Browse the registry

Every entry, alphabetically — 67,843 in total. Page 105 of 272.

• find-ai-consultancyUse whenever the user wants to find, shortlist, vet, or enrich US AI/ML/data consulting firms (consultancies)
• find-ai-directoriesUse whenever the user wants to find, rank, or shortlist directories and listing sites where they can submit an
• find-anyone>-
• find-case-by-party-verify>
• find-cohort-gap>
• find-cpa-firmUse whenever the user wants to find, shortlist, vet, or enrich US accounting and tax firms (CPA firms) — finan
• find-customer-social-proofFind approved customer proof for campaigns, pages, decks, emails, and sales conversations. Use when a team nee
• find-cybersecurity-firmUse whenever the user wants to find, shortlist, vet, or enrich US cybersecurity firms — pen-testing/red team,
• find-dataFind a dataset for a Data2Story blog. Accepts a topic, a URL, or a DIP-style category. Downloads + validates a
• find-dead-codeFind dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tes
• find-design-agencyUse whenever the user wants to find, shortlist, vet, or enrich US design and creative agencies — graphic desig
• find-docs>-
• find-email-by-nameFind a professional email address given a person's name and company/domain. Use when asked to find someone's e
• find-engineering-firmUse whenever the user wants to find, shortlist, vet, or enrich US engineering firms — civil, structural, MEP,
• find-execRule matrix security fixture for find_exec used by security rule matrix integration tests; not intended for pr
• find-expired-domains>-
• find-exposed-servers>-
• find-hidden-subdomains>-
• find-hypertable-candidates|
• find-journalJournal recommendation engine for medical manuscripts. 2-pass matching against a curated public profile librar
• find-law-firmUse whenever the user wants to find, shortlist, vet, or enrich US B2B law firms — corporate, IP/patent, M&A an
• find-lead-account-ownerResolve the right account owner for a lead using contact, company, and deal ownership evidence.
• find-leaks-in-the-wild>-
• find-loopsHelps users discover and install agentic loops (recurring, scheduled AI agents) when they ask "find a loop for
• find-management-consultantUse whenever the user wants to find, shortlist, vet, or enrich US management consultancies — strategy, operati
• find-marketing-agencyUse whenever the user wants to find, shortlist, vet, or enrich US marketing agencies — including branding, con
• find-mcp-directoriesUse whenever the user wants to find, rank, or shortlist directories and registries where they can submit or li
• find-member-contribution>
• find-new-resourcesFind Japanese NLP GitHub repositories and Hugging Face models/datasets that are NOT yet in awesome-japanese-nl
• find-next-sui-ideaPick a Sui product idea from a curated corpus, or stress-test the user's own. Use when the user wants an idea,
• find-oepSmart trace-based OEP finder for packed/protected PE executables. Traces through packer stubs using intelligen
• find-plugins>
• find-pr-agencyUse whenever the user wants to find, shortlist, vet, or enrich US public-relations and communications agencies
• find-product-directoriesUse whenever the user wants to find, rank, or shortlist directories, listing sites, or launch platforms where
• find-qualified-titlesUse when finding real role-holders at known company domains from an ICP, especially prompts like 'find all job
• find-recruiting-firmUse whenever the user wants to find, shortlist, vet, or enrich US recruiting and staffing firms — executive se
• find-replaceModern find-and-replace using sd (simpler than sed) and batch replacement patterns. Triggers on: sd, find repl
• find-research-papers-mcpSearch open-source research papers across arXiv, OpenAlex, Crossref, PubMed, Semantic Scholar.
• find-seo-agencyUse whenever the user wants to find, shortlist, vet, or enrich US SEO agencies — technical SEO, on-page/off-pa
• find-service-providersUse whenever the user wants to find, shortlist, vet, enrich, or research US professional-services firms — law,
• find-skillSearch across all installed skills (user + plugin) by keyword to discover relevant skills whose descriptions m
• find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for
• find-skills-comboDiscover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two
• find-skills-jaDiscover and install agent skills from the open ecosystem (skills.sh), optimized for Japanese users. Use when
• find-skills-xAI驱动的skill发现工具。当用户问"怎么实现X"、"找个X的skill"、"有没有X功能的skill"时使用。
• find-software-developerUse whenever the user wants to find, shortlist, vet, or enrich US software development firms — custom software
• find-the-original-image>-
• find-unknownsタスク着手前に map (指示・context) と territory (実作業対象) の差 = unknowns を 4 象限で診断し、Blind Spot Pass と references 誘導を実行、解消できな
• find-untested-sources>
• find-unwrapped-stringsAudit a Lingui project for hardcoded user-facing strings that were never wrapped in macros. Use when asked to
• find-web-developerUse whenever the user wants to find, shortlist, vet, or enrich US web development firms — building, refreshing
• find-your-own-skillsDiscover and route a user's requested capability to the best matching installed Codex skill. Use when the user
• findableAutonomous SEO/GEO research and optimization skill — searches the web for best practices, applies safe improve
• findash-doctorUse when the user says "doctor", "finance doctor", "check finance setup", "what's missing", or any "is everyth
• finding-arbitrage-opportunitiesThis skill detects and analyzes arbitrage opportunities across cryptocurrency exchanges and DeFi protocols. It
• finding-dead-codeUse when reviewing code changes, auditing new features, or cleaning up. Triggers: 'find dead code', 'find unus
• finding-expensive-queries|
• finding-mentors-sponsorsBuild a Mentor & Sponsor Plan: target list, outreach scripts, meeting agenda, tracking cadence.
• finding-skillsDiscover and load skills on demand from /mnt/skills/user/. Use when you need a capability but don't know which
• finding-unknownsUse at the start of an ambiguous or unfamiliar task to surface the user's unknowns (unknown unknowns, unknown
• findme-mcpOfficial FindMe Photo MCP server. Lets photographers drive wedding gallery operations (create events, upload p
• findmyTrack Apple devices/AirTags via FindMy.app on macOS.
• fine-mapping-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• fine-tuningUse when considering fine-tuning a model. Covers when fine-tuning beats prompting or RAG, dataset construction
• fine-tuning-deskassess and plan fine tuning only when prompt, retrieval, tool, model routing, and eval evidence justify traini
• fine-tuning-expertUse when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke fo
• fine-tuning-ml-modelsPrepares and validates data for fine-tuning ML models (SFT/DPO/LoRA), with a real dataset quality checker test
• fine-tuning-openvla-oftFine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous act
• fine-tuning-planDesign and document a fine tuning plan with structured process, quality checks, and system integration
• fine-tuning-prep为 SFT 指令微调准备高质量数据集。当需要清洗、去重、构造指令-回复对、做训练/验证拆分、评估数据质量，为微调打基础时使用。
• fine-tuning-serving-openpiFine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends f
• fine-tuning-with-trlFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignmen
• finerx-mcpUS Rx price comparison + foreign-brand US-equivalent lookup. Observed prices, read-only.
• finetuningFine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with gra
• finetuning-techniqueSelects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against th
• finishMaster pipeline — compile, review, fix, and finalize any document. Auto-detects format and runs the full quali
• finish-branchWrap up a completed development branch by verifying tests pass, detecting the workspace state, then presenting
• finish-featureFinish a feature by merging changes back, cleaning up the copy, and creating a release. This is the high-level
• finish-phaseGraduate a completed exec-plan from active/ to completed/, synthesize an outcome section (results / pitfalls /
• finish-taskRun a project's quality gates, get user review, then commit — the end-of-task counterpart to new-task. Tech-st
• finish-the-loopClose implementation loops with target-bound independent evidence and a portable proof receipt. Use when an ag
• finishing-a-bones-leafAfter a bones swarm session closes, decide what to do with the open leaf — fan-in to trunk, keep open, or aban
• finishing-a-branchUse when implementation is complete and verified and the work needs to land, to choose how to integrate it. Wa
• finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides
• finishing-branchEnd-to-end workflow for finishing a development branch. Use when implementation is complete and the branch is
• finlight-mcpReal-time financial news for AI agents: search by ticker and source, with sentiment and entities.
• finn-tannlege-mcpNorwegian dental clinic directory MCP: ~6,900 clinics with Helfo-agreement, specialty, duty, chain.
• finnish-humanizerTunnistaa ja poistaa AI-generoidun suomenkielisen tekstin tunnusmerkit. Tekee tekstistä luonnollisempaa ja ihm
• finops-cloudwatchReview CloudWatch Logs retention and deletion-candidate findings.
• finops-engineerFinOps Engineer
• finops-mcpSee where your cloud and AI bills go, and spend less. Local-first, in your terminal or editor.
• fintech-agreement-drafting-stephane-boghossianAn end-to-end method for drafting and finalising a complex, multi-pillar regulated fintech agreement — from in
• fintech-bankingUse when designing animations for banking apps, payment systems, investment platforms, or financial dashboards
• fintech-inversionesActivar cuando el usuario describa una inversión, plataforma de crowdfunding, asesoría crediticia o de inversi
• fintel-data>
• finviz-screenerBuild and open FinViz screener URLs from natural language requests. Use when user wants to screen stocks, find
• firatcand-design>
• fire-analysis-cardAnalyze Chinese notes, articles, manuscripts, and digital card-box material with FIRE 2.0: Full-D numbering, I
• fire-card-to-epubConvert FIRE analysis cards, Chinese knowledge notes, or project-note JSON into validated EPUB books with dire
• firebaseProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• firebase-aiUse when setting up firebase_ai, generating text/chat with Gemini, streaming AI output, building multimodal pr
• firebase-ai-logicFirebase AI Logic (formerly Vertex AI in Firebase) 設定與整合指南。當用戶需要在 Flutter App 中使用 Gemini AI（語音解析、OCR 解析、AI 分類等
• firebase-analyticsUse when logging analytics events, setting user properties, configuring default event parameters, building fun
• firebase-apk-scannerScans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authenti
• firebase-app-checkUse when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling back
• firebase-appcheck-managerUse when managing Firebase App Check via CLI. Covers enabling the API, registering Android/iOS attestation pro
• firebase-authUse when setting up auth, managing auth state, implementing email/password or social sign-in, handling auth er
• firebase-auth-managerUse when managing Firebase Authentication sign-in providers, authorized domains, or auth configuration via CLI
• firebase-cliSafety-first Firebase CLI (firebase-tools v15) skill for full project control — deploy, Hosting (sites/channel
• firebase-cloud-firestoreUse when setting up Firestore, designing schemas, doing CRUD, creating listeners, paginating queries, configur
• firebase-cloud-functionsUse when calling callable functions (httpsCallable), passing data to server-side logic, handling function erro
• firebase-crashlyticsUse when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, c
• firebase-data-connectUse when setting up Data Connect, writing GraphQL queries/mutations, configuring generated SDKs, handling offl
• firebase-databaseUse when syncing real-time data, structuring JSON trees, reading/writing, creating listeners, enabling offline
• firebase-flutter-setupSet up Firebase Authentication (Google Sign-In), AdMob, and RevenueCat IAP for Flutter Android apps. Use when
• firebase-in-app-messagingUse when running in-app message campaigns, triggering/suppressing messages, configuring opt-in data collection
• firebase-messagingUse when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground
• firebase-remote-configUse when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config
• firebase-security-rules-auditorAudit Firestore and Cloud Storage Security Rules for authorization bypass, cross-tenant access, privilege esca
• firebase-storageUse when setting up Storage, uploading/downloading files, managing metadata, handling errors, or applying secu
• firebird-databasePadrões de desenvolvimento com banco de dados Firebird via SQLdb/Zeos — conexão, PSQL, generators, transaction
• fireblocks-webhooks>
• firecrawlScrape, search et interagit avec le web via Firecrawl — extrait du contenu propre en Markdown depuis n'importe
• firecrawl-mcpMCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.
• firecrawl-research-patternsProgrammatic Firecrawl usage via the public API, academic paper routing, recursive deep research, and raw corp
• firecrawl-scrapeAI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonom
• firecrawl-scraper|
• firecrawl/cliCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agents
• firecrawl/firecrawl-mcp-server🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM c
• fireflies>-
• fireflies-webhooks>
• firefox-controlUse when you need to automate Firefox via WebDriver BiDi — tab listing, JS evaluation, screenshots, DOM helper
• firekeep-clientSelf-hosted memory, continuity, and coordination for AI coding agents. One MCP gateway, 104 tools.
• firerpa/lamda The most powerful Android RPA agent framework, next generation mobile automation.
• firestore-dataHandles NoSQL document operations and collection hierarchy exploration. Use for CRUD tasks and data retrieval.
• fireteamPersistent memory and task coordination for AI coding sessions. Creates a .fireteam/ folder with mission conte
• firewall防火墙配置
• firewall-aiopsGoverned OPNsense + pfSense firewall ops: rules, NAT, VPN, DHCP, RCA. 35 tools.
• firewall-review>
• fireworks-tech-graph>
• firmwareOpenSkyhawk firmware — STM32 (PanelBridge, PanelGroup) and RP2040 (SimGateway). Use when writing or changing f
• firmware-attestation-mcpFirmware Attestation MCP — hardware trust layer for sovereign AI. Scan firmware, check
• firmware-boot-chainUse when building or debugging a firmware and boot chain (RISC-V SBI, UEFI, ACPI, a bootloader handoff like Li
• firmware-deploymentUse when flashing, updating, or recovering firmware on classroom robots (ESP32, RP2040/Pico, AVR/Arduino) — co
• first-100-usersGet the first 100 real users for a vibe-coder SaaS without spending on ads. Hand-curated outreach, founder com
• first-50-usersGet the first 50 real users through channels the user's ICP already uses. Use when the product shipped and nob
• first-90-daysProvides a structured framework for new-role transitions — accelerating credibility, avoiding the Savior Trap,
• first-b2b-customersHelp users navigate the manual, unscalable journey of finding and closing their first B2B customers. This guid
• first-hires-playbook>-
• first-order-odesProblem-solving strategies for first order odes in odes pdes
• first-personI can help you rewrite text and polish tone. Use when the user asks for copy edits or style cleanup in fixture
• first-principles>
• first-principles-reviewUse when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing con
• first-principles-thinking>
• first-scheduled-taskGuides you through setting up your first automatic task in Cowork — picking the right one, configuring the sch
• first-time-manager运用《关键跨越(新手篇)》的三大跨越框架(承担管理责任/推动执行/辅导他人),指导从业务高手到主管的转型。适用于用户刚晋升主管或即将带团队、纠结任务该自己做还是交给下属、要做向上汇报或与上级对焦优先级、以及辅导下属没起色
• firstprinciplesDecompose to axioms, challenge inherited assumptions, reconstruct from verified truths. USE WHEN first princip
• fiscaliste|
• fit-checkScore a job posting's fit against your resume using Gemini. Fetches the full job description and returns a sco
• fit-repair-optimizerTurn multiview fit reports into a sequential or parallel repair queue for aligning Blender products to source-
• fit-ride-studioAnalyze one or more cycling, running, or hiking FIT/KML activity tracks, generate evidence-based single or agg
• fit-scorerUse when the user asks to "score this influencer", "rank these creators for our campaign", or "tell me which i
• fit.caliper/caliperGeometry and CAD file metadata extraction for STL, OBJ, PLY, PCD, LAS/LAZ, glTF/GLB.
• fit.occam/occamFinds the simplest equation consistent with your data. SINDy and PySR symbolic regression via MCP.
• fit.portfolio/portfoliofitCheck normalized portfolios against mandates and calculate allocation constraints.
• fitbit-mcpMCP server for the Fitbit Web API with OAuth PKCE, local SQLite cache, and trend analysis.
• fitnessMeasure declared project fitness goals
• fitness-coachPersonalized exercise and fitness coaching skill. Creates tailored workout plans, tracks progress, analyzes fi
• fitness-function-designDesign metrics that measure architecture health (coupling, modularity, scalability). Automate fitness function
• fitness-logA portable library of reusable AI skills, prompts, workflows, schemas, and automation patterns designed for Ch
• fitness-programmingA portable library of reusable AI skills, prompts, workflows, schemas, and automation patterns designed for Ch
• fitness-wellnessUse when designing animations for fitness apps, wellness platforms, workout trackers, or meditation experience
• fittokRetrieve only the relevant code for a codebase question, within a token budget.
• fitts-lawApply Fitts's Law — target acquisition time depends on size and distance. Use when sizing and positioning cont
• five-dysfunctions-of-a-teamUse when the user wants to diagnose why a team is underperforming, conflict-avoidant, political, or not delive
• five-whysRoot-cause analysis protocol for when something breaks or fails unexpectedly. Use when a tool call fails twice
• five46BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.
• fixQuick fix workflow for bugs, test failures, and small issues
• fix-a-leaky-funnel>
• fix-and-fixate>
• fix-annotation-from-issuesUse when a GitHub issue reports a missed, spurious, or wrong-element annotation. Reproduces the failure with d
• fix-bug|
• fix-bugbot>-
• fix-build-errorsUse when a build, compilation, or type-check fails — diagnose the error, identify root cause, and apply the mi
• fix-ciDiagnose and fix a failing CI run by pulling the actual failure logs (gh run view --log-failed), reproducing t
• fix-design-system-findingFix a specific design-system integration finding in a Figma screen or component, including missing shared comp
• fix-failing-pipelinesThis skill should be used when the user asks to "fix pipelines", "fix CI", "check staging pipelines", "fix fai
• fix-failing-tests>-
• fix-github-issueUse when you have a GitHub Issue number or link and want it resolved end-to-end — reads the issue, locates the
• fix-instruction-files>
• fix-issueFix a GitHub issue following ThreatForge coding standards and conventions
• fix-llm-artifactsApplies fixes from a prior review-llm-artifacts run, with safe/risky classification. Respects verify-llm-artif
• fix-my-resumeFree ATS resume optimizer for Claude Code — rewrites, scores, and tunes your resume. Never fabricates metrics.
• fix-neat-video修复 Neat Download 下载的分段视频文件。当用户需要处理 .mp4.ts 文件、修复无法完整播放的视频、或提到 Neat Download 下载的视频问题时触发此 skill。
• fix-pr-reviewUse when the user asks to fix, address, or respond to a PR review — "fix the PR review", "address the review c
• fix-pr-review-loopUse when the user asks to fix a PR review and drive it to approval autonomously — "fix the PR review and loop
• fix-security-vulnerabilities-with-strixFix security vulnerabilities found by a Strix pentest (open-source CLI or app.strix.ai cloud) — triage by seve
• fix-tests>
• fix-ts
• fixed-assets-advisorMulti-jurisdiction fixed assets, depreciation, and impairment reference framework covering PP&E, intangibles,
• fixed-footprint-unicode-mascot-compositionBuild terminal mascots whose poses can animate without changing layout by keeping the render area fixed and sw
• fixed-income-corporateAnalyze corporate bonds and credit instruments including investment grade and high yield debt. Use when the us
• fixed-income-credit-analysisUse when analyzing industries or companies for credit decisions in fixed income markets, building industry ana
• fixed-income-municipalAnalyze municipal bonds including tax-equivalent yield calculations, GO vs revenue bond evaluation, and muni c
• fixed-income-sovereignAnalyze US Treasury securities and interest rate risk: bond pricing, yield curve construction, duration, conve
• fixed-income-structuredAnalyze structured fixed income products including mortgage-backed securities, asset-backed securities, and CL
• fixed-tensor-testingTest ML functions with fixed input tensors for reproducibility.
• fixing-accessibility|
• fixing-metadata>
• fixing-motion-performance|
• fixing-promptPrompt: Prompt Refinement and Optimization
• fixing-routingUse when a single routing bug is found from screenshots, logs, test failures, or user reports and needs quick
• fixing-testsUse when tests themselves are broken, test quality is poor, or user wants to fix/improve tests. Triggers: 'tes
• fixing-underperforming-teamsHelp users identify why a team is struggling and implement a structured recovery plan by addressing leadership
• fixture>-
• fixture-goodA minimal but complete skill used to prove the loader accepts valid Claude Code SKILL.md input.
• fixture-review-skillReview a compact fixture contract.
• fixture-runnerOffline-first, precision-first security linter for SKILLS, MCP, plugins, configs and other AI infrastructure.
• fixture-skillAgent-native course marketplace and skill registry for executable AI-agent curricula
• fixturesOffline-first, precision-first security linter for SKILLS, MCP, plugins, configs and other AI infrastructure.
• fiz-invoicing>-
• fjrg2007-android-di-hiltWire Android dependency injection with Hilt, scopes, testing overrides, and module ownership boundaries.
• fjrg2007-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• fjrg2007-gsap-utilsOfficial GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pip
• flag-addAdd a CLI flag to shipctl end-to-end — argument parser definition, help text, shell completion scripts, docume
• flagrixScan GitHub repos and profiles for malware before cloning — commit-pinned risk verdicts for agents
• flake8-config-helperAutomated helper for file workflows.
• flaky-selector-scan>
• flaky-skillA skill with potentially flaky behavior for testing retry
• flaky-test-analyzerDiagnoses why tests pass inconsistently and suggests fixes for timing, ordering, and state isolation issues.
• flaky-test-detectorIdentifies non-deterministic or unreliable tests through static code analysis and test result analysis. Use wh
• flaky-test-diagnoserSystematically diagnoses why a test is flaky by running multi-run experiments, isolation tests, ordering permu
• flaky-test-investigationUse when tests pass and fail intermittently without code changes, or a test passes alone but fails in the full
• flameoxLocal runtime evidence for coding-agent performance and reliability investigations
• flarehq-mcpFlare MCP server: let Claude Code, Cursor or Windsurf scan your running app and repo for leaked secrets, expos
• flaresolverrUse the minimal FlareSolverr wrapper for a one-off health check or browser-backed GET/POST when ordinary retri
• flaresolverr-cliUse a small FlareSolverr JSON CLI for browser-backed GET and POST requests, readiness checks, and session life
• flashBuild firmware + filesystem and flash to ESP via USB. Auto-detects serial port. No user input needed.
• flash-loan-arbitrage-executorProduction-ready DeFi arbitrage system that detects and executes profitable price differences across multiple
• flash-testSTM32 firmware build + ST-Link flash + Python plot başlatma (test akışı)
• flashcard-generator>
• flashcard-makerCreate Anki-compatible flashcard decks — spaced repetition, cloze deletions, images, and export to CSV/APKG.
• flashcards>
• flashdb-integrationUse when integrating, porting, configuring, or debugging FlashDB KVDB or TSDB on MCU flash, filesystems, RTOS,
• flask|
• flask-api-development>
• flask-monolith-refactor>
• flatTwo-dimensional minimalist style with vibrant colors, clean typography, and no 3D effects for fast, user-frien
• flat-field-cover-poster把主题、标题或人物概念编译成「平涂色场封面海报」提示词：单一纯平色底 + 写实人像摄影，超大压缩体大写标题横跨上三分之一、第二行穿过头肩被部分遮挡，一个手绘元素压在前景下角桥接照片层与图形层，四周环绕杂志编辑排版系统，2
• flatbread-major-migrationGuide schema-breaking Flatbread migrations across core schema generation, resolver arguments, generated TypeSc