>-

>-

>-

>-

peekaboo

Build AI-native products with agency-control tradeoffs, calibration loops, and eval strategies. Use when building AI agents, LLM features, or products where AI handles user tasks autonomously. Part of the Modern Product Operating Model collection.

Run continuous discovery to find problems worth solving. Use when setting up weekly discovery rhythm, building Opportunity Solution Trees, creating interview snapshots, exploring solutions, or testing assumptions before committing engineering resources. Part of the Modern Product Operating Model collection.

Structured disagreement protocols that expose weaknesses, test assumptions, and generate alternatives. Use when stress-testing proposals, playing devil's advocate, challenging architectural decisions, or auditing assumptions before finalizing plans.

Use this skill when designing, cleaning, deduplicating, or documenting datasets for model training and evaluation including schema design, class imbalance handling, and train/val/test splits. Not for running model training or hyperparameter tuning. Not for real-time data pipeline engineering.

Validate that claims in documentation match codebase reality. Extracts verifiable assertions (file paths, commands, function references, behavioral claims, dependencies) from markdown docs and checks them against the actual project. Use after code changes, before releases, or when docs feel untrustworthy.

Systematic documentation audit and maintenance. This skill should be used when documentation may be stale, missing, or misorganized — after feature work, refactors, dependency upgrades, or as a periodic health check. It prescribes folder structure for docs/ and manual/, dispatches haiku subagents for codebase/doc scanning, and routes doc creation to specialized agents (reference-builder, technical-writer, learning-guide) with docs-architect as quality gate.

Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics design. Not for training or fine-tuning models. Not for dataset curation or benchmark comparison across publicly available models.

Use this skill when comparing AI or LLM models on benchmarks, capability, cost, latency, context window, or task-specific fit to help teams select the right model for their use case and budget. Not for training or fine-tuning models. Not for building eval frameworks from scratch.

OpenAPI 3.x specification design, schema patterns, and validation for REST API contracts. Use when creating or maintaining API specifications, generating documentation, or validating API contracts.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Optimize prompts for LLMs and AI systems with structured techniques, evaluation patterns, and synthetic test data generation. Use when building AI features, improving agent performance, or crafting system prompts.

Python testing patterns and best practices using pytest, mocking, and property-based testing. Use when writing unit tests, integration tests, or implementing test-driven development in Python projects.

Create exhaustive technical references, API documentation, and searchable reference materials. Use when building API docs, configuration references, or complete technical specifications.

Use when a repository needs cleanup of dead code, build artifacts, unused dependencies, outdated docs, or stale tests - provides safe cleanup workflows, validation steps, and reporting templates for code, deps, docs, tests, and sprint archives.

Stakeholder interviews, PRD structure, and scope definition for software requirements elicitation. Use when gathering requirements, defining project scope, or structuring product requirement documents.

Security testing patterns including SAST, DAST, penetration testing, and vulnerability assessment techniques. Use when implementing security testing pipelines, conducting security audits, or validating application security controls.

Use when designing system architecture, APIs, components, or data models - provides a structured design workflow with validation and documentation outputs.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Terraform infrastructure-as-code best practices for scalable and maintainable cloud infrastructure. Use when writing Terraform modules, managing infrastructure state, or implementing infrastructure automation at scale.

'Use this skill when planning or conducting user research, writing interview guides, designing surveys for UX insights, synthesizing qualitative findings, creating personas, or writing research reports. Trigger phrases: ''write a user interview guide'', ''how do I conduct usability testing'', ''synthesize research findings'', ''create a user persona'', ''design a UX survey''. Not for quantitative market sizing (use market-researcher), writing business requirements (use business-analyst), or product analytics.'

Use when activating visual showcase modes (supersaiyan, kamehameha, over9000) for UI or interaction design - provides mode-specific enhancement checklists.

Systematic approach to identifying, fixing, and validating bug fixes. Use when fixing bugs, resolving issues, or addressing errors.

Complete feature development workflow from design to deployment. Use when implementing new features or functionality.

Use this skill when planning or executing the human side of an Agentforce or Einstein AI feature rollout — user trust-building, AI-specific training, structured feedback collection via the Feedback API, and adoption measurement via Agentforce Analytics. NOT for general Salesforce rollout change management with no AI component, generic user training design, or CRM adoption without an AI feature in scope.

Use this skill when driving adoption of CRM Analytics (Einstein Analytics) across an org — including setting up the Analytics Adoption App to measure who uses which dashboards, embedding analytics into Lightning pages for in-context discovery, pinning dashboards to the Analytics home page, building self-service personas, and defining analytics-specific success metrics. Triggers: analytics adoption, dashboard usage tracking, embedded analytics strategy, self-service analytics enablement, CRM Analytics rollout. NOT for general Salesforce change management (use change-management-and-training), NOT for In-App Guidance prompt mechanics (use in-app-guidance-and-walkthroughs), NOT for dashboard technical design or JSON (use analytics-dashboard-design or analytics-dashboard-json).

Use when designing or troubleshooting CRM Analytics dashboards — chart types, bindings, faceting, dashboard interactions, mobile layout, and filters. NOT for standard Salesforce reports and dashboards.

Use when creating or managing CRM Analytics datasets: configuring dataflows, scheduling refreshes, selecting fields, handling date types, managing row-count growth, or troubleshooting stale or broken datasets. Triggers: 'dataset creation', 'dataflow schedule', 'dataflow quota', 'date field not filterable', 'dataset row limit', 'CRM Analytics data refresh', 'field type mismatch in dataset'. NOT for standard Salesforce report types or choosing between analytics tools.

Use this skill to define, document, and validate KPI metrics for CRM Analytics — covering metric formula design, dimension selection, target-dataset modeling, benchmark setting, and the KPI register that must exist before any dashboard or lens is built. Trigger keywords: KPI definition CRM Analytics, analytics metric design, analytics target attainment, CRM Analytics measures vs dimensions, analytics benchmark. NOT for building CRM Analytics dashboards or lenses (use analytics/dashboard-design), SOQL report KPI design, or Marketing Cloud analytics KPI work.

Use this skill to elicit, document, and validate CRM Analytics requirements — covering data source mapping (Salesforce object sync vs external connector vs Data Cloud), transformation needs, audience-specific lens or dashboard views, and drill-down path specifications — before any dataset or dashboard is built. Trigger keywords: CRM Analytics requirements, analytics data source mapping, CRM Analytics audience requirements, analytics visualization requirements. NOT for standard Salesforce Reports and Dashboards requirements, CRM Analytics implementation, SAQL query development, or KPI formula definition (use analytics-kpi-definition).

Use this skill when designing the FSC client onboarding process — mapping document collection touchpoints, approval steps, compliance checkpoint sequencing, and welcome journey handoffs. Trigger keywords: client onboarding design, onboarding workflow requirements, document collection flow, compliance checkpoint, welcome journey, intake process design. NOT for Action Plan template configuration mechanics, OmniStudio component implementation, or Flow builder steps — use fsc-action-plans for template setup details.

Use this skill when defining clinical data model requirements for Health Cloud: HL7/FHIR data mapping, interoperability requirements, FHIR R4-aligned object activation, CodeableConcept constraints, and middleware translation requirements. NOT for data migration procedures, Apex integration code, or generic data architecture unrelated to clinical interoperability.

Use this skill when setting up, configuring, or troubleshooting Salesforce Collaborative Forecasts: forecast types, forecast categories, rollup methods, quota management, forecast hierarchy, manager adjustments, and pipeline inspection integration. Trigger keywords: forecast type, forecast category, cumulative rollup, individual rollup, quota, forecast adjustment, forecast hierarchy, opportunity splits forecasting, pipeline forecast. NOT for custom report-based forecasting. NOT for Classic Forecasts (Customizable Forecasting). NOT for Territory Management setup (use enterprise-territory-management skill).

Declarative setup of Compliant Data Sharing (CDS) in Financial Services Cloud: enabling CDS per-object in IndustriesSettings, configuring OWDs, creating CDS permissions, adding the Financial Deal Participants related list, and defining Participant Roles. Trigger keywords: ethical walls, compliant data sharing setup, FSC sharing model, isolate banking teams, participant roles. NOT for standard Salesforce sharing rules, OWD, or role hierarchy sharing. NOT for programmatic participant record DML (use fsc-compliant-sharing-api instead).

Use when designing deployable Salesforce configuration with Custom Metadata Types, especially when choosing between CMTs, Custom Settings, and Custom Objects, protecting packaged defaults, or exposing config to Apex, Flow, and formulas. Triggers: 'custom metadata vs custom settings', 'deployable config', 'protected custom metadata', 'feature flags in Salesforce'. NOT for high-churn transactional data, user-managed business records, or secret storage that should live in Named Credentials.

Use this skill when designing data stories and narrative-driven analytics experiences in Salesforce: structuring CRM Analytics dashboards for executive communication, using text widgets and conditional highlights for contextual annotation, building sequential narrative in Tableau Story sheets, or using Einstein Discovery narrative REST API endpoints for machine-generated insight text. Trigger keywords: data storytelling dashboard, executive analytics narrative, CRM Analytics text widget annotation, Tableau story sheet, smart data discovery narrative API. NOT for technical chart-type selection, SAQL query construction, recipe node configuration, or CRM Analytics field binding mechanics.

Use when configuring delegated administration to allow non-system-admin users to manage specific user groups, reset passwords, assign permission sets, or administer custom objects. NOT for user management (use user-management) or full system admin setup.

Requirements mapping for the full donor lifecycle in NPSP or Nonprofit Cloud: acquisition stage design, moves management for cultivation and solicitation, upgrade path design, lapsed donor re-engagement strategy, and segmentation for portfolio management. NOT for marketing automation execution, email campaign configuration, or recurring donation implementation.

Configure Einstein Activity Capture (EAC) for an org: enable the feature, create Configuration profiles, set auth type (User-Level or Org-Level OAuth), define email and calendar sync scope, configure excluded domains and privacy settings, assign users, and verify sync health. NOT for manual activity logging, Einstein Opportunity Scoring setup, Pipeline Inspection, or troubleshooting email deliverability outside EAC.

Use when building, configuring, or troubleshooting email sends in Marketing Cloud Email Studio and Content Builder. Triggers: 'dynamic content', 'send classification', 'A/B test email', 'Content Builder template', 'triggered send', 'suppression list', 'Commercial vs Transactional'. NOT for MCAE (Pardot) email, SMS/push channel setup, or Journey Builder orchestration design.

Use this skill to gather, document, and validate FlexCard layout requirements before development begins — covering data visualization needs, action requirements, embedded component specifications, and user context mapping. Trigger keywords: FlexCard requirements, FlexCard BA, FlexCard layout design, FlexCard data sources, FlexCard actions. NOT for FlexCard development implementation, Card Designer configuration, or standard Lightning component requirements.

Use this skill to design, configure, and troubleshoot the Field Service Lightning (FSL) Optimizer — including selecting optimization type (Global, In-Day, Resource Schedule), understanding the priority-score model, configuring travel mode (Aerial vs Street-Level Routing), and tuning optimizer behavior for specific scheduling objectives. NOT for configuring scheduling policies, work rules, service objectives weights, or the Dispatcher Console dispatch settings.

Use this skill when configuring object-specific quick actions or global actions in Salesforce: choosing between action types, editing action layouts, pre-filling fields with predefined values, and adding actions to Lightning page layouts or mobile navigation. Trigger keywords: quick action, global action, action layout, pre-fill fields, predefined values, Salesforce mobile actions. NOT for Flow-triggered actions or Next Best Action recommendations (use flow/* or agentforce skills). NOT for Apex-defined actions.

Use this skill when configuring patient or member records in Salesforce Health Cloud — including Person Account enablement, Health Cloud patient record type creation, care team role configuration, patient card customization, and clinical data display. Trigger keywords: patient setup, Health Cloud person account, patient card component, care team roles, clinical data display. NOT for standard account setup, general CRM contact configuration, or non-Health-Cloud person account questions.

Operational setup guide for Salesforce Energy and Utilities Cloud: license activation, permission sets, industry-specific object configuration (ServicePoint, Meter, MeterReading, Consumption, ServiceAccount, ServiceContract, RatePlan), CIS/billing system integration, and service order management. NOT for generic admin setup, NOT for reading or querying the E&U data model schema (use architect/industries-data-model for that).

Use this skill to configure Salesforce Industries Insurance (Financial Services Cloud Insurance) including permission set licenses, irreversible org settings, core insurance objects, coverage types, claim configuration, and OmniScript-based quoting using the Insurance Product Administration API. Trigger keywords: insurance setup, FSC Insurance, InsurancePolicy object, InsurancePolicyCoverage, policy quoting OmniScript, claim type configuration, InsProductService, Digital Insurance Platform, many-to-many policy, multiple producers. NOT for generic OmniStudio setup, standard CPQ/Pricebook quoting, Health Cloud enrollment, or general FSC configuration unrelated to insurance line-of-business.