All categories
DevOps & Cloud
Deployment, cloud, containers, CI/CD, monitoring, and infrastructure
- 20,283
- 846
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse devops & cloud skills
Showing 11,209–11,232 of 20,283 skills
- RlExplorationHackingSafetyAgent Agent--> <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE --> --- name: 'rl-exploration-hacking-safety-agent' description: 'Detect and mitigate exploration hacking, where LLMs strategically suppress exploration during RL post-training to resist capability elicitation and influence training outcomes.' measurable_outcome: 'Execute skill workflow successfully with valid output within 15 minutes.' allowed-tools: - read_file - run_shell_command - web_fetch ---Votes: 0GitHub stars: 6
- LlamaIndex Workflows 2026--> --- name: llamaindex-workflows-2026 description: Build event-driven LlamaIndex workflows for document and data agents with serving, human-in-the-loop checkpoints, and workflow observability. Use when retrieval-heavy or document-centric systems need explicit workflow control. measurable_outcome: Select a LlamaIndex workflow pattern, data boundary, and serving path for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- Google ADK 2026--> --- name: google-adk-2026 description: Build code-first agents with Google Agent Development Kit (ADK). Use when you need explicit orchestration, evaluation, and Google ecosystem alignment without giving up model flexibility. measurable_outcome: Select an ADK agent pattern, evaluation path, and deployment direction for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- DSPy 2026--> --- name: dspy-2026 description: Build and optimize modular LM programs with DSPy. Use when evaluation, compilation, prompt optimization, and metric-driven improvement matter more than adopting a full agent hosting runtime. measurable_outcome: Select a DSPy module graph, optimization strategy, and evaluation metric for a concrete workload within 30 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- OpenAI Apps SDK 2026--> --- name: openai-apps-sdk-2026 description: Build ChatGPT-native apps with the OpenAI Apps SDK, MCP-backed tool servers, widgets, app metadata, and submission-ready integration patterns. Use when the main task is building an app surface inside ChatGPT rather than a raw API-only workflow. measurable_outcome: Design or update an Apps SDK integration with a clear MCP server plan, widget strategy, metadata posture, and test path within 25 minutes. allowed-tools: - read_file - run_shell_comman...Votes: 0GitHub stars: 6
- Frontier OSS Models 2026--> --- name: frontier-oss-models-2026 description: Work with leading open or openly available model ecosystems from Meta, Mistral, DeepSeek, and xAI. Use when evaluating self-hosted or hybrid deployment paths, model tradeoffs, and integration patterns across non-single-vendor stacks. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- AWS Bedrock Operations 2026--> --- name: aws-bedrock-operations-2026 description: Build and run production workloads on Amazon Bedrock with current model access, IAM controls, and reliability guardrails. Use when implementing Bedrock inference pipelines, agent workflows, or model upgrades. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command ---Votes: 0GitHub stars: 6
- HealthcheckHost security hardening and risk-tolerance configuration for Velaclaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, Velaclaw cron scheduling for periodic checks, or version status checks on a machine running Velaclaw (laptop, workstation, Pi, VPS).Votes: 0GitHub stars: 110
- DiffsUse the diffs tool to produce real, shareable diffs (viewer URL, file artifact, or both) instead of manual edit summaries.Votes: 0GitHub stars: 110
- Omnistudio Field Mapping GovernanceGovern DataRaptor field mappings to prevent runtime errors when source metadata changes: naming, versioning, and dependency tracking. NOT for DataRaptor authoring fundamentals.Votes: 0GitHub stars: 3
- Omnistudio Deployment DatapacksUse when exporting, importing, or version-controlling OmniStudio components using DataPacks via the OmniStudio DataPacks tool or vlocity CLI. Covers DataPack export/import, Git version control integration, CI/CD for OmniStudio. NOT for SFDX-based metadata deployment of non-OmniStudio components.Votes: 0GitHub stars: 3
- Omnistudio Ci Cd PatternsUse when designing or implementing CI/CD pipelines for OmniStudio components — DataPack export/import, versioning, environment promotion, and automated deployment. NOT for standard Salesforce metadata CI/CD or Apex-only pipelines.Votes: 0GitHub stars: 3
- Omniscript VersioningUse when managing OmniScript versions: activating new versions, deactivating prior versions, testing a specific version before activation, rolling back to a previous version, or understanding version identity (Type/Subtype/Language triplet). NOT for OmniStudio deployment or DataPack migration (use omnistudio/omnistudio-deployment-datapacks).Votes: 0GitHub stars: 3
- Static Resources In LwcUse when packaging third-party JavaScript, CSS, or asset files into Salesforce static resources for Lightning Web Components, including `@salesforce/resourceUrl`, `loadScript`, `loadStyle`, zip pathing, versioning, and CSP-safe delivery. Triggers: 'static resource in lwc', 'loadScript not working', 'resourceUrl path in zip', 'third party library in salesforce'. NOT for npm-bundled code that should ship through the build pipeline or server-side integration assets.Votes: 0GitHub stars: 3
- Slack Workflow BuilderUse this skill when designing or troubleshooting Slack Workflow Builder workflows that call Salesforce — especially the Salesforce connector step Run a Flow, mapping inputs/outputs, handling failures, and understanding limits. Triggers on: Slack Workflow Builder Salesforce, Run a Flow from Slack, autolaunched flow from Slack, Slack automation calling Salesforce. NOT for Salesforce Flow Builder tutorials unrelated to Slack (use flow skills), not for Flow Core Actions that send Slack messages f...Votes: 0GitHub stars: 3
- Outbound Messages And CallbacksUse when implementing or troubleshooting Salesforce Outbound Messages — the workflow-triggered SOAP notification mechanism that pushes record field values to an external HTTPS endpoint. Trigger keywords: outbound message not delivering, configure outbound message endpoint, SOAP callback from Salesforce, workflow rule sends notification to external system, outbound message retry loop, acknowledgment SOAP response, session ID in outbound message. NOT for Platform Events, Change Data Capture, RE...Votes: 0GitHub stars: 3
- Mulesoft Salesforce ConnectorDesigning and configuring MuleSoft Anypoint Salesforce Connector flows: API selection (SOAP/REST/Bulk/Streaming), OAuth 2.0 JWT Bearer auth, watermark-based incremental sync with Object Store, batch processing with record-level error isolation, and replay topic subscriptions. Use when building Mule 4 flows that read from or write to Salesforce, migrating from Mule 3 watermark to Mule 4 Object Store, or troubleshooting connector authentication and API limits. NOT for native Salesforce-to-Sales...Votes: 0GitHub stars: 3
- Data Cloud Ingestion ApiUse when implementing or troubleshooting the Salesforce Data Cloud Ingestion API — covers streaming ingestion (near-real-time micro-batches), bulk ingestion (CSV-based full-replace jobs), schema management in OpenAPI 3.0.x YAML, Connected App setup with cdp_ingest_api scope, and error handling for both modes. NOT for standard Salesforce Bulk API, CRM Analytics data import, or Data Cloud data streams from CRM objects.Votes: 0GitHub stars: 3
- Pause Elements And Wait EventsUse this skill when designing or troubleshooting flows that need to suspend execution and wait for an external signal — either a time-based alarm or a platform event. Trigger keywords: pause element, wait element, flow interview suspension, alarm event, platform event resume, async interview. NOT for scheduled flows that recur on a fixed schedule (use scheduled-flows), and NOT for record-triggered flow scheduled paths on a single record (those are set in the Start element, not a Pause element).Votes: 0GitHub stars: 3
- Flow BulkificationUse when designing, reviewing, or troubleshooting Salesforce Flows that must survive data loads, integrations, or high-volume record changes without hitting transaction limits. Triggers: 'Get Records in loop', 'Flow bulkification', 'data loader causing flow errors', 'DML in loop', 'record-triggered flow scale'. NOT for general screen-flow UX or Flow type selection when scale is not the main risk.Votes: 0GitHub stars: 3
- Auto Launched Flow PatternsUse when invoking auto-launched Flows from Apex (Flow.Interview), from external systems via REST API, from Platform Events, or from other Flows (subflow element). Covers input/output variable mapping, bulkification patterns, and error/fault handling. NOT for record-triggered flows (use record-triggered-flow-patterns) or scheduled flows (use scheduled-flows).Votes: 0GitHub stars: 3
- Unlocked Package DevelopmentUse this skill when designing, creating, versioning, or installing unlocked packages: package directory configuration in sfdx-project.json, namespace management, package dependencies, version lifecycle (beta vs. released), ancestor versions, installation keys, and subscriber installation via sf CLI or Package Install UI. NOT for 2GP managed packages (ISV packaging with namespaces, push upgrades, or AppExchange listings), 1GP managed packages, change set deployments, or scratch org setup.Votes: 0GitHub stars: 3
- Source Tracking And Conflict ResolutionUse when diagnosing and resolving SFDX source-tracking conflicts between a local project and a Salesforce org — covering sf project pull/push/retrieve/deploy conflict errors, force overwrite decisions, tracking file corruption, and sandbox source-tracking enablement. Trigger keywords: source tracking, conflict, --force-overwrite, --ignore-conflicts, maxRevision.json, sf project retrieve, source:status. NOT for Git merge conflicts, DevOps Center pipeline conflicts, or change-set deployments.Votes: 0GitHub stars: 3
- Sfdx Monorepo PatternsStructure a single repo with multiple unlocked packages, shared templates, and cross-package test strategies. NOT for multi-repo org strategies.Votes: 0GitHub stars: 3