Sfoglia il registro

Tutte le voci, in ordine alfabetico — 56.437 in totale. Pagina 6 di 226.

• ad-compliance-review广告合规审核技能，用于审核广告素材是否符合中国广告法及相关法规。适用场景：(1) 用户提交广告文案、广告素材要求合规审核时；(2) 用户提到"广告审核""广告合规""广告法审查"等关键词时；(3) 用户要求检查广告内容是
• ad-copyCreate platform-specific ad copy within character limits with A/B test variants. Supports Google Ads, Facebook
• ad-copy-compliance-review风险审阅助手适合运营、市场营销、销售、法务在用户提出“这里有什么风险”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
• ad-copy-evaluatorEvaluates search ad copy (headline + description) against a structured, intent-aware rubric across 5 dimension
• ad-copy-generatorGenerates paid ad copy for Meta, Google, TikTok, LinkedIn, and other paid channels. Use when the user asks for
• ad-copy-google-adsWrites Google Ads copy including RSA headlines, descriptions, extensions, DKI templates, and CTAs. Use when cr
• ad-copy-writerGenerate ad copy variations for Google, Meta, and LinkedIn Ads
• ad-creativeRender ad concepts as HTML with 5 template styles (cookie-cutter, ugly, meme, branded, native), optionally scr
• ad-creative-briefSkill especializada para a criação, revisão e otimização de Ad Creative Briefs focados em Meta Ads, Google Ads
• ad-creative-builderUse when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produce
• ad-creative-generationGenerate on-brand ad creatives — visuals + copy — for Google, Meta (Facebook / Instagram), and other paid plat
• ad-creative-paid-adsA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.tx
• ad-creative-strategyDevelop ad creative strategy for B2B campaigns — creative formats per platform, testing methodology, creative
• ad-creative-testingDesigns a disciplined ad creative testing system with hooks, isolated variables, and statistical rigor. Use wh
• ad-creative-v2Ad Creative workflow skill. Use this skill when the user needs Create, iterate, and scale paid ad creative for
• ad-creative-videoThis skill should be used when the user asks to "make a video ad", "create an animated ad", "build a performan
• ad-fatigue-diagnosisAd Fatigue Diagnosis — Skill especializada para ad fatigue diagnosis
• ad-lead-quality-analyzerFor paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joi
• ad-makerScroll-stopping ad creative for any product: hooks, full scripts, UGC briefs, storyboards, and angle matrices,
• ad-performance-loopClosed-loop ad performance optimization. Analyzes campaign results, identifies winning creatives by CPA/ROAS,
• ad-performance-reportUpload CSVs exported from Meta Ads, Google Ads, TikTok Ads, or any ad platform. Agent generates a standardized
• ad-reconCollect competitor ads from public ad libraries (Meta Ad Library, Google Ads Transparency Center, TikTok, Link
• ad-researchAutonomous competitor ad intelligence. Scrapes competitor ads from Meta Ad Library and other platforms, transc
• ad-script-generatorGenerate 100+ ad script variations from competitor intelligence. Takes ad-research output, rewrites competitor
• ad-spend-optimizerAnalyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and mi
• ad-test-designerUse when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test"
• ad-to-landing-page-auditorAnalyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries thr
• ad-yield-optimizationAnalyzes advertising yield across programmatic and direct-sold inventory including CPM/CPC/CPA performance, he
• adaAda, your Executive Assistant. Runs planning and reflection rituals by coordinating domain assistants.
• adafruit-io-rest-apiAdafruit IO REST API skill. Use when working with Adafruit IO REST for user, {username}, webhooks. Covers 71 e
• adaloAdalo integration. Manage data, records, and automate workflows. Use when the user wants to interact with Adal
• adam-self-improvementUse when the user types /reflect, asks "what has adam learned", asks to "review proposals", or wants to inspec
• adaptAdapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints,
• adapt-architectureExecute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation.
• adapt-copyAdapt post copy for every target platform — character limits, hashtag counts and placement, tone, compliance,
• adapt-workflowUse when porting a workflow to a different AI provider, deployment environment, model tier, or organizational
• adaptation-strategiesDecision framework for making a model do a task — choosing between in-context learning, RAG, fine-tuning (LoRA
• adapter-drift-auditUse when checking whether an IronLint adapter still matches its coding harness's current contract — auditing a
• adapticMaster skill composing the 5-step synoptic cycle for panoramic synthesis across multiple domains. Orchestrates
• adaptive-communicationUse when detecting ambiguous user intent, hedging language, open-ended framing, personal context before reques
• adaptive-sales-qualificationAssess, verify, score, and prioritize leads, accounts, and sales opportunities using an adaptive, evidence-bas
• adaptive-ui27 Android skills for AI agents (Claude Code, Codex, Cursor). Fixes Supabase auth, Hilt errors, design inconsi
• adaptyvCloud laboratory platform for automated protein testing and validation. Use when designing proteins and needin
• adatreeAdatree integration. Manage data, records, and automate workflows. Use when the user wants to interact with Ad
• adattributionkitMeasure ad effectiveness with privacy-preserving attribution using AdAttributionKit. Use when registering ad i
• adb-android-controlComprehensive Android device control via ADB (Android Debug Bridge). Use when user asks about: Android device
• adb-builderADB Auto Player with MoAI-ADK integration
• adbutlerAdButler integration. Manage data, records, and automate workflows. Use when the user wants to interact with A
• addADD (AI-Driven Development) — a minimal, state-tracked workflow for building software where the AI writes the
• add-a-linterAdd a new linter to vigiles's cross-referencing engine as one cohesive, type-enforced unit — a LinterAdapter i
• add-a-zeroForce 10x thinking on any goal using Brian Chesky's "Add a Zero" exercise. Breaks you out of incremental think
• add-admin-api-endpointAdd a new endpoint or endpoints to Ghost's Admin API at `ghost/api/admin/**`.
• add-agent-templatesAdd new Agent templates to the meta-agent-skills framework.
• add-aiUse when adding an AI/LLM feature to a product - chat, generation, summarization, extraction, semantic search
• add-ai-endpointScaffold a Claude API powered endpoint with system prompt, structured output, token tracking, and rate limitin
• add-analysis-ruleAdd a new analysis rule to the CLAUDE.md optimizer engine. Use when creating a new detection rule for ambiguit
• add-app-clipAdd an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-associati
• add-app-to-serverThis skill should be used when the user asks to "add an app to my MCP server", "add UI to my MCP server", "add
• add-atomic-chat-toolAdd Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app
• add-authUse when adding user accounts to an app - signup, login, OAuth, protected routes, sessions - or when the user
• add-backendEverything about the data layer — pick one of six ready-to-run backend templates (TanStack Start + Drizzle + b
• add-buildpadAdd Buildpad UI components to a DaaS project via CLI. Installs Copy & Own components from the registry includi
• add-cart-discountAdd per-item discount support to the cart total
• add-characterUse when implementing a Town Hall character ability in Salem 1692. Covers reading the rulebook edge cases, fol
• add-chilliAdds extra chilli to the wok for a spicy kick. Only invoked when the user requests spicy nasi goreng.
• add-clidashAdd clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any
• add-cobra-versionAdd a version subcommand with build metadata to an existing Cobra-based Go CLI. Use when the user says "add a
• add-codexUse Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP
• add-commandGuide for adding new CLI commands or subcommands to todoist-cli. Use when implementing new SDK endpoints, addi
• add-community-filesAdd standard community files to a project: CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md, and a pull reques
• add-companyAdds one or more company records to the Carta CRM via the Carta CRM MCP Server. Use this skill when the user s
• add-componentAdd a copy-ready admin UI building block to a dashboard built on the scaffold-dashboard base — forms (form, wi
• add-contactAdds one or more contact records to the Carta CRM via the Carta CRM MCP Server. Use this skill when the user s
• add-customer-to-user-listAdd or update a company in the Langfuse /users adopters table. Use when the user asks to add a customer, adopt
• add-dashboardAdd a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic J
• add-dealCreates one or more deal records in the Carta CRM via the Carta CRM MCP Server. Use this skill when the user s
• add-deltachatAdd DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-
• add-discordAdd Discord bot channel integration via Chat SDK.
• add-doctor-runbookAdds a new runbook to an existing doctor and registers it in the runbook index and mode config. Use when exten
• add-educational-commentsAdd educational comments to the file specified, or prompt asking for file to comment if one is not provided.
• add-emacsAdd Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw
• add-external-oauthAdd external OAuth/OIDC identity provider integration where Next.js acts as the OAuth client. Creates OAuth pr
• add-filesScaffold the Buildpad Files module — a ready-made /files library (FileManager) and /files/[id] detail view (Fi
• add-fundraisingAdds one or more fundraising records to the Carta CRM via the Carta CRM MCP Server. Use this skill when the us
• add-gchatAdd Google Chat channel integration via Chat SDK.
• add-githubAdd GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
• add-goreleaser-homebrewAdd GoReleaser configuration and a GitHub Actions release workflow to an existing Go CLI project with Homebrew
• add-i18n-localeNaiveTab 浏览器扩展的 i18n 国际化开发指南。当用户要新增/修改翻译文本、添加多语言 key 时使用。涵盖中英文同步更新规则、变量替换模式等，防止遗漏或格式错误。
• add-imessageAdd iMessage to NanoClaw — one channel, two backends. Local (this Mac's chat.db via the Chat SDK bridge; macOS
• add-ingredientsAdds all prepared ingredients into the hot wok.
• add-integrationWalk through adding a custom MCP server integration to the plugin — searches npm for an existing MCP package (
• add-investorAdds one or more investor records to the Carta CRM via the Carta CRM MCP Server. Use this skill when the user
• add-journalAdd a new journal to the MedSci Skills profile database. Extracts metadata from author guidelines, generates w
• add-json-schema-association为特定 JSON 文件（按文件名/glob 匹配）接 schema 智能提示（补全/校验/hover）。当用户说打开某类 JSON 给专属提示、像 settings.json 那样为 *.xxx.json 配 schem
• add-karpathy-llm-wikiAdd a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "a
• add-leadAdd company/person/relationship to CRM
• add-linearAdd Linear channel integration via Chat SDK. Issue comment threads as conversations.
• add-llm-evalsUse this when adding evaluation to an LLM/agent app - measuring output quality (correctness, faithfulness, rel
• add-llm-fallbacksUse this to make an LLM app resilient to provider failures, rate limits, timeouts, and outages. Trigger on "ha
• add-llm-guardrailsUse this to add safety and security guardrails to an LLM/agent app - blocking prompt injection, PII leakage, j
• add-localeAdd a new UI language/locale to the claude-code-gui webview i18n system, or extend/verify an existing one. Wal
• add-macos-statusbarAdd a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether
• add-matrixAdd Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
• add-mechanicAdd game mechanics with correct GDScript 4.x patterns -- movement, health, inventory, save/load
• add-metricTRIGGER when user asks to add or modify a metric, counter, gauge, or histogram, or to track/measure an operati
• add-microappSet up a microapp architecture where one Main App and multiple micro-apps all share a single DaaS backend. Eac
• add-microfrontendSet up a micro-frontend architecture using client-side iframe composition. Creates a Main App that hosts indep
• add-mnemonAdd persistent graph-based memory via mnemon. Agents recall past context before responding and remember insigh
• add-multitenancyMulti-tenancy for DaaS applications — delegates to /manage-scope, the standard approach.
• add-new-entry-from-temp-mdWorkflow and tools for adding new entries from temp.md to the section files. Includes legend format, section r
• add-new-opc-skillChecklist and automation guide for adding a new skill to the OPC Skills project. Ensures all required files, m
• add-new-skills-to-workflowAdd new skills to an existing workflow and update all related documentation. Use when user wants to add skills
• add-noteAdds a note to a deal in the Carta CRM via the Carta CRM MCP Server; notes are stored as comments on the deal
• add-ollama-providerRoute a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic
• add-ollama-toolAdd Ollama MCP server so the container agent can call local models and optionally manage the Ollama model libr
• add-opencodeUse OpenCode as an agent provider. OpenRouter, OpenAI, Google, DeepSeek, etc. via OpenCode config — not the An
• add-partScaffold a new Starblaster Part (a slotted ship upgrade with Mk.1–9 scaling). Use when adding a new upgrade th
• add-primitiveAdd or modify AI primitive definitions in the data layer with correct typing and complete metadata. Use when a
• add-pro-featureCollaborative Context for Humans and AI
• add-prompt-enhancement-guideAuthor a prompt-enhancement system prompt for a new ecosystem and register/update it on the orchestrator's pro
• add-providerAdd a new AI provider to agentconfig.org's comparison system. Use when integrating a new coding assistant (e.g
• add-provider-docAdd documentation for a new AI provider — usage docs, env vars, Docker config, image resources.
• add-puzzle-typeScaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle modu
• add-rcpp-integrationAdd Rcpp or RcppArmadillo integration to an R package for high-performance C++ code. Covers setup, writing C++
• add-reportGuide for adding new report cards to ClaudeBar that analyze local data sources and display metrics with compar
• add-resendAdd Resend (email) channel integration via Chat SDK.
• add-rtkInstall rtk token-compression proxy into agent containers. Routes Bash tool calls through rtk for 60–90% token
• add-scrut-cli-testsSet up scrut snapshot-based CLI integration testing for a CLI project. Use when the user says "add scrut tests
• add-seed-skillsUse when adding or editing QA skills in seed-skills/ or getting them onto the live qaskills.sh catalog, e.g. "
• add-setting-envAdd server-side environment variables that control default values for user settings.
• add-signalAdd Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge.
• add-skill建立符合官方規格的 Claude Code skill：蒐集需求、產出正確格式的 SKILL.md、驗證命名與描述規則、套用 Progressive Disclosure 結構。適合在新增 skill 或 slash c
• add-slackAdd Slack channel integration via Chat SDK.
• add-speciesAdd species from the suggestions file to the fixtures and update the suggest script. Use when the user says "a
• add-subSubscribe to a skill event. Adds a subscription that injects context before or after a skill runs. Supports op
• add-tauri-commandUse when adding, renaming, or changing the signature of a Tauri command in src-tauri — any new IPC surface bet
• add-tavily-toolAdd Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when install
• add-teamsAdd Microsoft Teams channel integration via Chat SDK.
• add-telegramAdd Telegram channel integration via Chat SDK.
• add-temp-entries-to-sectionsClassification guidelines for entries in temp_entries.md. Each entry has a title containing the markdown file
• add-tipCollaborative Context for Humans and AI
• add-to-changelogUse when you've shipped a feature, fix, or breaking change and need to update CHANGELOG.md — follows Keep a Ch
• add-to-my-skillsCopy a newly created skill from another repo into this catalog, refresh the README and generated manifests, th
• add-to-xcodeREQUIRED: After creating ANY .swift, .m, .mm, .c, .cpp, or .h file in a directory containing a .xcodeproj, yo
• add-toolUse when adding a new cybersecurity tool to this installer. Walks through editing the right module file, addin
• add-tracker
• add-uint-supportAdd unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding
• add-usersScaffold the Buildpad Users module — ready-made /users, /roles, and /policies admin pages (UsersManager/UserDe
• add-vercelAdd Vercel deployment capability to NanoClaw agents. Installs the Vercel CLI in agent containers and sets up O
• add-webexAdd Webex channel integration via Chat SDK.
• add-wechatAdd WeChat (personal) channel integration via Tencent's official iLink Bot API. Uses long-polling and QR scan
• add-whatsappAdd WhatsApp channel via native Baileys adapter. Direct connection — no Chat SDK bridge. Uses QR code or pairi
• add-whatsapp-cloudAdd WhatsApp Business Cloud API channel via Chat SDK. Official Meta API.
• add-yourself-to-team-langfuseAdd a new team member to Langfuse's canonical team data and shared team table. Use when onboarding a new emplo
• addeventAddevent integration. Manage data, records, and automate workflows. Use when the user wants to interact with A
• addin-operationsTIA Portal Add-In development in Visual Studio Code: creating Add-In C# projects, adding Add-In templates, com
• adding-a-commandCreates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in
• adding-an-anchorUse when adding a new anchor integration to this project — creating an anchor client, its server singleton, AP
• adding-authenticationAdds token-based authentication to an app, with 5 real attack scenarios (tampering, expiry, wrong secret, algo
• adding-notesAdd notes to the knowledge repository. Use whenever the user provides content to save (commands, config, code,
• additive-agent-tool-surface-constructionMerge agent-specific tool sets (MCP clients + fetched tools) into the parent context without disrupting the pa
• address-github-commentsUse when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
• address-github-comments-v2Address GitHub Comments workflow skill. Use this skill when the user needs you need to address review or issue
• address-issueFetch a GitHub issue, analyze it, plan and execute the work in the current branch, and commit with issue refer
• address-pr-commentsFix, decline, or escalate the open review feedback on a pull request, pushing fixes to the PR's own branch and
• address-pr-comments-cecilStandard workflow to address pull request review comments in Cecil. Use when responding to review feedback, fi
• address-pr-reviewLook at the pull request review comments and address any issues raised.
• address-reviewParse a review document for actionable feedback items, work through them systematically, and track resolution
• address-sanitizerAddressSanitizer detects memory errors during fuzzing. Use when fuzzing C/C++ code to find buffer overflows an
• addressfinder-australiaAddressFinder Australia integration. Manage data, records, and automate workflows. Use when the user wants to
• addresszen-automationAutomate Addresszen tasks via Rube MCP (Composio). Always search tools first for current schemas.
• addsearchAddSearch integration. Manage data, records, and automate workflows. Use when the user wants to interact with
• addxai-architectUse when designing a new feature or system, making architecture decisions, writing technical design docs, or s
• addxai-code-reviewUse when reviewing code changes — MR/PR review, local commits, or uncommitted changes. Reviews document compli
• addyosmani-code-simplificationSimplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code wo
• addyosmani-frontend-ui-engineeringBuilds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces a
• addyosmani-idea-refineRefines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use wh
• addyosmani-interview-meExtracts what the user actually wants instead of what they think they should want. Achieves this through one-q
• addyosmani-quality6 web quality skills from Google Chrome's Addy Osmani: accessibility (WCAG), web quality audit (Lighthouse-sty
• addyosmani-tddDrives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use
• addyosmani/agent-skillsProduction-grade engineering skills for AI coding agents.
• addyosmani/web-quality-skillsAgent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.
• aden-hive/hiveMulti-Agent Harness for Production AI
• adeonir-debuggingGuide for debugging with targeted log injection and runtime analysis
• adeonir-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• adept-code-styleCross-harness AI skill portability CLI. Author an agent skill once, sync it into Claude Code, Cursor, Copilot,
• adept-contributingCross-harness AI skill portability CLI. Author an agent skill once, sync it into Claude Code, Cursor, Copilot,
• adept-self-improveCapture a durable lesson, correction, or convention from this session as a reusable adept skill, then sync it
• adept-writing-testsCross-harness AI skill portability CLI. Author an agent skill once, sync it into Claude Code, Cursor, Copilot,
• adequacy-assessmentGuides assessment of third-country adequacy decisions under GDPR Article 45 for international data transfers.
• adev-writing-guideComprehensive writing guide for Angular documentation (adev). Covers Google Technical Writing standards, Angul
• adhdFormats output for ADHD-friendly action — lead with the next step, number tasks, restate state, cut fluff. Use
• adhd-and-47-tabsUse when a user needs a direct, low-friction response for research, studying, writing, planning, decisions, ad
• adhd-daily-plannerTime-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in
• adhd-output-styleThis skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps",
• adhoc-flowWorkflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
• adhoc-gcalWrapper skill: inspect Google Calendar meetings and create draft-confirmed events.
• adhxADHX - X/Twitter Post Reader workflow skill. Use this skill when the user needs Fetch any X/Twitter post as cl
• adityakhetarpal235/MCP-Resume-EditorMCP server system for AI-driven resume customization through LibreOffice UNO, dual stdio/HTTP deployment, stru
• adityakhetarpal235/MCP-Server-CollectionCollection of purpose-built MCP servers for AI agent workflows.
• adjudication-sheetsBuild human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when:
• adka set of guidelines to build with Botpress's Agent Development Kit (ADK) - use these whenever you're tasked wi
• adk-agent-builderBuild production-ready AI agents using Google's Agent Development Kit with AI assistant integration, React pat
• adk-agent-patternsAgent architecture patterns for Google ADK 2.0 — when to reach for a single LlmAgent, a Workflow graph (new de
• adk-callbacks-hitlADK callback signatures, HITL approval gates, and state management — exact parameter names, before/after hooks
• adk-composio-tool-routerThe Composio Tool Router for ADK agents — the --with-composio scaffold flag, per-user sessions via composio.cr
• adk-cron-isolationBlast-radius control for scheduled (cron) runs of an ADK agent — scoped secrets, the headless tool-approval po
• adk-deploy-guideMUST READ before deploying any ADK agent to Google Cloud — covers Cloud Run, Agent Engine, Vertex AI, event-dr
• adk-fundamentalsFoundational knowledge for creating ADK (Agent Development Kit) agents including environment setup, project st
• adk-long-horizon-guardrailsHalt guards and command-safety guardrails for ADK agents — the shared halt latch, NoProgressGuard, RepeatedFai
• adk-long-horizon-sessionsSurviving long ADK runs — resumability so an interrupted invocation continues instead of restarting, and event
• adk-memory-self-improvementEXPERIMENTAL, opt-in memory self-improvement for long-lived ADK agents — relevance-conditioned preload, the pe
• adk-org-memory-retrievalScope-aware hierarchical memory for ADK agents via OrgMemoryService — wiring it through ADK's service registry
• adk-prompt-engineeringWriting effective ADK system prompts — dynamic instructions with InstructionProvider, state placeholders, cont
• adk-skill-creationCreating valid SKILL.md files following the agentskills.io specification — frontmatter, instructions, referenc
• adk-skill-design-patternsFive canonical skill design patterns for ADK agents: Tool Wrapper, Generator, Reviewer, Inversion, and Pipelin
• adk-streamingBuilding voice and video agents with Gemini Live API — bidirectional streaming via WebSocket, LiveRequestQueue
• adk-task-delegationDelegate work to sub-agents with the ADK 2.0 Task API — `mode='task'`, `mode='single_turn'`, `mode='chat'` on
• adk-tool-creationBuilding Google ADK function tools — ToolContext usage, proper signatures, error handling, return formats, typ
• adk-tool-scaffoldScaffolds a new custom Tool class for the Agent Development Kit (ADK).
• adk-workflow-graphsBuild graph-based agents with ADK 2.0 `Workflow` — declare nodes and edges, route conditionally, fan-out/fan-i
• adkarUse when the user wants an ADKAR analysis of a change, asks why a change is not sticking or not being adopted,
• adkitAI agent for managing Google Ads and Meta (Facebook & Instagram) Ads. Create and publish campaigns, ad sets/gr
• admapixAd intelligence & app analytics assistant. Search ad creatives, analyze apps, view rankings, track downloads/r
• admet-modeling-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• admin-reportsThis skill should be used when building or modifying a BO-style admin analytics report in majstorbg-admin (FE)
• admin-reviewReviews administrative case documents for procedural compliance across 38 checkpoints, covering filing, summon
• administering-linuxManage Linux systems covering systemd services, process management, filesystems, networking, performance tunin
• administrative-managerExpert administrative manager with 10+ years experience in office management, facilities coordination, vendor
• administrativo-administrativo-acao-anulatoria-de-ato-administrativoGera petição inicial completa de ação anulatória de ato administrativo ilegal, com pedido de tutela de urgênci
• administrativo-administrativo-acao-de-improbidade-administrativaGera petição inicial completa de Ação de Improbidade Administrativa ajuizada pelo Ministério Público ou pela p
• administrativo-administrativo-acao-popular-improbidade-lesao-ao-patrimonio-publicoGera petição inicial completa de Ação Popular para anular ato lesivo ao patrimônio público, à moralidade admin
• administrativo-administrativo-anulacao-de-ato-administrativoGera uma ação judicial (ordinária ou mandado de segurança, conforme o caso) para anulação de ato administrativ
• administrativo-administrativo-defesa-em-acao-de-improbidade-administrativaGera uma contestação completa em ação de improbidade administrativa, com preliminares, análise das tipificaçõe
• administrativo-administrativo-defesa-em-processo-administrativo-disciplinar-padGera uma defesa completa em Processo Administrativo Disciplinar (PAD) instaurado contra servidor público feder
• administrativo-administrativo-impugnacao-de-edital-de-licitacaoGera uma impugnação de edital de licitação completa e fundamentada, identificando cláusulas restritivas, ilega
• administrativo-administrativo-mandado-de-seguranca-contra-ato-administrativoGera petição inicial completa de Mandado de Segurança para atacar ato administrativo ilegal ou abusivo de auto
• administrativo-administrativo-mandado-de-seguranca-em-concurso-publicoGera um mandado de segurança em matéria de concurso público completo e fundamentado, com demonstração do direi
• administrativo-administrativo-pedido-de-acesso-a-informacao-lai-recursoGera tanto o pedido inicial de acesso à informação (via e-SIC ou protocolo físico) quanto o recurso administra
• administrativo-administrativo-recurso-administrativo-em-processo-licitatorioGera recurso administrativo completo em processo licitatório, atacando decisões de habilitação, inabilitação,
• administrativo-administrativo-recurso-contra-penalidade-em-contrato-administrativoGera recurso administrativo completo contra penalidades aplicadas pela Administração Pública em contratos admi
• administrativo-administrativo-recurso-de-auto-de-infracao-administrativoGera um recurso administrativo completo contra auto de infração lavrado por órgão regulador ou fiscalizatório
• administrativo-administrativo-recurso-licitatorioGera um recurso administrativo licitatório completo, contra decisões da comissão de licitação ou pregoeiro (in
• admob-ux-best-practicesAdMob banner and native ad placement best practices for mobile apps. Use this skill when the user asks to add,
• adobe-acrobat-signAdobe Acrobat Sign integration. Manage Users, Agreements, Widgets. Use when the user wants to interact with Ad
• adobe-automationAutomate Adobe tasks via Rube MCP (Composio). Always search tools first for current schemas.
• adobe-commerceAdobe Commerce integration. Manage data, records, and automate workflows. Use when the user wants to interact
• adobe-experience-manager-aem-apiAdobe Experience Manager (AEM) API skill. Use when working with Adobe Experience Manager (AEM) for system, lib
• adobe-illustrator-scriptingWrite, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when
• adobe-pdf-servicesAdobe PDF Services integration. Manage data, records, and automate workflows. Use when the user wants to inter