Architecture specialist for software/system design, module and service boundaries, tradeoff analysis, and stakeholder synthesis.
Backend specialist for APIs, databases, authentication with clean architecture (Repository/Service/Router pattern).
Database specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning,…
Use when setting up or optimizing developer workflows in a monorepo, managing mise tasks, git hooks, CI/CD pipelines, database migrations, or release automation.
Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment.
Intent-based observability + traceability router across layers, boundaries, and signals. Routes to vendor-specific skills via category taxonomy; owns transport tuning,…
Behavior-preserving refactoring specialist - plans and executes safe incremental restructuring with code smell / SATD / hotspot targeting, characterization-test safety nets,…
Infrastructure-as-code specialist for multi-cloud provisioning using Terraform across any provider (AWS, GCP, Azure, Oracle Cloud).
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize TP-Link Omada SDN Controller, REST OpenAPI, MongoDB bac — from…
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening an — from…
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening an — from…
Build and deliver a new website, web app, API, or Expo app created through omg.dev New Project or Quick Chat.
Signpost (not a knowledge pack) for OMG modelling specifications — UML, SysML, BPMN, UAF, SoaML, MOF, OCL, XMI, DDS.
[omh] Agent Debug workflow: capture a stuck, looping, drifting, or repeatedly failing agent run, diagnose the likely failure pattern, and prepare the smallest safe recovery…
[omh] Hermes AI slop cleaner workflow: delete AI-generated slop, dead code, and duplication while observable behavior stays identical.
[omh] Hermes Code Review workflow: bug-first review with evidence. Use when the user says: code-review, review, audit, find bugs, release gate, claim audit, evidence audit, README…
[omh] Hermes Deploy-and-Monitor workflow: release checklist, deploy decision, health signals, rollback gate, and post-deploy status.
Enforces coding best practices: deep-read before modify, LSP-first navigation, TDD red-green-refactor, minimal changes, self-review, verification.
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code.
Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.
Designing Omni-Channel capacity models for service orgs: agent capacity allocation, channel weighting (cases, chats, calls), skills matrix design, overflow strategy, presence…
Omni-expert principal software architect. Triggers on requests for app development, coding, refactoring, or architectural design.
Create and manage secure tunnels (ngrok, Cloudflare Tunnel, custom) to expose OmniRoute to the internet or share access with remote agents and CI pipelines.
Store, retrieve, and query knowledge, memory, and relationships in an Omnigraph graph, and operate a local or remote Omnigraph deployment.
Use when managing OmniScript versions: activating new versions, deactivating prior versions, testing a specific version before activation, rolling back to a previous version, or…
Configure caching on DataRaptors and Integration Procedures to cut response times, with cache-bust and freshness guarantees. NOT for platform-level org cache.
Use when designing or implementing CI/CD pipelines for OmniStudio components — DataPack export/import, versioning, environment promotion, and automated deployment.
Use when diagnosing failures, unexpected output, or silent errors in OmniScript, DataRaptor, or Integration Procedure assets.
Use when exporting, importing, or version-controlling OmniStudio components using DataPacks via the OmniStudio DataPacks tool or vlocity CLI.
Migrate classic Visualforce-based OmniScripts to LWC-based runtime with feature parity and regression testing. NOT for new OmniScript design.
Use when diagnosing or improving runtime performance in OmniStudio assets: slow OmniScripts, Integration Procedures with high latency, DataRaptor caching, excessive API call…
Use when OmniStudio components are degrading under high concurrent user load, when Integration Procedures are hitting governor limits at portal scale, or when designing an…
Use when testing or validating OmniStudio components — OmniScript preview, Integration Procedure step debugging, DataRaptor field-mapping validation, and end-to-end UTAM-based…
Architecture decision framework for choosing between OmniStudio and the standard Salesforce platform (Screen Flow, LWC, Apex) for guided UI and data orchestration use cases.
Delegate a coding task to Oh My Pi (`omp`) as a background implementer, then review its diff and land it yourself.
标准 SOP：OceanBase 社区版经 OMS 同步至 Kafka 的延迟、吞吐与调优。涵盖全量/增量并发与限速、KafkaSink、OMS 平台 limitator 与 JVM、源端 OB 与表结构策略；与 observer 日志、OBProxy、单条 SQL 深查 skill 分工明确。
Use at session start to detect available skills, load active context, and enforce skill usage discipline for the current session.
Generate onboarding guide with key symbols, architecture overview, and subject matter experts. Use when joining a new project, onboarding teammates, or creating project…
Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.
Inicializa novo projeto: cria AGENTS.md, CLAUDE.md, ERROR_LOG.md, PENDING_LOG.md, memory/MEMORY.md, docs/architecture/SPEC_FORMAT.md, docs/architecture/TDD.md.
Developer onboarding guide that composes architecture mapping, tooling review, and agentic setup review with setup, troubleshooting, and next-steps agents to produce a…
Optimize user onboarding to reduce time-to-value and increase activation rates. Design clear paths to the "aha moment" through checklists, product tours, educational content, and…
Three-pillar onboarding assistant for cluster, namespace, and app requests. Use when a user needs a guided interview that either triggers existing Argo WorkflowTemplates for…
Load this when authoring or refining a profile file for a TECHNICAL audience (developer, architect, tech lead, DevOps/SRE, QA, data engineer) under onboard/profiles/.
Run an AI-assisted PR review that validates issue linkage, local quality gates, manageable scope, and review comments.
Server-side data loading in One framework. Use when fetching data for pages, implementing caching, redirects, response headers, ISR, refetching, or file-driven content with…
Use when you need to stand up or standardize a fresh OpenClaw setup as the Fire Dragon Fruit Architecture: one strong main, one isolated rescue, layered file...
The One Codex Python Client provides an object-oriented API for accessing sample data, analyzing and visualizing results, and generating branded reports via Jupyter notebooks…
Set up CI/CD pipelines for OneNote integrations with Graph API testing and mock strategies. Use when configuring GitHub Actions, setting up test credentials, or building…
Decode and fix every common OneNote Graph API error with root cause analysis. Use when debugging 400, 403, 404, 429, 500, 502, or 507 errors from OneNote API.
Optimize costs and API usage for OneNote Graph API integrations with caching and batching strategies.
Generate comprehensive diagnostic bundles for OneNote Graph API issues with request tracing and token analysis.
Deploy OneNote integrations with MSAL token persistence, health checks, and container best practices.
Create your first OneNote notebook, section, and page with correct XHTML content. Use when starting a new OneNote integration or testing Graph API connectivity.
Production readiness checklist for OneNote Graph API integrations covering auth, rate limits, and failure modes.
Implement proper rate limit handling for OneNote Graph API with queue-based throttling. Use when building high-throughput OneNote integrations or debugging 429 errors.
Reference architecture for OneNote integrations covering all notebook locations and API path patterns.
Automate OneSignal tasks via Rube MCP (Composio). Always search tools first for current schemas. — from engineering/backend
Use when analyzing online algorithms, competitive analysis, adversarial input, list update with move-to-front, online caching, paging, randomized marking, or…
Onnx Converter - Auto-activating skill for ML Deployment. Triggers on: onnx converter, onnx converter Part of the ML Deployment skill category.