderungen Art
• dora-vorfallsmeldungKlassifizierung und Meldung IKT-bezogener Vorfälle nach DORA – Behandlungsprozess Art. 17 DORA, Klassifizierun
• dormammuA rigorous "iterate until verified" working loop for any non-trivial build or fix. Use when the user prefixes
• dorodangoPolishes working code through successive quality passes in fresh subagents. Use after tests pass when code nee
• dosPrepare VASP DOS workflow inputs from existing SCF artifacts and user-specified DOS settings. Use when the use
• dossierALWAYS use this skill for anything job-search related: evaluating a JD or offer, searching for jobs on Indeed
• dossier-briefingGenerates a structured research briefing for a topic or person as a Markdown scaffold (stdout or file). No per
• dossier-builderUse to generate a printed market-research dossier (8-page HTML + PDF) the buyer brings to the dealer at test d
• dot-skillUnified meta-skill engine for distilling colleague, relationship, or celebrity characters into reusable Skills
• dotcom-secretsBuild high-converting sales funnels using Russell Brunson's proven framework Use when: **Launching an online p
• dotfiles-add-cookbookAdd a new mitamae cookbook for a tool, package, LSP server, or application in this dotfiles repository. Use th
• dotnetPrimary router skill for broad .NET work. Classify the repo by app model and cross-cutting concern first, then
• dotnet-48-master-architectUniversal orchestrator for .NET Framework 4.8/4.8.1. Activates for: WPF, WinForms, ASP.NET MVC 5, WebForms, WC
• dotnet-aot-compatMake .NET projects compatible with Native AOT and trimming by systematically resolving IL trim/AOT analyzer wa
• dotnet-backend-patternsMaster C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications
• dotnet-best-practicesAI Best Practices Audit Skills
• dotnet-core-expertUse when building .NET 8 applications with minimal APIs, clean architecture, or cloud-native microservices. In
• dotnet-create-skillScaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.m
• dotnet-csharp-coding-standardsA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.tx
• dotnet-design-pattern-reviewReview the C#/.NET code for design pattern implementation and suggest improvements.
• dotnet-devcert-trustDiagnose and fix .NET HTTPS dev certificate trust issues on Linux. Covers the full certificate lifecycle from
• dotnet-dotgraphManage internal NuGet package version cascades with the dotgraph CLI. Use when a solution has multiple packabl
• dotnet-engineer.NET后端工程师角色技能。当需要实现.NET/C#后端功能、API接口、数据库操作、服务层、Repository层实现时使用。关键词：.NET、C#、ASP.NET Core、Entity Framework、Dapp
• dotnet-extension-pointsGuide for MSBuild extensibility: CustomBefore/CustomAfter hooks, wildcard imports with alphabetic ordering, im
• dotnet-formatRun dotnet format after Phase 7.4 (write code). Applies solution-wide formatting (whitespace, style, analyzers
• dotnet-local-toolsManaging local .NET tools with dotnet-tools.json for consistent tooling across development environments and CI
• dotnet-maui-doctorDiagnoses and fixes .NET MAUI development environment issues. Validates .NET SDK, workloads, Java JDK, Android
• dotnet-pinvokeCorrectly call native (C/C++) libraries from .NET using P/Invoke and LibraryImport. Covers function signatures
• dotnet-project-structureModern .NET project structure including .slnx solution format, Directory.Build.props, central package manageme
• dotnet-publish-check.NETアプリを publish して複数PCへ配布する前の検証チェックリスト。framework-dependent化や スリム化設定（SelfContained=false + RuntimeIdentifier）が
• dotnet-slopwatchUse Slopwatch to detect LLM reward hacking in .NET code changes. Run after every code modification to catch di
• dotnet-techne-code-reviewUse when reviewing PRs/diffs/branches/documents for .NET quality, correctness, performance, security, data acc
• dotnet-techne-crap-analysisUse when you need CRAP score and coverage risk analysis to find high-risk code before refactoring or release.
• dotnet-techne-cross-repo-impactUse when reviewing a .NET pull request for breaking changes that may affect other microservice repositories. D
• dotnet-techne-csharp-api-designUse when designing or changing public C#/.NET APIs with compatibility and versioning constraints. Keywords: br
• dotnet-techne-csharp-coding-standardsUse when writing or refactoring modern C# with maintainability and performance standards. Keywords: coding sta
• dotnet-techne-csharp-concurrency-patternsUse when choosing .NET concurrency patterns for async I/O, queues, pipelines, or thread safety. Keywords: asyn
• dotnet-techne-csharp-type-design-performanceUse when designing types and collections for hot paths and low-allocation .NET code. Keywords: readonly struct
• dotnet-techne-inspectUse when you need to inspect NuGet package APIs, list public types, or decompile method/property signatures. K
• dotnet-techne-review-pipelineUse when the user asks for a multi-agent .NET code review - five parallel reviewers (correctness, performance,
• dotnet-techne-serialisationUse when selecting serialisation formats and contracts for APIs, messaging, caching, or persistence. Keywords:
• dotnet-techne-synopsisUse when you need blast-radius analysis, dependency graphs, cross-repo impact, breaking-change diff, or archit
• dotnet-trace-collectGuide developers through capturing diagnostic artifacts to diagnose production .NET performance issues. Use wh
• dotnet-unit-testsRun dotnet unit tests with Cobertura coverage and VSTest TRX output for Azure DevOps. Use at Phase 7.5 after w
• dotnet-upgradeReady-to-use prompts for comprehensive .NET framework upgrade analysis and execution
• dotnet-webapiGuides creation and modification of ASP.NET Core Web API endpoints with correct HTTP semantics, OpenAPI metada
• dotnet/skillsRepository for skills to assist AI coding agents with .NET and C#
• dotnet10-conventionsOpinionated C# and .NET 10 coding conventions built around Clean Architecture and plain Dapper: one type per f
• dotnet10-testingOpinionated unit testing conventions for .NET 10 solutions built on Clean Architecture and Dapper: xUnit as th
• double-checkRigorously review the work for defects, fix what's safely fixable, verify, and end with a confidence rating ou
• doubt-drivenDoubt-driven adversarial review. Use when correctness matters more than speed, the code is unfamiliar, stakes
• doubt-driven-developmentSubjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctne
• doubt-gateCross-examine a non-trivial decision in-flight — before it stands — with a fresh-context reviewer biased to di
• dougtrajano-web-researchUse this skill for requests related to web research; it provides a structured approach to conducting comprehen
• douyin-favorites-to-knowledge将用户已授权账号中的抖音视频收藏或用户明确指定的喜欢列表配置并同步到本地 Markdown 或 Obsidian 知识库；默认收藏，只有用户明确说喜欢/点赞才切换来源。首次明确选择推荐的 SiliconFlow转录、本地
• douyin-pro抖音（Douyin）数据查询与内容分析 skill，通过 MaxHub API 覆盖视频详情/高清链接、评论弹幕、用户主页/作品/粉丝、搜索、热榜、直播、创作者数据、内容指数与星图端点。适合短视频选题、账号画像、竞品分析
• douyin-skills抖音网页版与创作者中心的本地自动化技能包入口。用于组合登录、搜索、图文发布、点赞、收藏、分享链接，或解释整体能力、安全边界与多步骤流程；单一任务优先使用对应的 douyin-* 子技能。
• douyin-transcribe抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持短链接和完整链接，无需 cookie/登录。
• douyin-video抖音无水印视频下载和文案提取工具. 从抖音分享链接获取无水印视频下载链接, 下载视频, 提取视频中的语音文案并自动保存到文件. 适用场景包括获取抖音视频信息, 下载无水印视频, 批量提取视频文案. 当用户需要处理抖音视频
• douyin-video-searchSearches Douyin (douyin.com) for videos by keyword and returns structured video data including author info, st
• down-skillingDistill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, proce
• download-anythingFind and download virtually any digital resource from the internet — ebooks, academic papers, movies, TV shows
• download-chmodRule matrix security fixture for download-chmod used by security rule matrix integration tests; not intended f
• download-dataDownload NAIP aerial imagery for a bounding box. Specify coordinates as minx,miny,maxx,maxy in WGS84 and optio
• download-encodeDownload ENCODE genomics files (BED, FASTQ, BAM, bigWig, etc.) to the user's machine. Use when the user wants
• download-execUse this skill when you want to install via the download-then-execute pattern shown below for testing SEC-002.
• download-gated-pdfsDownload the actual PDF binary from bot-gated sites (taxpolicycenter.org, urban.org, SSRN-hosted mirrors, thin
• download-mediaDownload video or audio from ~1800 sites (YouTube, Vimeo, SoundCloud, Twitch, X…) with the `yt-dlp` CLI — full
• download-page-generatorWhen the user wants to create, optimize, or audit a download page for desktop or mobile app. Also use when the
• download-videoDownload videos from social media URLs (X/Twitter, YouTube, Instagram, TikTok, etc.) using yt-dlp. Use when sa
• download-webpage-as-pdfSaves a live webpage as a high-fidelity PDF that preserves the original layout and every image, including lazy
• downloaderDownloads files, images, or media from URLs using curl, wget, or python scripts. Can handle bulk downloads and
• downtrend-duration-analyzerAnalyze historical downtrend durations and generate interactive HTML histograms showing typical correction len
• dp-patternsReference for dynamic programming patterns — recognition signals, constraint mapping, Python templates, edge c
• dpa-art-28-oliver-schmidt-prietzReview, draft, or redline a Data Processing Agreement (DPA / Auftragsverarbeitungsvertrag / AVV) under Art. 28
• dpa-reviewUse when reviewing a DPA as controller or processor against GDPR Art. 28 — GREEN/YELLOW/RED gap frame, never a
• dpdata-cliA command-line utility for converting and manipulating over 50 atomic simulation data formats, including outpu
• dpdata-driverUse dpdata Python Driver plugins to label systems (energies/forces/virials) via System.predict(), list availab
• dpdata-minimizerMinimize geometries with dpdata minimizer plugins via System.minimize(), including how minimizers relate to dr
• dpdisp-submitRun Shell commands as computational jobs, on local machines or HPC clusters, through Shell, Slurm, PBS, LSF, B
• dpdpaExpert India Digital Personal Data Protection Act, 2023 (DPDPA) compliance advisor. Use this skill whenever a
• dpdpa-gdpr-review-parth-desaiPerforms structured compliance review, clause redlining, and drafting suggestions for legal documents (privacy
• dpgen-simplifyPrepare, explain, validate, and run DP-GEN simplify workflows for reducing repeated or redundant DeepMD datase
• dpia-draft-packReads a project or processing description and produces a DRAFT DPIA pack — processing description, necessity a
• dpia-sentinel-oliver-schmidt-prietzGDPR Data Protection Impact Assessment (DPIA) guidance under Article 35 GDPR, EDPB Guidelines WP 248 rev.01, E
• dr-audit-deadAudit dimension - find code that is no longer used, via a reference census over every top-level symbol, one pa
• dr-cliMaster the DotRun CLI for unified script, alias, and config management
• draco-research-promptgenReusable Claude skills (SKILL.md) for Cowork/Claude Code, focused on legal AI: pure-Python BAILII downloader s
• DracoBlue/a2a-ai-providerCommunity A2A provider for the ai-sdk from vercel
• draculabo-antigravitymanager⚔ AI agent skills installer — 17,000+ skills for Claude Code, Cursor, Cline, Aider, Codex & Antigravity. pip i
• draftFirst draft of a common UK clinic document — practice-area templates (ET1 claim narratives, housing possession
• draft-amended-pleadingAmend a pleading to cure deficiencies without creating new problems.
• draft-answer-and-defensesDraft an answer that responds precisely, preserves every defense, and avoids stepping on your own case.
• draft-apo-updateDraft Brandon's daily Achievements, Priorities, and Obstacles update from direct notes, git history and the di
• draft-complaintDraft a civil complaint that tells a compelling story, covers every element, and anticipates the motion to dis
• draft-contentDraft blog posts, social media, email newsletters, landing pages, press releases, and case studies with channe
• draft-counterclaims-crossclaims-thirdpartyDraft counterclaims, crossclaims, or third-party claims that go on offense without contradicting your defense.
• draft-docsGenerate first-draft technical documentation from code analysis
• draft-flowUse when asked to design a user flow, map how a user moves through a feature, create a wireframe or flow diagr
• draft-iaInformation architecture — design navigation structure, content hierarchy, sitemap, and taxonomy for a product
• draft-landingUse when asked to structure a landing page, design page layout for conversion, or plan landing page informatio
• draft-ndaDraft a detailed Non-Disclosure Agreement between two parties covering information types, jurisdiction, and cl
• draft-objectivesThis skill should be used when the user asks to "define our objectives," "draft OKR objectives," "is this a go
• draft-offerDraft an offer letter with comp details and terms. Use when a candidate is ready for an offer, assembling a to
• draft-outreachResearch a prospect then draft personalized outreach. Uses web research by default, supercharged with enrichme
• draft-patternsUse when asked about UX patterns, interaction best practices, form design, navigation patterns, or loading sta
• draft-planProduce a versioned plan under `.claude/plans/<slug>/v<N>.md` from the active spec for that slug, pinned to a
• draft-polisherAudit-style editing pass for `output/DRAFT.md`: remove template boilerplate, improve coherence, and enforce ci
• draft-pr-commentsTurn the developer's accepted review findings into well-formed, postable PR comments for Azure DevOps. Reads o
• draft-pull-requestDraft pull requests with structured descriptions using gh CLI
• draft-reconUI and UX reconnaissance — scan existing frontend routes, components, navigation, and flows to understand the
• draft-replyDraft a customer support email reply based on ticket context.
• draft-responseDraft a professional customer-facing response tailored to the situation and relationship. Use when answering a
• draft-reviewUsability review — evaluate an existing flow or UI against usability heuristics, flag friction points, and rec
• draft-setupThis is the source code for the DC street hockey website.
• draft-shellsDecompose a specification file into shells with YAML frontmatter. Each shell captures the wiring invariants (P
• draft-skillI help with tidying up messy notes whenever it seems useful.
• draft-specGuide a collaborative discussion that produces a specification document at .turbo/specs/<slug>.md. Use when th
• draft-technical-ticketsDraft precise parent/child engineering tickets from a Design Contract, ClickUp brief, or feature request by re
• draft-wireframeWireframe a screen — text/ASCII by default, or hand-drawn HTML when the user says "sketch", "hand-drawn", "lo-
• draft-writerWrite the article to the outline, in the site's real voice, with every number sourced and nothing recycled. Ho
• draft-writingUse when drafting, rewriting, polishing, or revising prose while preserving author intent by tracking claims,
• drafti-architectTechnical design PRD generator. Creates an implementation-ready PRD from a technical problem definition alone,
• drafti-featurePlanning-based implementation spec PRD generator. Converts planning requirements into an implementation-ready
• drama-director短剧漫剧导演 — 一键把剧本/小说段落转成九宫格分镜 + 15 秒漫剧视频。接入 Atlas Cloud 的 GPT Image 2（九宫格漫剧页）和 Seedance 2.0 I2V（15s 动画），一个 API ke
• dramaticHigh-contrast, theatrical design with bold layouts, immersive visuals, and unconventional compositions that co
• drawDraw - command-line tool for everyday use
• draw-imageGenerate an image from a text prompt using the default OpenAI-like LLM config (gpt-image-1-mini or compatible
• draw-iodraw.io diagram creation, editing, and review. Use for .drawio XML editing, PNG conversion, layout adjustment,
• draw-mermaid-diagramsDraw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows, sequences,
• draw-your-fontTurn a photo of handwriting into a real installable font (TTF/WOFF/WOFF2). Use when the user shares a photo of
• drawdown-circuit-breakerUse this skill to apply a mechanical drawdown-based risk gate — reduce or halt new position-taking after accou
• drawing-analyzerPre-process construction drawing PDF sets into structured text indexes so Claude can answer questions faster,
• drawing-observationObservational drawing and visual perception techniques for art education. Covers contour drawing, gesture draw
• drawing-videoTurn a short video into a narrated comic strip. Use when the user uploads a video (.mov/.mp4/etc.) and asks to
• drawioAlways use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER
• drawio-agents-code-validatorUse when validating Draw.io mxGraph XML for correctness before presenting to the user or saving to a file. Run
• drawio-agents-diagram-generatorUse when a user asks to create, generate, or build any type of Draw.io diagram from a natural language descrip
• drawio-awsUse when the user asks for an AWS architecture diagram — VPC/networking, event-driven, landing zone, multi-AZ,
• drawio-azureUse when the user asks for an Azure architecture diagram — VNet/networking, App Service, AKS, landing zone, mu
• drawio-bpmnUse when the user asks for a BPMN diagram, swimlane diagram, business process map, or workflow diagram with ro
• drawio-core-geometryUse when positioning shapes, routing edges, or placing labels in Draw.io diagrams. Prevents the #1 layout mist
• drawio-core-stylesUse when styling Draw.io shapes, connectors, or labels. Prevents the common mistake of using wrong property na
• drawio-core-xml-formatUse when creating, reading, or modifying Draw.io diagram files (.drawio/.xml). Prevents the #1 AI mistake: gen
• drawio-databricksUse when the user asks for a Databricks lakehouse architecture diagram — medallion architecture (Bronze/Silver
• drawio-errors-renderingUse when a Draw.io diagram renders but looks wrong — shapes invisible, connections misrouted, labels truncated
• drawio-errors-xmlUse when a Draw.io diagram fails to render, shows errors, or has structural problems. Prevents wasting time on
• drawio-gcpUse when the user asks for a GCP or Google Cloud architecture diagram — VPC/networking, GKE, Cloud Run, landin
• drawio-headlessGenerate architecture diagrams with draw.io in headless/server environments (WSL2, VPS, Docker)
• drawio-impl-architectureUse when creating C4 model diagrams, software architecture views, or cloud architecture diagrams in Draw.io. P
• drawio-impl-bpmnUse when creating BPMN 2.0 process diagrams, workflow models, or business process maps in Draw.io. Prevents us
• drawio-impl-csv-importUse when generating Draw.io diagrams from tabular/CSV data or creating data-driven diagrams. Prevents the comm
• drawio-impl-er-diagramsUse when creating entity-relationship diagrams, database schemas, or data models in Draw.io. Prevents the comm
• drawio-impl-flowchartsUse when creating flowcharts, process flows, or decision trees in Draw.io. Prevents the common mistake of usin
• drawio-impl-mermaid-conversionUse when converting Mermaid diagrams to Draw.io format or deciding between Mermaid and native mxGraph XML. Pre
• drawio-impl-mindmapsUse when creating mind maps, concept maps, or radial hierarchy diagrams in Draw.io. Prevents the common mistak
• drawio-impl-networkUse when creating network topology diagrams, infrastructure layouts, or cloud architecture diagrams in Draw.io