Parcourir le registre

Toutes les entrées, par ordre alphabétique — 56 437 au total. Page 58 sur 226.

• correo-argentinoIntegración de envíos con Correo Argentino (apiMiCorreo) para ecommerce. Cubre autenticación y alta de cliente
• cors-auditorAudit a site's Cross-Origin Resource Sharing (CORS) configuration for misconfigurations — wildcard origin with
• cors-securityStrict CORS: no wildcard with credentials, exact-match origin allowlists, sane preflight cache, minimal expose
• cors-security-testingTesting Cross-Origin Resource Sharing configurations for misconfigurations, overly permissive policies, and cr
• cortexML/AI engineer — LLM integrations, prompt engineering, model pipelines, evals, RAG.
• cortex-automateSet up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user s
• cortex-broadcastllm-wiki style broadcast ingest — conversational update of related existing pages when a Raw has been distille
• cortex-consolidateRun memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semant
• cortex-debug-memoryDebug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories,
• cortex-distillDistill raw session records into refined Notes and Projects. Use when the user says "提煉", "整理 raw", "distill",
• cortex-evalEvaluate model performance — check for accuracy drops, data drift, and error patterns. Use when asked about "m
• cortex-evolveSave knowledge to the cortex vault. Use when the user says "存到 cortex", "記一下", "save to cortex", "記到筆記", "cort
• cortex-explore-memoryExplore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Us
• cortex-importImport memories from other AI memory systems into Cortex. Supports claude-mem (SQLite), Claude Desktop session
• cortex-integrateDesign and implement an AI feature integration — model selection, architecture pattern, system prompt, data fl
• cortex-mBuild, test, or develop the Cortex-M (CMSIS-NN) backend. Use when working on backends/cortex_m/, running Corte
• cortex-m-debugUse when debugging Cortex-M microcontrollers, firmware bring-up, SWD/JTAG sessions, faults, startup code, or f
• cortex-modelBuild an ML pipeline — from data to trained model to serving endpoint. Use when asked to "build ML model", "tr
• cortex-navigate-knowledgeNavigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters,
• cortex-profileView and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connectio
• cortex-promptBuild a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling,
• cortex-querySearch and retrieve content from the cortex vault — the user's external memory. Use (1) when the user says "查
• cortex-r5-debugUse when debugging Cortex-R5 or Cortex-R firmware — TCM, MPU, caches, DFSR/DFAR aborts, exceptions, GIC/VIC in
• cortex-recallSearch and retrieve memories from Cortex persistent memory. Use when the user asks 'what did we decide about X
• cortex-recall-globalSearch and retrieve global memories — knowledge that applies across all projects. Use when the user asks 'what
• cortex-reconML reconnaissance — inventory all models, pipelines, data sources, and monitoring. Use when asked "what ML do
• cortex-rememberStore important decisions, patterns, errors, lessons, and context into Cortex persistent memory. Use when the
• cortex-remember-globalStore a global memory that is visible across all projects. Use when the user shares architecture rules, coding
• cortex-setup-projectBootstrap Cortex for a new project or import existing session history. Use when the user says 'set up Cortex',
• cortex-skills-loopDrives the cortex skills recommend-feedback-rate loop. Use when a context change occurs (new file types, domai
• cortex-takeoffCreate or resume a session takeoff baton — a curated, ephemeral, git-ignored hand-off note that lets the next
• cortex-wiki-authorAuthor first-class wiki pages (ADRs, specs, file docs, notes) that live alongside Cortex memory. Use when the
• corv89-prCommit changes, bump version, update changelog, and open a PR
• cosmicFuturistic sci-fi aesthetic with dark themes, vibrant neon accents, and immersive spatial elements.
• cosmic-databaseAccess COSMIC cancer mutation database. Query somatic mutations, Cancer Gene Census, mutational signatures, ge
• cosmic-eldritch-horrorCosmic, eldritch, and Lovecraftian horror art direction for Blender with non-Euclidean cues, impossible scale,
• cosmic-mythic-overlayLayer an Arcanea-style cosmic-mythic framing over a real space object or event, keeping the astronomy intact a
• cosmological-observationObservational cosmology from Hubble's law to the CMB. Covers redshift, Hubble expansion, the cosmological para
• cosmos-dbt-coreTurns a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos. Use turning a dbt Core project
• cosmos-dbt-fusionRun a dbt Fusion project with Astronomer Cosmos. Use when running a dbt Fusion project with Astronomer Cosmos
• cosmos-vulnerability-scannerScans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities — chain halt
• cosmosdbAzure Cosmos DB multi-model database with global distribution. Use for Azure.
• cosmosdb-best-practicesAzure Cosmos DB performance optimization and best practices guidelines for NoSQL, partitioning, queries, and S
• cosmosdb-datamodelingStep-by-step guide for capturing key application requirements for NoSQL use-case and produce Azure Cosmos DB D
• costEstimate and analyze costs for AI/cloud services, infrastructure, or feature implementations. Use when user as
• cost-alertReview the configured cost alert rules and the alerts currently fired on the Agent Monitor dashboard, then exp
• cost-analysisPerforms cost-of-goods-sold and cost-per-unit analyses with margin calculations and optimization recommendatio
• cost-auditUse when AI inference costs are growing unexpectedly, when comparing model choices by cost/quality ratio, or w
• cost-aware-llm-pipelineCost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic,
• cost-breakdownBreak down Claude Code costs using the Agent Monitor pricing engine. Shows per-model costs (input, output, cac
• cost-estimateEstimates project cost at market rates. Scans codebase, counts APIs, integrations, and complexity. Shows what
• cost-latency-optimization-deskoptimize AI system cost and latency using model routing, caching, prompt compression, context pruning, batchin
• cost-latency-optimizerReduces LLM costs and improves response times through caching, model selection, batching, and prompt optimizat
• cost-optimisationFind cloud spend that buys nothing: idle capacity, egress surprises, and the storage class nobody revisited.
• cost-optimizationGuides systematic cloud and infrastructure cost reduction. Use when cloud bills are growing unpredictably, whe
• cost-optimization-patternsCloud cost optimization, token/API cost tracking, build time optimization, and FinOps patterns
• cost-overrun-predictorAudit construction project management software for budget tracking accuracy, earned value management (EVM) for
• cost-reportProduce a scoped CCAM cost and token report by model, provider, source, and session. Use for spend reviews, mo
• cost-routingTop-level dispatcher that classifies every incoming request into scout / coder / architect tiers BEFORE any to
• cost-tier-routingUse BEFORE doing direct file search, bulk reads, data import/export, or routine coding edits in the main conve
• cost-trackerTrack session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spendi
• cost-watchdogFlag potentially expensive technical choices BEFORE they are committed — AI model selection, hosting tier upgr
• costanalysisBeton Kemon cost monitor. Two modes. `live`: pulls current usage from Vercel + Supabase via MCP / dashboards (
• costiash-docsRouter for the /docs command. Look up Claude documentation, ask plain-English questions, generate interactive
• couchbaseCouchbase distributed NoSQL database. Use for mobile and edge.
• couchdbCouchDB document database with sync. Use for offline-first apps.
• councilLaunches a multi-agent advisory board (Visionary, Critic, Pragmatist, Recorder) to deliberate on any topic thr
• council-implementExecute a Carmack Council plan task by task. Use when explicitly asked to implement a plan, do a "council impl
• council-planArchitect a feature with the Carmack Council before writing code. Use when explicitly asked to plan a feature,
• council-reviewPerform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review
• countbot-ai-agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating
• countbot-ai-cron-manager定时任务管理。创建、查看、修改、删除定时任务，管理任务会话数据。当用户需要设置提醒、定时执行任务、管理调度计划时使用。
• countbot-ai-skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to c
• countdown-videoThis skill should be used when the user asks to "make a countdown timer video", "create a countdown animation"
• counter-narrativeBuild a counter-narrative playbook responding to a competitor's positioning move — rebrand, category claim, ag
• counterargumentGenerates rigorous devil's advocate critiques from methodological, theoretical, and practical perspectives. Us
• counterexample-debuggerDebug proof failures using counterexamples from Nitpick (Isabelle) or QuickChick (Coq) to identify specificati
• counterexample-explainerExplain why counterexamples violate specifications by analyzing formal specifications (temporal logic, invaria
• counterexample-generatorGenerate concrete counterexamples when formal verification, assertions, or specifications fail. Use this skill
• counterexample-to-test-generatorAutomatically generates executable test cases from model checking counterexample traces. Translates abstract c
• counterparty-guardПроверка контрагента (юрлица/ИП) по ИНН перед сделкой, отгрузкой в долг или предоплатой. Двухскоростная: быстр
• counterparty-riskGuide counterparty credit risk measurement and management for OTC and securities trading, organized around thr
• coupang-collectCollect current public job postings from Coupang (쿠팡) careers. Use when the user wants to gather, scan, or mon
• coupling-analysisAnalyzes coupling between modules using the three-dimensional model (strength, distance, volatility) from "Bal
• courier-webhooksReceive and verify Courier outbound webhooks. Use when setting up Courier webhook handlers, debugging courier-
• course-canvasRoute Canvas LMS course operations through the course_hoanganhduc canvas agent: preflight, list assignments/me
• course-content-mapRefresh a safe, concise map of this GCI World 2026 workspace before deeper course, assignment, or dataset work
• course-correctRewind a bad chunk of work by capturing what was tried + learned to a summary file, then telling the user how
• course-creatorDesign full online courses — learning objectives, module outlines, lesson scripts, quizzes, and assessment rub
• course-dbRoute local course student-database operations through the course_hoanganhduc db agent: search, details, domai
• course-designerDesign complete online courses, workshops, and training programs. Produces course outlines, lesson plans, lear
• course-direction-advisorTurn user-provided source materials into market-fit course-topic decisions without exceeding the evidence boun
• course-google-classroomRoute Google Classroom operations through the course_hoanganhduc gclass agent: preflight, list courses/student
• course-material-creatorCreate custom educational materials including syllabi, lesson plans, assessments, reading lists, and learning
• course-outline-architectDesigns a paid online course structure backward from the student transformation - before/after states, one mod
• course-sales-pageWrites the long-form sales page for a paid online course - above-the-fold promise, PAS-to-proof-to-program-to-
• court-sms本技能应在用户收到法院短信（文书送达、立案通知、开庭提醒等）时使用，自动提取案号、当事人、下载链接，下载文书并归档到对应案件目录。
• coveThe first CLI and MCP server for Cove Data Protection - fleet-wide backup health, billing usage, and storage
• cover-letterGenerate a tailored, truthful cover letter from the user's resume, profile, and a specific job description. Dr
• cover-letter-generatorCreate personalized, compelling cover letters from resume and job description
• cover-letter-thcover letter ตามตำแหน่ง | สำหรับ นักศึกษา. Triggers when user says (Thai/EN): 'cover letter', 'จดหมายสมัครงาน
• cover-letter-writerWrite Korean job application cover letter drafts from a question, JD, resume.md, and optional company values i
• cover-lettersMethodology for evidence-based cover letters: an evidence bank mined from the candidate's real record, JD keyw
• cover-makerTurn cover metadata (title / creator / subtitle / medium) into an album, book, podcast, report, deck, or magaz
• cover-meSpawn a fresh-context senior peer (the supervisor subagent) to scrutinize in-flight work and catch it going of
• cover-xiaohongshuCodex 中的小红书封面设计与图片生成进化 Skill。唤醒词：小红书封面生成、小红书封面拆解。读取文章或结构化入参，通过目标提取、多路构图尝试、Judge 改进器和记忆更新，生成小红书封面提示词，或在 Codex 中
• coverage[UDS] 多維度分析測試覆蓋率並提供可執行的建議
• coverage-analysisProject-wide code coverage and CRAP (Change Risk Anti-Patterns) score analysis for .NET projects. Calculates C
• coverage-checkCount how many independent origins are behind news coverage of a claim, instead of counting URLs. Queries GDEL
• coverage-closureMeasure RTL simulation code coverage (statement / branch / condition) and iteratively close it toward an expli
• coverage-enhancerAnalyze existing test suites and source code to suggest additional unit tests that improve test coverage. Use
• coverage-gap-finderProduces a risk-ranked list of untested critical paths and branches from a real branch-coverage report crossed
• coverage-gateCheck endpoint_map.md coverage at Phase 1→2 transition. Blocks Phase 2 if below 80%. Matches "coverage check",
• coverage-initInitialize the coverage backfill in a .NET repo. Use when setting up dotnet-coverage-kit in a new service for
• coverage-issue-spotterUse when issue-spotting insurance coverage questions from a policy, claim facts, tender, pleadings, and corres
• coverage-position-outlineUse when assembling a draft coverage-position outline from supplied policy and claim materials for a coverage
• coverage-redoRe-audit and reconcile a repo that was already onboarded with an OLDER version of this kit, and apply every ki
• coverage-reportProduce the latest deterministic C0/C1 coverage report for a .NET service. Use when the user asks for a 'cover
• coverletUse the open-source free `coverlet` toolchain for .NET code coverage. Use when a repo needs line and branch co
• coworkDesigns safe, source-grounded Cowork workflows with folders, connectors, skills, schedules, approval gates, an
• cowork-calendar-defragAudit your calendar with Cowork's calendar tools -- measure meeting load and fragmentation, identify which rec
• cowork-contract-renewal-radarSweep a contracts folder and extract every renewal date, auto-renew clause, notice window, and price-escalatio
• cowork-data-room-builderPrepare YOUR data room for a fundraise, acquisition, or bank diligence -- builds the checklist for your deal s
• cowork-deal-roomUses Cowork-style multi-step analysis to process deal room documents -- contracts, financials, org charts. Out
• cowork-expense-auditCowork-style sweep of a folder of receipts, statements, and expense exports -- categorizes every transaction,
• cowork-folder-organizerCowork-style cleanup of a messy folder or shared drive -- classifies every file, proposes a target structure,
• cowork-fundamentalsReference guide to Anthropic's Cowork mode: what makes it different from turn-by-turn chat and from agentic co
• cowork-health-checkAudits your Cowork setup across five categories, scores each one, and gives you a prioritized improvement plan
• cowork-hiring-screenerPoint Cowork at a folder of resumes plus a job description -- screens every candidate against the actual requi
• cowork-home-inventoryBuild an insurance-grade home inventory from a folder of photos and receipts -- identifies items, pulls values
• cowork-inbox-triageDaily inbox triage using Cowork's email write tools (Microsoft 365 or Gmail) -- classifies unread mail, drafts
• cowork-invoice-chaserPoint Cowork at your invoices and payments records -- builds an AR aging report, drafts escalating follow-up e
• cowork-medical-bill-auditorPoint Cowork at a folder of medical bills and insurance EOBs -- matches every bill to its explanation of benef
• cowork-plugin-auditAudit active Cowork plugins and get a keep/disable table. Reduces token usage and cognitive noise. Use when re
• cowork-prompt-generatorGenerates optimized prompts for Claude Cowork (Anthropic's autonomous file-based agent mode). Use whenever the
• cowork-qbr-builderBuild a quarterly business review from a client folder -- reports, usage exports, support tickets, meeting not
• cowork-rfp-responseTurn an RFP and a folder of your past proposals, case studies, and capability docs into a requirement-by-requi
• cowork-session-plannerGenerate a pre-session brief for Cowork: current status, session goal, and prioritised work plan from local pr
• cowork-setupOne-shot setup that wires Digital Marketing Pro for team use in Anthropic Cowork — verifies the sandbox via pl
• cowork-setup-wizardA 15-minute guided setup that teaches Cowork who you are, how you work,
• cowork-sop-writerTurn a process walkthrough -- meeting transcript, screen-recording transcript, rough notes, or a folder of sca
• cowork-tax-prep-organizerSweep your folders and downloads for tax documents and build a CPA-ready package -- checklist by form type, ev
• cowork-vendor-comparisonDrop a folder of vendor quotes, proposals, and SOWs on Cowork -- normalizes them into one comparison matrix, c
• cowork-vs-chat-demoSee the difference between Chat and Cowork with a live side-by-side comparison for understanding why Cowork is
• cozempic-doctorRun health checks on Claude Code configuration and sessions. Use when troubleshooting Claude Code issues. (coz
• cozy-wholesome-moodCozy, cute, wholesome, relaxing, and peaceful mood direction for Blender assets and scenes.
• cpLocal verify-commit-push wrapper for Codex. Use only when the user explicitly says `/cp` or clearly asks to fi
• cp-skill-connectDiscover connections for a single artifact. Writes a connect-report under kb/reports/connect/<collection>/ wit
• cp-skill-convertConvert notes between types. Currently supports text to note by adding unverified structured frontmatter, rena
• cp-skill-health-checkDiagnose Commonplace project layout, promoted-skill discovery, user-level uv tool installation, command PATH o
• cp-skill-ingestUse when asked to ingest a URL or existing kb/sources snapshot into a .ingest.md source analysis.
• cp-skill-revise-autoreasonExperimentally revise a note with fresh critic, author, synthesizer, and blind-judge agents while retaining th
• cp-skill-revise-iterativeExplicit-invocation instruction for iteratively revising a note for flow and cohesion while retaining numbered
• cp-skill-snapshot-webSnapshot a URL into kb/sources/, routing GitHub, X/Twitter, PDF, and ordinary web sources to the appropriate c
• cp-skill-validateRun deterministic validation on KB artifacts, collections, collection landings, and the published redirect map
• cp-skill-writeWrite one KB note whose intended contribution is already determined, under its collection and type contracts;
• cp-skill-write-multistageWrite or substantially rebuild one consequential KB artifact through a source-first, multi-stage workshop befo
• cpa-optimizationCpa Optimization — Skill especializada para cpa optimization
• cpo-advisorProduct leadership for scaling companies. Product vision, portfolio strategy, product-market fit, and product
• cpo-eligibilityUse to check Certified Pre-Owned eligibility, coverage, and embedded value for a specific vehicle (VIN/year/mi
• cpo-reviewerReviews a proposal, business case, deck or product plan in character as a Chief Product Officer archetype, the
• cppDesign, implement, and review modern C++ APIs and native implementation code. Use when working on .cpp, .hpp,
• cpp-build-systemsUse in C/C++ projects for build configure/errors, compile_commands.json generation, or selecting CMake/Meson/M
• cpp-coding-standardsC++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refa
• cpp-debuggingUse when a C++ failure involves memory lifetime, undefined behavior, native crashes, or debugger-only state —
• cpp-formattingUse in C/C++ projects for clang-format. Changed-lines-only; never reformat unchanged code mid-feature. .clang-
• cpp-proWrites, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and h
• cpp-sanitizersUse in C/C++ projects for crashes, hangs, UB, data races, memory errors. ASan/UBSan/TSan runtime checks. Build
• cpp-static-analysisUse in C/C++ projects when reviewing changes or hunting bugs. Runs clang-tidy/cppcheck/IWYU. Needs compile_com
• cpp-systemsModern C++ patterns: RAII and ownership, rule of zero/five, exceptions and error handling, API and ABI boundar
• cpp-testingUse only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tes
• cpp-to-dafny-translatorTranslate C/C++ programs to equivalent Dafny code while preserving semantics and ensuring verification. Use wh
• cpr-letter-drafter-andrew-birdWrites the formal letter you send before suing someone in a civil case in England & Wales — the Letter Before
• cps-rca-central-african-republic-jeanne-sulzerMéthodologie « verification-first » pour la Cour Pénale Spéciale de Centrafrique (cour hybride, siège à Bangui
• cpu-gpu-performanceEstablishes CPU/GPU baselines before resource-intensive operations. Use before builds, training runs, or any t
• cpu-info-collectorSimple tool for project management tasks.
• cpu-memory-tuning-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• cqrsCQRS command query responsibility segregation. Use for complex domains.
• cqrs-designSeparate command (write) and query (read) models for complex domains. Use when read/write patterns diverge sig
• cqrs-event-sourcingCQRS and Event Sourcing patterns for scalable, auditable systems with separated read/write models. Use when bu
• cqrs-implementationImplement Command Query Responsibility Segregation for scalable architectures. Use when separating read and wr
• cr-ation-de-fiches-d-valuation-et-questionnaires-en-bureautiqueGénère des modèles structurés pour l'évaluation des compétences bureautiques, incluant la fiche d'évaluation p
• cr-er-une-cl-active-setup-pour-d-sactiver-une-t-che-planifi-e-via-powershell-directGénère un script PowerShell créant une clé de registre Active Setup qui exécute directement une commande Power
• cra-anwendungsbereichPrüfung, ob ein Produkt in den Anwendungsbereich des Cyber Resilience Act fällt – Produkt mit digitalen Elemen
• cra-meldepflichtenSteuerung der CRA-Meldepflichten nach Art. 14 VO (EU) 2024/2847 ab dem 11.09.2026 – Abgrenzung aktiv ausgenutz
• cra-produktanforderungenBestimmung der grundlegenden Cybersicherheitsanforderungen nach Anhang I VO (EU) 2024/2847 – Sicherheitseigens
• cra-schwachstellenmanagementAufbau und Prüfung des Schwachstellenmanagements nach Anhang I Teil II VO (EU) 2024/2847 – Politik zur koordin
• cra-vulnerability-obligationsUse when a user asks what the EU Cyber Resilience Act (CRA) means for their product, whether and when they mus
• crabboxDetect and use Crabbox for repository tests and validation on remote runners. Use when crabbox.yaml or .crabbo
• crabbox-setupScaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe coun
• craftOne-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → t
• craft-and-distinctivenessDesign quality bar for any UI build — website, dashboard, mobile, or watch. Use whenever generating, reviewing
• craft-cloudCraft Cloud — Pixel & Tonic's serverless hosting platform for Craft CMS. Covers craft-cloud.yaml configuration
• craft-content-modelingCraft CMS 5 content modeling — sections, entry types, fields, Matrix, relations, project config, and content a
• craft-critiqueCritique and review the way Dinesh does — for any design, prototype, copy, case study, or claim. Load when rev
• craft-design-system-and-figma-architectureBuilds, audits, extends, fixes, and migrates design systems and Figma architectures at any product lifecycle s
• craft-design-system-coachGuided, one-question-at-a-time coaching for scoping, structuring, and operating a design system — use this whe
• craft-diorama-still-life把文章、观点或产品主张编译成「一个实物替一句判断」的手作拟物静物提示词——剪纸质感、微缩场景、轻拟物、克制静物摄影感。用户提到拟物风封面、拟物风章节图、剪纸质感、微缩静物、实物隐喻配图、craft diorama、cut
• craft-garnishGarnish — Craft CMS's built-in JavaScript UI toolkit for the control panel. ALWAYS load when writing, editing,
• craft-goalCompile or lint a persistent Mayor-style
• craft-goal-driven-promptsTransform a user's objective into a detailed, ready-to-run agent prompt built around the goal, context, non-ne
• craft-motionDesigns and implements UI motion the way Dinesh ships it — choreography, stagger math, state feedback, and wor
• craft-my-business-planGuides you step-by-step to a rigorous, honest business plan for any idea — vending machine, SaaS, podcast, age
• craft-pestTesting Craft CMS 5 plugins and modules with Pest — test isolation, database safety, and the markhuot/craft-pe
• craft-php-guidelinesCraft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing
• craft-plugin-releaseReleasing Craft CMS plugins — tagging, Packagist propagation, GitHub releases, branch promotion, shared-librar
• craft-pluginsIndex and router for plugin-specific Craft CMS 5 guidance — configuration, Twig API, PHP API, migrations, depl
• craft-project-setupScaffold Claude Code configuration specifically for Craft CMS projects. Generates CLAUDE.md and .claude/rules/
• craft-roles-founding-designerA structured thinking framework for a founding senior designer at a startup operating at the intersection of c
• craft-siteCraft CMS 5 front-end Twig development — atomic design, template architecture, components, Vite buildchain. Co
• craft-software-spec-architectTurns any rough software idea, or a process you just built and want to keep as an app, into a functional spec
• craft-styleBuilds a personal output style on hush's frame — the user's voice on the surface, hush's silence-and-structure
• craft-tufte-data-visualizationApplies Edward Tufte's data-visualization canon — data-ink ratio, chartjunk elimination, graphical integrity a
• craft-twig-guidelinesTwig coding standards and conventions for Craft CMS 5 templates. ALWAYS load this skill when writing, editing,
• craft-ui-design-cross-devicesActs as a veteran visual/UI designer (decades of experience, from feature-phone/BlackBerry-era interfaces thro
• craft-ui-design-generalDesigns production-grade graphical interfaces for any platform — web, iOS, Android, macOS, Vision Pro, respons
• craft-ui-skillsCraft's UI design system. Use when building interfaces inspired by Craft's aesthetic - light mode, Inter font,
• craft-your-textbook让你具备"亲手为自己造一本教材"的能力——把源材料（教材/考纲/讲义等）加工成 AI 苏格拉底老师能拿去上课的教学蓝本（pure-blueprint），或一本给人读的流畅教材（human-readable，AI 也能直接
• craftcmsCraft CMS 5 plugin and module development — extending Craft with PHP. Covers elements, element queries, servic
• crafted-web把文章、数据或素材制作成单个自包含、零外部依赖、双击即开的精致 HTML 成品，适用于动效长文、仪表盘、数据故事、对比页、时间线和分步图解。当用户明确要求单文件 HTML、可离线打开或嵌入文档平台时使用。不用于需要部署的
• crafting-effective-readmesUse when writing or improving README files. Not all READMEs are the same — provides templates and guidance mat
• crafting-instructionsGenerate optimized instructions for Claude (Project instructions, Skills, or standalone prompts). Use when use
• cran-extrachecksPrepare R packages for CRAN submission by checking for common ad-hoc requirements not caught by devtools::chec
• crane-operatorCertified crane operator with 10+ years experience in tower cranes, mobile cranes, and overhead cranes. Specia
• crap-analysisAnalyze code coverage and CRAP (Change Risk Anti-Patterns) scores to identify high-risk code. Use OpenCover fo
• crap-scoreCalculates targeted CRAP (Change Risk Anti-Patterns) scores for a named .NET method, class, or single source f
• crash-courseExpert tutor that gets you from zero to working knowledge on any TOPIC fast, grounded in real sources rather t
• crashlyticsGenerate crash reports from Firebase Crashlytics with automated fix proposals, severity scoring, and developer
• crashoutCALL THIS whenever frustration spikes: user contradicts themselves, approved work gets reverted, you're overru
• crawl-apisScan a target codebase for API definitions (OpenAPI, REST routes, GraphQL schemas) and propose api_contract an
• crawl-budget-manipulationDüşük rekabetli long-tail anahtar kelimelerde hızlı index ve ilk sayfa sıralaması elde etmek için crawl budget
• crawl-dataScan a target codebase for data model definitions (SQL schemas, ORM models, TypeScript interfaces, Pydantic mo
• crawl-websites-at-scaleScrape websites at scale using Scrapy, a Python web crawling and scraping framework. Use when: (1) Crawling mu
• crawl4aiUse when working with unclecode/crawl4ai or the local Crawl4AI stack: installing, updating, setting up, diagno
• crc-checksum-integrationUse when implementing, verifying, or debugging CRC, checksum, hash-lite integrity checks, polynomial parameter
• cre-underwritingGenerate an institutional-grade commercial real estate underwriting model — input schema (T-12 income, T-3 tra
• crear-historias-de-usuarioAterriza UNA única historia de usuario en su definición completa y lista para que un equipo de desarrollo la p
• crear-lean-canvasGuía paso a paso, en modo conversación, para construir un Lean Canvas (el modelo de negocio de Ash Maurya) rel
• crear-spec-sddConvierte una idea de feature en un spec.md completo, listo para SDD (Spec-Driven Development). Sigue el están
• crear-y-revisar-okrsAsistente de OKRs (Objetivos y Resultados Clave) con el método probado de Javier Garzás. Ayuda de tres formas
• createPlan, implement, and test a new feature or change with pre-implementation review
• create-2d-compositionCompose 2D graphics programmatically using SVG generation, diagram layout algorithms, image compositing, and b
• create-3d-sceneSet up a Blender scene programmatically via Python (bpy) with objects, materials, lighting, camera, and enviro
• create-a-custom-mcpGuide for registering a new custom MCP server (mcp.json) — covers local vs remote transport, config fields, se
• create-a-modeGuide for creating a new custom Bob mode (custom_modes.yaml) — covers the schema, permission groups, roleDefin
• create-a-skillGuide for creating a new Bob skill (SKILL.md) — covers the frontmatter schema, name rules, file location, and
• create-adrRecord an Architecture Decision Record (ADR) — a 1–3 sentence note capturing what was decided and why. Use whe
• create-agentCreate a new agent definition file following the agent-almanac agent template and registry conventions. Covers
• create-agent-skillsExpert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.
• create-agent-specialistConstruye subagentes especialistas para Claude Code. Genera archivos agent-name.md para un agente especialista