Parcourir le registre

Toutes les entrées, par ordre alphabétique — 76 676 au total. Page 297 sur 307.

• vendor-checkCheck the status of existing agreements with a vendor across all connected systems — CLM, CRM, email, and docu
• vendor-commitment-trackerTracks every commitment made by vendors across active procurement relationships — delivery promises, SLA guara
• vendor-coordination-trackerTracks every outstanding vendor coordination item across active transactions — inspectors, appraisers, contrac
• vendor-escalation-logFinds every vendor escalation, supplier complaint, and unresolved service failure across procurement email thr
• vendor-evaluationUse this skill when the user asks to evaluate a vendor, score candidate SaaS or services providers, build a ve
• vendor-evaluation-scorecardEvaluates and compares vendors, software platforms, or service providers using a weighted scoring methodology.
• vendor-managementImplement vendor risk management programs. Assess third-party security and maintain vendor inventory. Use when
• vendor-reviewEvaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor propos
• vendor-spend-analyzerCalculates total spend per vendor over a time period from email receipts and invoices, identifying the largest
• vendor-topic[What this skill covers — the domain knowledge inside: entities, API surface, workflows, gotchas. One clear st
• venice-api-keysManage Venice API keys. Covers GET/POST/PATCH/DELETE /api_keys, GET /api_keys/{id}, GET /api_keys/rate_limits,
• venice-api-overviewHigh-level map of the Venice.ai API - base URL, authentication modes, endpoint categories, response headers, p
• venice-audio-musicAsync music / audio-track generation via Venice. Covers the /audio/quote + /audio/queue + /audio/retrieve + /a
• venice-audio-speechGenerate speech from text via POST /audio/speech, and clone a voice via POST /audio/voices. Covers TTS models
• venice-audio-transcriptionTranscribe audio files to text via POST /audio/transcriptions. Covers supported models (Parakeet, Whisper, Wiz
• venice-augmentVenice augmentation endpoints for agent pipelines. Covers POST /augment/text-parser (extract text from PDF/DOC
• venice-authAuthenticate to the Venice API with a Bearer API key or with an x402 / SIWX wallet (EVM on Base or Ed25519 on
• venice-billingVenice billing and usage analytics - GET /billing/balance, GET /billing/usage-history (keyset-paginated per-re
• venice-charactersDiscover and use Venice public characters (persona-driven system prompts with a bound model). Covers GET /char
• venice-chatCall POST /chat/completions on Venice. Covers the OpenAI-compatible request shape, Venice-only venice_paramete
• venice-crypto-rpcUse Venice as a pay-per-call JSON-RPC proxy to 27 EVM, Starknet, and Solana networks. Covers GET /crypto/rpc/n
• venice-embeddingsCall POST /embeddings on Venice. Covers request shape (input, model, encoding_format, dimensions, user), OpenA
• venice-errorsHandle Venice API errors correctly. Covers the StandardError / DetailedError / ContentViolationError / X402Inf
• venice-image-editTransform existing images with Venice. Covers POST /image/edit (prompt-driven single-image edit), /image/multi
• venice-image-generateGenerate images with Venice. Covers POST /image/generate (Venice-native), POST /images/generations (OpenAI-com
• venice-modelsDiscover Venice models, their capabilities, constraints, and pricing. Covers GET /models (with ?type filter),
• venice-responsesUse Venice's Alpha POST /responses endpoint - an OpenAI-compatible Responses API with typed output blocks (rea
• venice-text-routingRoute a prompt to the right Venice text model based on privacy tier (anonymized / private / TEE / E2EE), modal
• venice-videoGenerate and transcribe videos via Venice. Covers the async /video/quote + /video/queue + /video/retrieve + /v
• venice-x402Manage Venice x402 wallet credits. Covers POST /x402/top-up (payment discovery + signed USDC settlement), GET
• venmo-reconcilerReconcile Venmo business transactions and separate personal from business.
• venture-analystStartup and SaaS idea validation. Researches market evidence, maps competitors, scores viability, and generate
• venture-strategistConverts vision and market opportunity into traceable business models, product portfolios, and strategic plans
• venue-ranking-evidenceUse when identifying a journal, conference, or proceedings series from a partial name, acronym, alias, ISSN, o
• venue-templatesPrepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific for
• venunite-events400,000+ source-verifiable US events from independent venues/community calendars in all 50 states.
• veo-3Use to write great prompts for Google Veo (Veo 3.1) to generate or animate video for social media — the video-
• veraciumProvenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.
• veracrypt-mcpMCP server to mount and unmount VeraCrypt containers with secure stdin password handling.
• veragent-mcpCheck the trust/security score of MCP servers, agents, skills & CLIs before you install them.
• verantis-mcpVerified directory for machine payments (x402 & MPP): check services and wallets before agents pay.
• verb-domain-taskPerform {{CAPABILITY}} with {{KEY_CONSTRAINTS}}. Use when users ask to {{TRIGGER_SCENARIOS}}, or when working
• verbatim-transcribe-mcp让 agent 驱动本机的 Verbatim 音视频转写与博主观点分析：提交转写、轮询、搜索转写库。
• verbative-memoryOn-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
• vercelManage Vercel deployments, projects, environment variables, domains, DNS, and build/runtime logs via REST API.
• vercel-ai-gatewayRoutes OpenAI-compatible chat completions, embeddings, and image generation through Vercel's AI Gateway for co
• vercel-ai-sdkVercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool c
• vercel-cliDeploy and manage Vercel projects. Use for deployments, environment variables, logs, domains, and cron jobs.
• vercel-cli-with-tokensDeploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using
• vercel-composition-patternsA lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as
• vercel-deployDeploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app"
• vercel-deploymentExpert knowledge for deploying to Vercel with Next.js
• vercel-envUse when environment variables must reach Vercel: push environment variables to Vercel for the preview and pro
• vercel-forensicsPreservation-first forensic evidence collection and analysis for Vercel security incidents (OAuth supply-chain
• vercel-hygieneAudit and harden the 4 pivoshenko brand sites on Vercel (pivoshenko.dev, pivoshenko.startpage, pivoshenko.wall
• vercel-labs/agent-skillsVercel's official collection of agent skills
• vercel-linkUse when first connecting a repository to a Vercel project: link the local repository to a Vercel project so d
• vercel-msUse when working with the `ms` package (vercel/ms) for converting between millisecond numbers and human-readab
• vercel-optimizeUse for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, an
• vercel-platform-mcp-serverLocal implementation of Vercel MCP server
• vercel-previewUse when every branch should get an isolated preview deploy: ensure every branch gets an isolated preview depl
• vercel-react-best-practicesReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when
• vercel-react-native-skillsA lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as
• vercel-react-view-transitionsGuide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>`
• vercel-satoriALWAYS use when writing code importing \"satori\". Consult for debugging, best practices, or modifying satori.
• vercel-ui-skillsVercel's UI design system. Use when building interfaces inspired by Vercel's aesthetic - light mode, Inter fon
• vercel/aiThe AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for buil
• verdachtsmeldung-fiuPrüfung und Entwurf einer Verdachtsmeldung an die FIU nach § 43 GwG – niedrige Meldeschwelle ('Tatsachen darau
• verdict-auditorStress-tests an AZIMUTH output against the skill's own structural rules. Paste an AZIMUTH output and invoke to
• verdict-finance-mcpVerdict, the due-diligence house for DeFi: keyless ratings, methodology and a hack incident feed.
• verdict-mcpSandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history
• verdict-qa-mcpRead-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.
• verdictswarm-mcpRead-only pre-trade token risk verdicts and size-aware Solana exit screening for agents.
• vericontextGuides AI agents to follow VeriContext citation/claim rules when writing or editing documents (README, AGENTS.
• veridigitVerified IBAN, card, ISBN-13 & VIN validation for AI agents — checksums, not guesses.
• verifiable-claim-seedZero-dependency verifiable-claims MCP: validate safely, verify with allow_execution, self-test.
• verificar-spec>
• verificationEnforce evidence-based verification before claiming any task is complete
• verification-and-reliabilityUse first when the user asks for tests, correctness, high reliability, static reasoning, proof, or safety evid
• verification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires runn
• verification-before-mergeUse before merging PR - final gate ensuring all tests pass, review complete, CI green, and acceptance criteria
• verification-contractInternal contract: one compact frozen ACCEPTANCE.md per delivery unit, its validation ladder, anti-weakening r
• verification-engineActivate when the user needs to verify citations, check source accuracy, or validate that referenced papers ac
• verification-gateRun a read-only verification pass after implementation to check whether completion claims are real, validation
• verification-gatesThe verification tiers and gate commands for Struq Voice. Use whenever finishing a slice, before a commit, or
• verification-loopA comprehensive verification system for Claude Code sessions.
• verification-qualityUse when you need to verify work quality using truth scoring (0.0–1.0) with environment-tiered thresholds and
• verification-quality-assuranceComprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy thres
• verification-suitePlan structure validation, phase completeness checks, reference integrity verification, and artifact existence
• verified-googledocs-mcpMCP server for Google Docs with verified writes — every mutation returns before/after proof.
• verifier-pattern安価な (または同格の) executor が成果物を作り、上位モデル (verifier) が完了判定・品質判定の時点でのみ介入して検査する「verifier delegation」パターンの opt-in 判断支援
• verifier-setupSet a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a
• verifox-mcpVerifox MCP server — verify email deliverability and find business emails (single + bulk) for Claude and any M
• verifyVerifica se uma mudança no Magic Collector funciona corretamente. Use quando precisar confirmar que uma featur
• verify-against-intentAfter a Sui build session, check what was built against .suiperpower/intent.md and flag drift. Use when the us
• verify-api-mcpEvidence-backed verification for citations, packages, repos, cases, filings, drugs, x402 sellers.
• verify-baseline-before-changesBefore implementing new features, run existing tests to confirm green baseline: this ensures any failures afte
• verify-before-claimUse when an agent is about to claim completion, correctness, safety, publication, deployment, or any consequen
• verify-before-doneUse before claiming "done", "fixed", "tested", or "it runs", and before committing or opening a PR or MR—no ta
• verify-buildSeldonFrame merge gate — run unit tests + tsc + check-use-server + migration-journal + regression-grep and ret
• verify-build-worksSmoke-test that the project still builds, the dev server starts, and the main user flow loads after a change.
• verify-changeDesign and execute a risk-based verification strategy for a software change, bug fix, refactor, migration, con
• verify-command-executionAutocreates skill.md files from Claude Code logs dataset
• verify-completionGate every "it works / it's fixed / tests pass / done" claim behind fresh evidence — run the actual verifying
• verify-diagramVerify an SVG diagram or HTML scene for visual quality. Renders to PNG, checks for overlaps, clipping, readabi
• verify-docs-findableAudit whether a repo's docs actually ANSWER the questions a reader has — by spawning fresh, cheap (Haiku) agen
• verify-doneUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires runn
• verify-editAutocreates skill.md files from Claude Code logs dataset
• verify-edit-changesAutocreates skill.md files from Claude Code logs dataset
• verify-email-snapshotsSnapshot test email templates using Verify to catch regressions. Validates rendered HTML output matches approv
• verify-environment-readyAutocreates skill.md files from Claude Code logs dataset
• verify-harnessRun after `rig init` to verify all hooks, skills, and agents are installed and working correctly in the live s
• verify-homecoreRun the smallest relevant core, Wasmtime, HAP, or full Homecore test profile.
• verify-hypothesesСверка журнала гипотез (hypotheses-log.md) по запросу вне ритма week-close. Фильтрует записи со статусом «на с
• verify-implementationLoad this skill when the user says "verify-implementation", "verify implementation", or "/verify-implementatio
• verify-interpreterInterpret the output of `specgraph verify` and explain what each status means and what to do next.
• verify-languageLanguage-specific verification for Python, TypeScript/JavaScript, and Go. Checks type safety, language idioms,
• verify-llm-artifactsConfirms or rejects findings from review-llm-artifacts before deletes or risky refactors. Loads review-verific
• verify-mockVerification checklist to walk before declaring a tt-emule mock complete. Use after implementing a stub (typic
• verify-patternsVerify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle
• verify-prerequisitesAutocreates skill.md files from Claude Code logs dataset
• verify-product-imageQC gate for a generated static ad image — verify the file opens, matches the requested dimensions, shows the c
• verify-project-locationAutocreates skill.md files from Claude Code logs dataset
• verify-proofVerify blockchain timestamp proofs offline, or anchor a new one through ProofLedger.
• verify-qualityUse when you need to run quality verification with truth scoring (0.0-1.0) and environment-tiered thresholds.
• verify-refsAudit-only verification of manuscript references against PubMed and CrossRef. Detects fabricated or mismatched
• verify-regimeLevel 5 verification: regime conditioning tests across VIX regimes, stress event validations (March 2020, Febr
• verify-securityVerify code for security issues including hardcoded secrets, input validation, error exposure, and dependency
• verify-signAdd an Artifact Verification (SscaArtifactVerification) step to an existing Harness pipeline to verify Cosign
• verify-sourcesCaptures human source verification for tracks, timestamps it, and updates track files. Use when sources need h
• verify-specDescribe el proceso a seguir para verificar los resultados de la implementacion de una spec
• verify-thisProve a concrete behavior, performance, UI, CLI, API, or memory claim with fresh baseline-versus-treatment evi
• verify-uiVerify Flutter UI matches Figma or reference design on real device. Use when doing UI work, comparing screens
• verify-ui-autoAutomated UI verification loop: Marionette screenshot -> Figma reference -> pixel-diff -> difference list -> a
• verify-ui-qualityMechanical pre-ship verification of self-built UI: measures the build against design intent (spacing, type, st
• verify-understandingVerify the engineer is ready to implement a feature — a teach-back conversation over a .TICKET-REVIEW.md where
• verify-with-curlVerifies work done in the current context using curl. Auto-fixes issues found. Does not write tests. Trigger w
• verify-with-playwright-mcpVerifies work done in the current context using Playwright MCP tools. Auto-fixes visual issues found. Does not
• verifyfirst-mcpLook up what your verification method cannot see: 48 failures that report success.
• verifyingUse when verifying information (fact, number, quote, event, statement) against authoritative primary sources,
• verifying-claimsCheck that a document's claims about code are actually true by reading the prose, the code, and the tests and
• verifying-compose-uiVerifying Compose UI by rendering components or previews and inspecting the resulting images and state transit
• verifying-hunchesUse when about to claim discovery during debugging. Triggers: "I found", "this is the issue", "I think I see",
• verifying-modulesScans directory structure, detects missing documentation, and verifies code-doc synchronization. Use when chec
• verifying-results-before-claimingUse when about to claim a result, effect, significance, or that an analysis reproduces, before reporting or wr
• verikod/hectorA2A-Native AI Agent Platform written in Go
• verimcpTransparent MCP proxy that independently re-verifies tool-call claims before the Host trusts them.
• veriroute-intel-mcpTells your agent whether a number is safe to call or text right now. Local stdio shim for the hosted VeriRoute
• verirunExecution-grounded verification for AI coding agents on Windows: evidence, not agent claims.
• veritap-mcpMCP server for checking whether a real-world fact can be verified before an AI agent acts on it — businesses,
• veritasgraph-mcpZero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.
• verity-mcpFail-closed verify-before-you-act gate for AI agents. Signed receipts. Pay-per-call via x402.
• verl-rl-trainingProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when imple
• vermenschlichenSchreibregeln für natürliche, sachliche deutsche Texte, die typische KI-Verräter vermeiden. Immer anwenden, we
• verotusmenettely-ja-muutoksenhakuVerotusmenettely ja muutoksenhaku verotukseen Suomessa (laki verotusmenettelystä 1558/1995). Käytä tätä skilli
• versionBump the project version (major, minor, or patch) across all manifest files and add a changelog entry. Use whe
• version-archive为"多版本归档目录"（类似 LC_CPUWR_history，同一模块按版本迭代归档 RTL/env/文档的目录）建立独立的目录级维护规则：目录内 CHANGES.md 总览、README 版本速查表、归档结构规范。触发
• version-bumpAutomated semantic versioning and release workflow for Claude Code plugins. Handles version increments across
• version-bump-advisorRecommend the correct semver bump with reasoning and a generated changelog entry. Trigger when someone says: w
• version-bump-rulesKeep versions up-to-date — every production change bumps the version in the same commit. Semantic versioning r
• version-controlManage Git repositories and collaborative workflows — branching strategies, commit hygiene, conflict resolutio
• version-control-strategyDefine version control strategies for design files, components, and libraries.
• version-datasetDataset version control for research reproducibility. Builds a deterministic content-hash manifest of a datase
• version-releaseVersion release workflow — release process and GitHub Release notes (not docs/changelog pages).
• versioning-guideUse when bumping a package version, cutting a release, or detecting which packages changed version. Triggers o
• vertakhan-plan-eng-reviewEng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test
• vertex-ai-fedramp-high-il2-launchKey takeaways and a short, compliant checklist for enabling Claude models on Google Cloud Vertex AI in FedRAMP
• vertical-marketplace-mcpMCP server for Vertical Marketplace by Vermarco - the marketplace where AI agents buy and sell. Sellers keep 9
• vertical-sliceThe standard workflow for building one complete feature in the Spiral Nexus codebase (or any Next.js + Supabas
• vertical-slice-architectureEnforce Vertical Slice Architecture (VSA) when building applications in any language (Go, .NET/C#, Java, Kotli
• vertically-sliced-feature-modulesOpinionated feature-first architecture conventions for cohesive modules, owned subtrees, entry points, shared-
• vertiport-planning-engineerExpert-level Vertiport Planning Engineer specializing in vertiport site selection, FATO/TLOF design, passenger
• vertragsverletzungsverfahrenReaktionsstrategie auf ein Vertragsverletzungsverfahren der EU-Kommission gegen die Bundesrepublik Deutschland
• very-good-analysis-upgradeUpgrade the very_good_analysis lint package to a new version across Dart/Flutter projects. Handles the pubspec
• verychic-mcpUnofficial read-only MCP server for VeryChic hotel offers
• verygoodopensource-testingBest practices for Dart unit tests, Flutter widget tests, and golden file tests.
• vestige-mcp-serverLocal-first memory for AI agents that reaches backward to find a failure's root cause.
• vet(forwward) Go/no-go readiness audit before promoting to production — checks for unsigned commits (which can si
• vet-skillSecurity-audits a third-party agent skill before installing or adapting it — checks for prerequisite-trap malw
• vet.bio/biovet-mcpMoscow vet clinic network (20 clinics, 24/7): clinics, live prices, slots, booking, triage. Russian
• Veteranet/kybernetesAgent supervision, memory distillation, and multi-model orchestration. Kybernetes steers AI agents — catching
• veterinarianExpert veterinary practitioner with 15+ years in livestock disease diagnosis, treatment protocols, herd health
• Vexa-ai/vexaOpen-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSo
• vexorA semantic search engine for files and code.
• vexorVector-powered CLI for semantic file search with a Claude/Codex skill
• vexor-cliSemantic file discovery via `vexor`. Use whenever locating where something is implemented/loaded/defined in a
• vfx-fxCinematic and game VFX in Blender including smoke, fire, particles, trails, and Geometry Nodes FX setups via M
• vfx-text-cursorCursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.
• vg-resource-mcpSearch and download sprites, models, textures, and sounds from VG Resource.
• vglMaximum control over AI image generation — write structured VGL (Visual Generation Language) JSON that explici
• viajanteFlight and hotel search for the terminal, Python, and AI assistants.
• vibatchiumPatchright stealth + Vibium-style LLM-friendly CLI for agentic browser automation.
• vibeVibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, bounds execution, and enfo
• vibe-acceptance-gateValidates completed work against defined acceptance criteria. Use after completing a task that has specific su
• vibe-adversarial-test-generationGenerates edge case, failure mode, and spec-driven test cases. Covers boundary values, nil inputs, concurrency
• vibe-agentsGenerate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instru
• vibe-anti-rationalization-checkDetects and prevents shortcut rationalization — when the agent is about to skip a step, simplify a requirement
• vibe-async-task-queueProvides a persistent cross-session task queue for work that should be done but isn't blocking current tasks.
• vibe-auditRuns a comprehensive 20-point code quality audit on a "vibe-coded" codebase that was shipped fast and now need
• vibe-buildBuild your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or
• vibe-checkTurn a complete beginner's app idea into a buildable plan, then keep them oriented while they build. Use it wh
• vibe-cherry-pick-integrationSafely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work c
• vibe-codingTurn an idea into a demo-ready prototype using AI-assisted vibe coding.
• vibe-coding-architecture教非技术背景的人看懂技术架构、做好技术选型——把"只会照搬话术的小白"练成"能看穿方案好坏的人"。 当用户问"该用什么技术/框架"、"帮我选技术栈"、"AI 给的方案我看不懂"、"这几个方案怎么选"， 或者需要把 dem
• vibe-coding-harness质检 Agent：检查 vibe-coding-kit 其他 Skill 的产出物是否符合治理规范。 当用户说"检查一下产出"、"帮我看看合不合规"、"质检"、"验证 PRD"、"检查项目说明书"， 或在任何 Skill
• vibe-coding-prd把需求、原始 PRD、竞品分析、零散笔记或模糊产品想法提炼成可直接发给 Claude Code、Codex 或其他编码 Agent 的精简中文 Markdown PRD。触发：用户说“帮我写一个用来vibe coding
• vibe-coding-production把验证过的 Vibe Coding demo，做成能长期运行、给别人用的正式系统。 当用户说"想上线"、"怎么部署"、"这个 demo 想做成正式的"、"要注意安全吗"、"怎么测试我的项目"， 或者准备把代码开源/公开发
• vibe-coding-requirementsVibe Coding（用 AI 写代码）项目的第一步：把模糊的想法，变成 AI 能精准落地、不会跑偏的需求。 当用户说"我想做一个 XX"、"帮我用 AI 做个 demo"、"我有个想法想验证"、"帮我跟 AI 对齐需
• vibe-coding-survivalVibe Coding（用 AI 写代码）开发过程中的避坑与自救——真正翻车大多发生在"开工后"。 当用户说"AI 越改越乱"、"demo 改坏了退不回去"、"AI 老忘记之前说的"、"功能越加越多很乱"、 "AI 说做
• vibe-concurrent-test-safetyAudits tests for concurrency safety — race conditions, shared mock state, cleanup ordering. Use when writing t
• vibe-coverage-enforcerEnforces tiered test coverage standards with three dimensions — line coverage by tier, spec-to-test traceabili
• vibe-creating-promptJudges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distill
• vibe-debugging-journalRecords resolved bugs in a persistent journal — symptom, root cause, difficulty, fix, prevention. Organized by
• vibe-decision-journalExtracts and records architectural decisions from diffs, conversation context, and explicit choices. Supports
• vibe-delegateDelegate a coding task to the Mistral Vibe CLI (`vibe`) as a background implementer, then review its diff and
• vibe-devil-advocate-reviewChallenges recommendations, designs, or synthesis by adversarial review across 5 dimensions. Use before shippi
• vibe-doc-quality-gatePerforms a fast 6-point quality check for technical documents (specs, design docs, READMEs). Use after editing
• vibe-fuzz-parser-inputsGenerates fuzz test scaffolding for parsers handling external input (YAML, JSON, config files, user input). Se
• vibe-gap-analysisAssesses production readiness or audits a codebase against its specs. Supports quick static mode, deep 17-dime
• vibe-gap-closure-loopCloses production readiness gaps from a gap analysis document. Autonomously loops dependency analysis, paralle
• vibe-golden-file-testingImplements snapshot/golden file tests with temporal normalization so tests don't break daily. Use when impleme
• vibe-handover-docGenerates a session continuity document at the end of a long session or when switching context on a multi-sess
• vibe-helpRoutes users to the right vibe-engineering skill for their current task. Use when user asks "what skill should
• vibe-iteration-reviewPerforms end-of-iteration review with quality grading, metrics, and trend analysis. Use at the end of each dev
• vibe-maintainerMaintainer playbook for agent-era OSS — PR triage, fix-merge discipline, and attribution rules for a solo huma
• vibe-marketingAI-powered marketing at scale — vibe marketing workflows for rapid content generation, creative iteration, cam
• vibe-mergeUse when the user wants to "vibe-merge"/"vibe-marge" a PR or branch: independently reimplement good ideas, avo
• vibe-modeThis skill should be used when the user wants to adjust Claude's interaction style and personality level. It p
• vibe-parallel-task-decompositionAnalyzes large tasks for independent subtasks that can be safely parallelized. Produces a DAG-based dispatch p
• vibe-pattern-libraryDetects recurring implementation patterns and records them for reuse. When the same code pattern appears 3+ ti
• vibe-prdCreate a Product Requirements Document (PRD) for your MVP. Use when the user wants to define product requireme
• vibe-pre-commit-auditScans staged changes for secrets, debug statements, TODOs without references, and other common commit mistakes
• vibe-production-mindsetSets quality expectations for implementation — "imagine this serves 1 million users." Checks for observability
• vibe-quality-loopEnforces the Implement→Review→Test→Fix→Loop cycle until work is clean. Use after any non-trivial implementatio
• vibe-reflect-and-compoundExtracts learnings from completed work, feedback, or failures. Updates a persistent learnings file with capped
• vibe-requirements-validatorValidates PRD, user stories, or feature requirements against SMART criteria. Use when reviewing requirements t
• vibe-researchDeep research and market validation for app ideas. Use when starting a new project, validating an idea, or whe
• vibe-research-before-designDispatches SOTA research before proposing any new feature, architecture, or technology choice. Use when facing
• vibe-rollback-planDocuments rollback procedures before making risky changes. Covers what's changing, verification steps, rollbac
• vibe-safe-deployPerforms deployment with pre-flight checks, atomic replacement, post-deploy verification, and automatic rollba
• vibe-scenario-matrixGenerates a behavioral scenario acceptance matrix for comprehensive test coverage planning. Maps user scenario
• vibe-scope-guardDetects and redirects scope creep during implementation. Catches unrequested features, unnecessary refactoring
• vibe-securitySecurity intelligence for code analysis. Detects SQL injection, XSS, CSRF, authentication issues, crypto failu
• vibe-service-health-dashboardQueries all configured services for health status — uptime, restarts, errors, resources. Use when checking the
• vibe-session-context-flushPerforms smart context summarization when the context window is approaching capacity. Identifies what to keep,
• vibe-shipGenerates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.
• vibe-spec-syncBidirectional sync between specification documents and code. Detects spec drift from staged changes, updates s
• vibe-spec-vs-code-auditCompares specification documents against implementation code to find divergences. Use when implementation of a
• vibe-start-informedDispatches research agents to find real projects, papers, and documented failures before proposing any feature
• vibe-story将 Claude Code 的多个开发会话提取为时间线骨架，并生成公众号长文。当用户想把 Vibe Coding 过程写成开发分享、技术文章、公众号推文时使用此 Skill。触发词包括：开发分享、写文章、总结开发过程、v