Browse the registry

Every entry, alphabetically — 67,843 in total. Page 192 of 272.

• mk-backend-developmentDesign and implement backend service changes: API contracts, service boundaries, auth integration, reliability
• mk-benchmarkExperimental/manual harness canary procedure. It records benchmark manifests and scores but does not provide a
• mk-bootstrap|
• mk-brainstormingGenerate or compare multiple technical approaches for one validated decision. Do not use for product discovery
• mk-build-fixBuild error triage: detect language, load fix patterns, auto-retry. Use for ''build failed'', ''fix compilatio
• mk-careful|
• mk-chomUse when copy-catting, replicating, or adapting features from external systems, repos, apps, or ideas into the
• mk-chrome-profileTarget a specific Google Chrome user profile for browser automation via CDP. Discovers installed profiles from
• mk-clean-codeEnforces KISS/DRY/YAGNI during authoring and ad-hoc quality reviews. Pragmatic standards: concise, direct, no
• mk-confluenceRouting skill — recommends the correct mk:confluence-* leaf for any Confluence Cloud task. Triggers: ''conflue
• mk-confluence-bulkBulk Confluence operations on 10+ pages via the confluence-as wrapper: bulk-label / bulk-move / bulk-delete. D
• mk-confluence-collaborateManage Confluence collaboration surface via the confluence-as wrapper: comments, attachments, labels, watchers
• mk-confluence-pageConfluence page CRUD via the confluence-as wrapper. Triggers: ''create page in SPACE'', ''show me page 12345''
• mk-confluence-searchConfluence CQL search + space list + saved-filter + export via the confluence-as wrapper. Triggers: ''search c
• mk-confluence-spec-analystDeep spec analysis on a Confluence page. Reads page (+ children) via the confluence-as wrapper, produces a str
• mk-context-audit|
• mk-context-engineering>-
• mk-cookOrchestrates single-task implementation pipeline: plan → test → build → review. Shipping is an explicit follow
• mk-cso|
• mk-databaseDesign and safely evolve data models, database schemas, migrations, queries, indexes, and ORM data-access boun
• mk-decision-frameworkOperational decision frameworks: triage, escalation, case management, billing ops. Use for ''how to handle X c
• mk-developmentUse when implementing features or writing code. TDD enforcement is opt-in via --tdd / MEOWKIT_TDD=1. Provides
• mk-devopsPlan and implement infrastructure, containers, CI/CD, deployment safety, observability, and rollback changes.
• mk-docs-finderRetrieve up-to-date library, framework, and project documentation using scripts + MCP tools (Context7, Context
• mk-docs-init|
• mk-document-release|
• mk-elicitStructured second-pass reasoning after code review or plan evaluation. Offers named reasoning methods (pre-mor
• mk-evaluateExperimental behavioral evaluator. Drives a running artifact via browser/curl/CLI and records rubric evidence;
• mk-figmaRead-first Figma gateway via Figma MCP: analyze designs, implement Figma-to-code for 1–3 screens, extract desi
• mk-fixDiagnoses and fixes bugs, type errors, lint failures, CI/CD issues, and runtime errors via root-cause-first in
• mk-freeze|
• mk-frontend-designUse when designing UI components, reviewing visual design, building design systems, or checking accessibility.
• mk-ghpmGitHub project management via the gh CLI — create and triage issues, manage GitHub Projects v2 boards (add ite
• mk-grill|
• mk-helpWorkflow navigation assistant. Scans project state (plans, reviews, tests, git) and recommends the next step i
• mk-henshinUse when transforming existing code into agent-consumable surfaces — CLI (npm-publishable), MCP server (stdio/
• mk-html-videoRender an HTML/CSS/JS template to a local MP4 video by capturing frames with headless Chromium (via Playwright
• mk-improve-codebase-architecture|
• mk-intakeTicket/PRD intake: product area classification, completeness scoring, RCA, technical assessment. Works with Ji
• mk-investigate|
• mk-jiraRouting skill — recommends the correct mk:jira-* leaf for any Jira task. Triggers: ''jira'', ''jira ticket'',
• mk-jira-adminJIRA project / user / group / scheme / automation administration via the jira-as wrapper (11 sub-domains, ~65
• mk-jira-agileJIRA agile via the jira-as wrapper: epics, sprints, backlog, ranking, story points, subtasks, velocity. Trigge
• mk-jira-analystFull Jira ticket context analysis via the jira-analyst agent — including media (attached images / PDFs / scree
• mk-jira-bulkBulk JIRA operations on 10+ issues via the jira-as wrapper: bulk transition / assign / set-priority / clone /
• mk-jira-collaborateManage JIRA collaboration surface via the jira-as wrapper: comments, attachments, watchers, notify. Triggers:
• mk-jira-devGenerate developer artifacts from Jira tickets via the jira-as wrapper: branch names, PR descriptions, parsed
• mk-jira-estimatorHeuristic story-point estimation for a single Jira ticket via the jira-estimator agent. Read-only. Triggers: '
• mk-jira-evaluatorEvaluate Jira ticket complexity + inconsistencies via the jira-evaluator agent. Read-only. Triggers: ''evaluat
• mk-jira-fieldsJIRA custom field discovery + configuration via the jira-as wrapper. Triggers: ''field ID for X'', ''list cust
• mk-jira-issueJIRA issue CRUD via the jira-as wrapper. Triggers: ''create bug/task/story'', ''show me PROJ-123'', ''get/view
• mk-jira-jsmJIRA Service Management via the jira-as wrapper: service desks, request types, requests, customers, organizati
• mk-jira-lifecycleDrive JIRA workflow lifecycle via the jira-as wrapper: transition, assign, resolve, reopen, manage versions an
• mk-jira-opsJIRA-side cache + project-context discovery via the jira-as wrapper. Triggers: ''jira cache status'', ''clear
• mk-jira-relationshipsManage JIRA issue relationships via the jira-as wrapper: link, unlink, blockers, dependencies, clone, bulk-lin
• mk-jira-searchJIRA search + filter management via the jira-as wrapper. Triggers: ''search jira'', ''find issues where X'', '
• mk-jira-timeJIRA time tracking via the jira-as wrapper: log work, list/update/delete worklogs, set estimates, generate rep
• mk-lazy-agent-loaderDeprecated compatibility shim. Agent routing reads the canonical inventory under .claude/agents/ directly; do
• mk-lint-and-validateAutomatic quality control, linting, and static analysis after code modifications. Triggers on: lint, format, c
• mk-llmsGenerate llms.txt files from project documentation following the llmstxt.org spec. Use when asked to create AI
• mk-loopUse when autonomously improving a measurable scalar metric through bounded, git-tracked iterations: modify one
• mk-markdown-reader|
• mk-memoryJSON-canonical session memory. Use when capturing session learnings, extracting patterns, or tracking costs —
• mk-mermaidjs-v11Create inline Mermaid v11 diagram blocks — flowcharts, sequence, class, ER, Gantt, state, timeline, user-journ
• mk-multimodalProcess images, video, audio, PDFs with Gemini API. Generate images (Nano Banana 2), videos (Veo 3), speech (M
• mk-nyquistTest-to-requirement coverage mapping. Reads plan acceptance criteria and test files, produces a coverage gap r
• mk-office-hours|
• mk-orchestrateCoordinates staged or parallel jobs across live-verified coding-agent runtimes (Claude Code, Codex, Cursor, an
• mk-packPack an EXTERNAL repository into a single AI-friendly file (markdown/xml/json). Use for third-party library an
• mk-partyMulti-agent collaboration session. Brings 2-4 agent perspectives into one discussion for architecture decision
• mk-plan-ceo-review|
• mk-plan-creatorCreates structured multi-file implementation plans before build. Scope-aware: trivial tasks exit early, simple
• mk-planning-engineAnalyzes ticket complexity and maps dependencies against an existing codebase before sprint planning. Triggers
• mk-playwright-cliSession-persistent browser automation via Playwright CLI — form filling, screenshots, data extraction, multi-s
• mk-preview|
• mk-problem-solving|
• mk-project-contextGenerate or update docs/project-context.md — the single source of truth for project conventions, tech stack, a
• mk-project-organizationUse when creating files and need the correct path, organizing project layout, or enforcing naming conventions.
• mk-prompt-enhancerUse when refining a draft user prompt before sending it to a coding agent. Decomposes goal/context/constraints
• mk-qa|
• mk-qa-manualSpec-driven manual QA testing and Playwright E2E code generation. Orchestrates browser skills to navigate apps
• mk-react-patterns|
• mk-research|
• mk-resolving-merge-conflicts|
• mk-respond-prTriage reviewer comments on a GitHub PR with receiving-code-review discipline — verify each against the codeba
• mk-retro|
• mk-review|
• mk-review-prReviews a GitHub PR with a single shallow correctness/security/breaking/AI-slop checklist and emits a verdict;
• mk-rubricUse when loading, listing, composing, or validating graded evaluation rubrics — PASS/WARN/FAIL grading with we
• mk-scale-routingDomain-aware complexity routing. Scans task description for domain keywords, matches against domain-complexity
• mk-scoutFast parallel codebase scouting. Spawns multiple Explore subagents to search directories simultaneously, retur
• mk-sequential-thinking|
• mk-session-continuationPersists and restores mid-session workflow progress across context resets. Use when resuming workflows, saving
• mklab-se-releaseRelease a new version: bump version, update docs, commit, push, and tag
• mkopo-mcp💳 mkopo-mcp — Alternative Credit Scoring MCP Server
• mksglu/context-modeContext window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms
• mlMachine learning and LLM engineering judgment, distilled from a stronger model - invoke when DECIDING whether/
• ml-autoresearch>
• ml-classification-pipeline>-
• ml-contentGenerate publication-grade ML explainer videos and carousels the way 3Blue1Brown actually builds them — in rea
• ml-data-pipeline-architecturePatterns for efficient ML data pipelines using Polars, Arrow, and ClickHouse. TRIGGERS - data pipeline, polars
• ml-debugDebug ML issues systematically -- tensor shapes, NaN propagation, gradient flow, device mismatches, dtype erro
• ml-engineerUse when building ML pipelines, training models, evaluating LLMs, setting up RAG systems, or designing model d
• ml-engineering>-
• ml-experiment-trackerPlan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model traini
• ml-experimentsML experiment workflow from problem formulation through reproducible handoff. Use for model experiments, metri
• ml-failfast-validationPOC validation patterns to catch issues before committing to long-running ML experiments. TRIGGERS - fail-fast
• ml-leakage-checkUse when reviewing ML preprocessing or feature pipelines for target leakage -- validation metrics look suspici
• ml-model-eval-benchmarkCompare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboa
• ml-ops-engineer>
• ml-paper-writingWrite publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOS
• ml-pipelineUse when building or operating a machine learning pipeline. Covers feature engineering, training reproducibili
• ml-pipeline-creationDesign, implement, and validate reproducible machine-learning pipelines spanning data preparation, training, e
• ml-pipeline-reportUse when checking ML pipeline health, Metaflow flow status, failed runs, or generating an ML pipeline report.
• ml-problem-definitionValidate whether ML is the right solution before building the model — so you don't spend months on a predictio
• ml-product-analysis>
• ml-research-labMachine-learning research loop for dataset curation, fine-tuning, evaluation, inference deployment, experiment
• ml-securityThe model and data artifacts: checkpoint formats that execute code on load, provenance for a model you did not
• ml-trainingMachine learning model training with HuggingFace. Fine-tuning LLMs, dataset creation, GPU selection, training
• ml-training-recipes🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
• mlai-textbooksA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.tx
• mlb-pick-analysisStructured MLB pick analysis with three-tier framework, suspicious-edge audit, correlation matrix sizing, line
• mlb-situational-systemsOskeim-style situational systems analysis for an individual MLB pick — looks up historical performance of team
• mle-workflowProduction machine-learning engineering workflow for data contracts, reproducible training, model evaluation,
• mlflowMLflow ML lifecycle management. Use for ML experiment tracking.
• mlflow-pythonMLflow experiment tracking via Python API. TRIGGERS - MLflow metrics, log backtest, experiment tracking, searc
• mllm-eval>
• mlnetUse ML.NET to train, evaluate, or integrate machine-learning models into .NET applications with realistic data
• mlops-and-deploymentMLOps and the production ML lifecycle -- model packaging and serving, CI/CD for ML, experiment tracking, model
• mlops-automationAutomate an MLOps project with mise tasks, lefthook hooks, Docker images, GitHub Actions, and MLflow tracking
• mlops-collaborationPrepare a project for public collaboration — license, code of conduct, docs, branch rulesets, templates, and g
• mlops-engineerElite MLOps Engineer skill with expertise in ML pipeline automation, model versioning (MLflow, DVC), experimen
• mlops-industrializationConvert notebook prototypes into a distributable Python package with a src layout, a domain/io/application spl
• mlops-initializationInitialize a production-ready Python MLOps project with uv, git, mise, and a shared editor setup. Use when sta
• mlops-observabilityMake an ML system a glass box with reproducible runs, MLflow dataset lineage, drift monitoring, alerting, and
• mlops-prototypingStructure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free
• mlops-validationAdd the validation layers that gate a merge — ty typing, Ruff linting, pytest coverage, structured logging, an
• mlxRunning and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, convertin
• mlx-memoMemory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
• mmДиспетчер mm-системы — короткая команда вместо длинных. /mm без аргументов = список всех команд. /mm new = ini
• mm-bridgeCompose a ready-to-copy prompt for the user's OTHER Claude Code instance (running in PowerShell). Use when the
• mm-clear-gateГейт перед /clear — read-only проверка «всё ли записано», вердикт из exit code скрипта, а не из реплики модели
• mm-doctorСамопроверка mm-системы — junction'ы, конфиг, vault, паспорта, bridge-архив, GSD-консистентность (passport vs
• mm-focusСНЯТ 2026-08-02 — команда больше ничего не грузит. Её детекция этапа дублировала /gsd-resume-work и расходилас
• mm-handoffГенерирует handoff.md — компактную сводку для нового чата claude.ai когда контекст текущего заполнился. Включа
• mm-init-projectИнициализирует или обновляет проект для mm-системы — создаёт passport.md в корне, копию в Obsidian, dashboard.
• mm-instructionsГенерирует текст для claude.ai → Project → Instructions из шаблона + персонализирует под текущий проект. Кладё
• mm-projectsОбзор всех зарегистрированных mm-проектов одним экраном — статус, тип, GSD-фаза, последняя активность, число о
• mm-resumeВосстановить контекст в начале сессии или после /clear. Читает passport.md + dashboard + последнюю сессию + gi
• mm-save-sessionЗакрывает текущую Claude Code сессию — сохраняет лог в Obsidian/Claude/Sessions/, обновляет project note, обно
• mm-setupОнбординг/персонализация mm-системы под конкретного пользователя — спрашивает имя, чем занимается, стек, язык,
• mm-updateСамообновление mm-системы из удалённого репозитория. mm раздаётся через git clone + register-skills (не npm),
• mm-vaultСоздаёт приватный vault-репозиторий памяти проекта в Obsidian и пушит его на GitHub для синхронизации с claude
• mm-web-bridgeПартнёр louise в claude.ai — обсуждает идеи, ставит их под сомнение, проверяет актуальность в интернете перед
• mmx-cli>
• mneme-mcp-serverVault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.
• mnemo-mcpPersistent AI memory with hybrid search (FTS5 + semantic) and cross-machine sync.
• mnmballa2323-pdfComprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting do
• moai-workflow-docs-claim-check>
• moat-analysis>
• moatazhamada-example-skillUse when you need a minimal example skill to copy or test the toolkit.
• mobbin-ui-skillsMobbin's UI design system. Use when building interfaces inspired by Mobbin's aesthetic - light mode, Inter fon
• mobil-ui-ux-rulesetDeprecated alias for the canonical `mobile-ruleset` mobile workspace rules.
• mobileReact Native and Expo mobile development. Navigation, native modules, platform-specific code, app store prepar
• mobile-adaptation|
• mobile-app|
• mobile-app-builderPlan, design, build, test, and publish mobile apps (iOS and Android) end-to-end, with Claude driving the imple
• mobile-app-designerUse when designing or refining Expo Go React Native screens in apps/mobile, with separate iOS and Android cons
• mobile-app-integratorUse when implementing new mobile features in apps/mobile or libs/* with Expo/React Native and the shared mobil
• mobile-app-launch-checklistA collection of custom skills that extend Claude's capabilities with specialized workflows, methods, and domai
• mobile-app-product-ownerUse when planning mobile app features, roadmaps, or research-backed product decisions for apps/mobile.
• mobile-app-reviewerUse when reviewing apps/mobile or libs/* for mobile performance, security, storage, network, permissions, or r
• mobile-application-securityAndroid and iOS application security testing — static and dynamic analysis, APK/IPA inspection, OWASP MASVS/MA
• mobile-architectUse when building iOS/Android/Flutter/React Native apps, implementing offline sync, optimizing mobile performa
• mobile-cicd>-
• mobile-debuggingRemote JavaScript console access and debugging on mobile devices. Use when debugging web pages on phones/table
• mobile-designMobile app design patterns for iOS and Android. Native navigation, touch targets, platform conventions, safe a
• mobile-design-systemComprehensive mobile UI/UX design system covering React Native components, touch interactions, gesture pattern
• mobile-developmentMobile development patterns for React Native and Flutter including navigation, state management, and responsiv
• mobile-engineerMobile Engineer — Mobile-First Architecture & Offline-First Patterns
• mobile-experience-reportUse when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site brok
• mobile-iot-device-security当目标为Android/iOS APP、微信/支付宝小程序、IoT设备/固件，或需要ADB调试、抓包突破、so层逆向、WebView/DeepLink/本地存储安全测试时调用。负责协议分析、导出组件、WebView漏洞、
• mobile-language-checkerUse when validating language preferences, locale resolution, onboarding localization, or in-app language setti
• mobile-next/mobile-a2aAgent2Agent Server for Mobile Automation and Scraping
• mobile-onboarding|
• mobile-principlesMobile-specific UX principles - touch targets, hover-less doctrine, thumb zones, safe areas, gestures, mobile
• mobile-responsive>
• mobile-responsive-qaRun mobile responsive QA for websites and apps. Use after layout, media, navigation, form, pricing, dashboard,
• mobile-rulesetShared mobile workspace rules for apps/mobile and libs/* in lenserfight. Use when navigating native UI boundar
• mobile-securityAndroid and iOS hardening on a device you do not control: hardware-backed credential storage, exported compone
• mobile-store-upload-cliManual CLI workflows for uploading iOS builds to TestFlight and Android builds to Google Play. Use when you ne
• mobile-testing>-
• mobile-touchUse when designing iOS/Android gestures, haptic feedback, touch interactions, or native mobile animations.
• mobile-ui-replicator把手机 UI 截图复刻成可交互 HTML 的 Claude Code skill · A Claude Code skill that replicates mobile UI screenshots into inte
• mobile-ui-reviewerA curated open-source library of reusable SKILL.md files for Claude. Learn, use, and build powerful AI skills
• mobile-web-planner사용자가 모바일 웹/앱의 기획서 / 화면설계서 / 스토리보드(storyboard) / 와이어프레임(wireframe) / IA / 화면기획을 요청할 때 도메인 불문(쇼핑, 커뮤니티, 예약, 뉴스,
• mobilia-apiIntegration with Mobilia Public API — a RESTful CRM for real estate agencies. Use when working with Mobilia's
• mochi-questPersonal growth coaching skill. Activate when the user mentions goals, progress, daily tasks, habit tracking,
• mock-engineMock Engine local development environment management. Use for starting/stopping mock services, loading test da
• mock-interviewerRun a realistic, pressure-tested mock interview for a specific role, one question at a time, with honest feedb
• mocking-stubbing>
• mocking-test-generatorGenerate unit tests with proper mocking for Python (unittest.mock/pytest) or Java (Mockito/JUnit) code. Use wh
• mockitoUse when generating mocks, stubbing methods, verifying interactions, capturing arguments, or choosing between
• mockplus-context|
• mocktailUse when creating mocks, stubbing methods, verifying interactions, registering fallback values, or choosing be
• mockup-device-3diPhone + MacBook 仿 GLTF 静态展架, 屏幕内嵌真实 HTML 内容, 玻璃镜头折射, 360° 转盘构图
• mod-lisation-lagrangienne-de-syst-me-de-masses-ressortsModéliser et analyser une chaîne d'oscillateurs (masses reliées par des ressorts) en calculant les énergies, l
• moda.ai/remote-cameraCapture photos remotely from mobile devices via S3-backed upload URLs
• modalBuild serverless AI pipelines with Modal for cloud-based compute and inference
• modal-and-overlay-patternsOverlays — modals, drawers, bottom sheets, popovers — interrupt or augment the main flow. Each type has a diff
• modal-drawer-systemImplements accessible modals and drawers with focus trap, ESC to close, scroll lock, portal rendering, and ARI
• modal-research-computeUse when a research or engineering task needs automatic heavy-compute routing through the unified local broker
• modal-serverless-gpuServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrast
• modality-preserving-binary-offloadPersist binary output with a mime-derived extension and a matching saved-file message so downstream tools keep
• modalsPyWry is a cross-platform app factory, rendering engine and UI toolkit for Python that produces native desktop
• modals-dialogsUse when animating modals, dialogs, popovers, or overlay content to create smooth entrances and exits
• modeShow or set NeatContext routing to auto, ask, or manual for the current Codex thread, with an optional global
• mode-00-failsafe>
• mode-01-instruction-following>
• mode-02-tool-calling-accuracy>
• mode-03-long-context>
• mode-04-abstention>
• mode-05-citation-accuracy>
• mode-06-anti-sycophancy>
• mode-07-math>
• mode-08-prompt-injection>
• mode-classificationUse before routing a /meta-agent request to choose single-agent-creator, team-builder, or agentlas-packager fr
• mode-creative-vibe>
• mode-creatorInteractively create, install, activate, and verify custom claude-mem modes, including domain-specific observa
• mode-gated-reconcile-skip-filterInject mode-specific skip rules into a shared reconciler so unsupported source types are recorded and skipped
• mode-unhinged>
• modelThis skill should be used when the user asks about business models, unit economics, lean canvas, pricing math,
• model-bakeoffChoose a model with evidence by running the few prompts that actually matter across candidate models inside a
• model-bank-metadataBackfill and maintain model-bank metadata (knowledgeCutoff, family, generation). Use when adding models, fixin
• model-benchRun a 3-leg evaluation against a newly released LLM. Leg 1 is trap questions with deterministic answers, leg 2
• model-calibrationCalculating RMSE metrics and parameter calibration for lake model validation
• model-card>
• model-checkFind the model that is currently best for a capability by reading the provider live catalogue, and record it w
• model-claimSynthetic audit fixture for model-claim.
• model-comparatorUse this skill when comparing AI or LLM models on benchmarks, capability, cost, latency, context window, or ta
• model-compatibilityModel family compatibility matrix — loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibili
• model-context-protocolThe one and only MCP Server for dads jokes.
• model-councilMulti-agent debate system for complex queries. Four agents (Scholar, Logician, Contrarian, Captain) analyze in
• model-council-mcpConsult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.
• model-delegationInitiate the orchestrator-worker cost model for this session. The main-loop model (expensive, metered) orchest
• model-deploymentGenerates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpo
• model-domain-languageBuild the ONE shared name per concept — a ubiquitous language / domain model — used identically across client
• model-evaluationGenerates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom
• model-evaluation-reportingUse when writing or reviewing a model evaluation report -- accuracy is being quoted alone, or stakeholders nee
• model-forgePick the right model for a task and the right git strategy for the work. Use when about to dispatch a subagent