テスト設計、脆弱性診断、品質保証（1.3万 件）
Use when configuring Remote Site Settings to allow Apex callouts to external URLs, or distinguishing them from CSP Trusted Sites for Lightning component resource loading. NOT for storing an endpoint and its auth as a Named Credential — use integration/named-credentials-setup. NOT for allow-listing a URL the browser itself loads (script, iframe, fetch) — use security/csp-and-trusted-urls.
日本語の概要は準備中です。原文の説明を表示しています。
Use when an assignment must expire on a date, not stand forever. Trigger keywords: permission set expiration date, permission set group expiry, temporary access, time-boxed elevation, contractor access, ExpirationDate. NOT for PSG composition - use admin/permission-set-group-composition. NOT for muting mechanics - use security/permission-set-groups-and-muting. NOT for criteria-based auto-assignment - use admin/user-access-policies.
日本語の概要は準備中です。原文の説明を表示しています。
Use when designing or auditing Salesforce access control — deciding between Profiles, Permission Sets, and Permission Set Groups. Triggers: 'user can't see field', 'too many profiles', 'permission model', 'least privilege', 'profile migration', 'what stays on the profile', 'profile only settings', 'login hours permission set', 'layout assignment permission set', 'IsOwnedByProfile', 'profile retrieve empty'. NOT for sharing rules or record-level access — use admin/sharing-and-visibility for that.
日本語の概要は準備中です。原文の説明を表示しています。
Use when designing, auditing, or simplifying Record Types and Page Layouts. Triggers: 'record type', 'page layout', 'different picklist values', 'different fields per team', 'dynamic forms', 'business process', 'recordTypeVisibilities', 'layoutAssignments', 'record type deploy failed', 'businessProcess required', 'layout assignment matrix'. NOT for layout explosion across many profiles — use admin/record-type-strategy-at-scale. NOT for sharing rules — use admin/sharing-and-visibility. NOT for FLS — use admin/permission-sets-vs-profiles.
日本語の概要は準備中です。原文の説明を表示しています。
Build Salesforce-anchored personas and journey maps where every persona ties to a Permission Set Group, primary record types, list views, dashboards, automation, and a measured mobile/desktop posture, and journeys walk each task end-to-end with friction tags that drive UX decisions. NOT for stakeholder authority / RACI (use admin/stakeholder-raci-for-sf-projects), NOT for system-side process flows (use admin/process-flow-as-is-to-be), NOT for Lightning page design itself (use admin/lightning-app-builder-advanced or the lightning-record-page-auditor agent), NOT for pure design / UX research disconnected from org artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Use when configuring org-wide platform settings: MFA enforcement, My Domain setup and deployment, session timeout and security settings, password policies, trusted IP ranges (Network Access), and CSP Trusted Sites. Owns these settings as deployable Settings metadata (Security.settings, MyDomain.settings, Company.settings, Language.settings) and the order in which a new org is stood up. Trigger keywords: 'MFA setup', 'My Domain', 'session settings', 'password policy', 'trusted IP ranges', 'CSP trusted sites', 'Security.settings', 'SecuritySettings metadata', 'MyDomainSettings', 'settings-meta.xml', 'enhanced domains', 'deploy org settings', 'new org setup order', 'sessionTimeout enum', 'lockSessionsToIp', 'enableAdminLoginAsAnyUser'. NOT for user-level login restrictions (use user-management), NOT for permission model design (use permission-sets-vs-profiles), NOT for security audit and hardening review (use security/org-hardening-and-baseline-config).
日本語の概要は準備中です。原文の説明を表示しています。
Use when setting up, configuring, or troubleshooting Marketing Cloud Journey Builder — including entry sources, activities, decision splits, wait activities, goals, exit criteria, journey versions, test mode, or journey analytics. Triggers: 'journey builder setup', 'entry source configuration', 'decision split not routing', 'exit criteria not removing contacts', 'goal not tracking conversion', 'journey version publishing', 'journey re-entry settings', 'wait activity date field'. NOT for coding a custom activity or entry source — use apex/marketing-cloud-custom-activities. NOT for business units and sender profiles — use admin/marketing-cloud-engagement-setup.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a subscriber admin is installing, upgrading, or rolling back a managed package (1GP or 2GP) sourced from AppExchange or a private install URL — covers pre-install evaluation, sandbox dry runs, license and dependency checks, the install/upgrade audit trail, post-install configuration the package's InstallHandler cannot perform, and uninstall fallback. NOT for building managed packages as an ISV (use devops/managed-package-development), unlocked-package development (use devops/unlocked-package-development), or AppExchange listing setup. Trigger keywords: InstalledPackage, installedPackages, securityType, activateRSS, sf package install, sf package installed list, PackageLicense, UserPackageLicense, AllowedLicenses, UsedLicenses, push upgrade, PackageSubscriber, namespace prefix, 04t, certified managed package limits.
日本語の概要は準備中です。原文の説明を表示しています。
Use when designing, reviewing, or debugging Salesforce Flows from an Admin perspective. Triggers: 'flow', 'automation', 'record-triggered flow', 'screen flow', 'scheduled flow', 'flow error', 'flow interview', 'before-save vs after-save', 'flow deployed as draft', 'entry criteria', 'fault connector', 'flow-meta.xml', 'FlowDefinitionView'. NOT for Flow debug mode, Run As user, or Flow test suites — use flow/flow-debugging. NOT for building an OmniStudio OmniScript — use omnistudio/omniscript-design-patterns.
日本語の概要は準備中です。原文の説明を表示しています。
Configure and manage Field Service Lightning inventory: ProductItem (stock at locations), ProductTransfer (stock movement), ProductConsumed (parts used on work orders), ProductRequest/ProductRequestLineItem (replenishment ordering), ProductItemTransaction (audit trail). NOT for work orders, work types, or service appointments — use admin/fsl-work-order-management. NOT for ERP parts and inventory sync — use architect/fsl-integration-patterns. NOT for Omnichannel Inventory (OCI) — use architect/order-management-architecture.
日本語の概要は準備中です。原文の説明を表示しています。
Migrating standard Lightning Record Page layouts (Page Layouts on the Record Detail component) to Dynamic Forms — converting fields and sections to component-level placement, replacing record-type-driven layouts with field-visibility filters, retaining or replacing Quick Action layouts, planning custom-object vs standard-object rollout, and verifying field-level security and Reading View parity. NOT for Dynamic Forms initial setup (use admin/dynamic-forms-and-actions) or Lightning Record Page design from scratch (use admin/lightning-app-builder-advanced).
日本語の概要は準備中です。原文の説明を表示しています。
Use when choosing between Custom Metadata Types and Custom Settings, understanding hierarchical vs list settings, deployment behavior, governor limit implications, or accessing either from Apex and Flow. Trigger keywords: 'custom metadata vs custom settings', 'hierarchical settings per user profile', 'deployable config vs runtime settings', 'getValues getInstance in apex', 'flow get records custom settings'. NOT for modelling the CMT itself or protecting packaged defaults — use admin/custom-metadata-types. NOT for records users edit as business data — use admin/object-creation-and-design. NOT for secrets — use integration/named-credentials-setup. More trigger keywords: customSettingsType, customSettingsVisibility, SetupOwnerId, getOrgDefaults, getAll, DUPLICATE_VALUE in test, SeeAllData custom settings, enableAdvancedCSSecurity, customSettingAccesses, org default profile user override.
日本語の概要は準備中です。原文の説明を表示しています。
Use when creating, assigning, or checking custom permissions to control feature access beyond CRUD and FLS. Trigger keywords: 'custom permission', 'FeatureManagement.checkPermission', '$Permission global variable', 'feature gate', 'named access grant', 'beta feature flag', 'SetupEntityAccess', 'requiredPermission', 'who has this custom permission'. NOT for gating Apex service code and its tests — use apex/apex-custom-permissions-check. NOT for permission set design — use admin/permission-set-architecture.
日本語の概要は準備中です。原文の説明を表示しています。
Use when creating a new custom field on any Salesforce object: choosing field type, setting API name, configuring Field-Level Security, adding to page layouts, and deploying. Triggers: 'add a field', 'new custom field', 'what field type should I use', 'FLS not working', 'field not showing on page layout'. NOT for creating the object itself - use admin/object-creation-and-design. NOT for formula field logic - use admin/formula-fields. NOT for picklist value set management - use admin/picklist-and-value-sets. Also covers: field-meta.xml, CustomField metadata, deleteConstraint, externalId, unique, precision and scale, relationshipOrder, writeRequiresMasterRead, fieldPermissions, package.xml for fields.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when defining AI governance policies, designing human oversight workflows, documenting bias mitigation strategies, or meeting regulatory transparency requirements for Salesforce AI features. Trigger keywords: responsible AI, AI bias, AI audit trail, AI transparency, human-in-the-loop, AI risk inventory, AI disclosure. NOT for the MLOps pipeline or Policy-as-Code engine architecture — use architect/ai-governance-architecture. NOT for Trust Layer technical configuration — use agentforce/einstein-trust-layer.
日本語の概要は準備中です。原文の説明を表示しています。
Router for the 49 SfSkills `security` skill packages. Platform security and compliance: org hardening, encryption, session policy, MFA, monitoring, incident response, and TROUBLESHOOTING a specific record-access denial. Designing the sharing model itself (OWD, role hierarchy, sharing rules) is salesforce-admin. Use when the request mentions security, org hardening, Shield, platform encryption, field audit trail, MFA, SSO, SAML, session policy, guest user, event monitoring, GDPR, XSS, injection, why can this one user see this record, Apex managed sharing, sharing recalculation. Finds and opens the exact skill package to read; it does not contain the guidance itself.
日本語の概要は準備中です。原文の説明を表示しています。
Design, implement, or audit a Change Advisory Board (CAB) process for Salesforce deployments: change classification (standard, normal, emergency), required approvals, deployment gate sequencing, and integration with external ITSM tooling. NOT for scoring how risky one release is - use admin/deployment-risk-assessment. NOT for executing or troubleshooting the deployment itself - use admin/change-management-and-deployment. Also covers: the CAB charter (membership, quorum, decision rights), the CAB decision record artefact and its linter, the change classification matrix, the deployOptions a CAB decision pins (checkOnly, testLevel, rollbackOnError, ignoreWarnings, runTests), the 10-day quick-deploy validity window, the deploy-window vs freeze-register check, and the emergency (ECAB) path with its mandatory retrospective.
日本語の概要は準備中です。原文の説明を表示しています。
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
日本語の概要は準備中です。原文の説明を表示しています。
Run bounded, read-only semantic advisory sidecar passes for candidate mapping, issue triage, upstream diffs, evidence verification triage, and meta audit hints. Enforces monthly spend limits with explicit fallback to worker-luna.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when the user wants to turn code graph analysis into tracked GitHub issues — "audit the architecture", "find god nodes", "triage architectural debt", "run graphify and log issues", "what's over-coupled in this codebase", "create issues from graphify findings", "check for structural problems", "scan for architectural smells", or any request that combines codebase topology analysis with issue tracking. This skill runs graphify to build a dependency graph, parses GRAPH_REPORT.md for god nodes and structural patterns, converts findings into GitHub issue payloads, and optionally pushes them to the repo. It bridges static analysis and project management in a single automated pass. Requires graphify and gh CLI.
日本語の概要は準備中です。原文の説明を表示しています。
Explore a feature or CLI, repair verified defects, review adversarially, and leave one existing or new PR ready for its authorized reviewer. Use for "explore X", "test and ship X", "run the pipeline on X", "stress-test X", or "take X through the full pipeline" when exploration and integration matter. Supports lean autonomous, structured economy (default), and explicit hard-gated runs. Routine checkpoints do not require user approval; actual founder, L4, security, schema and merge gates always apply. Not for a one-file edit with no exploration need. Uses scripts/state.sh for resumable checkpoints.
日本語の概要は準備中です。原文の説明を表示しています。
Phase 1 of the Gaia evidence verification pipeline. Use this skill whenever you need to gather, consolidate, or refresh raw evidence for named skills in the registry. Trigger phrases: "collect evidence", "populate the data lake", "gather sources", "run ev-collection", "Phase 1", "compile the evidence index", "refresh the unified lake", "aggregate skill evidence", "build the evidence database". Also invoke as the first step before running ev-star-verification, ev-adversarial-audit, or ev-link-validation — nothing downstream is meaningful without a fresh, compiled index. Covers GitHub repo links, stargazer signals, YouTube showcases, arXiv papers, peer reviews, benchmark results, blog/newsletter posts, and self-attestation artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Appraise the complete post-ingest Gaia tree: run 13 deterministic audit dimensions, recompute evidence, Trust Magnitude and rank eligibility, use Jev/Luna for bounded semantic review, adversarially verify findings, and report structural proposals. Gaia computes authority; Jev is read-only advice; humans ratify all mutations. Use for a registry-wide sweep, full meta audit, evidence/rank review, fusion candidates, generic proposals, or a durable findings report. This is the macro companion to /gaia-meta-audit (prioritized queue) and /gaia-audit (single skill).
日本語の概要は準備中です。原文の説明を表示しています。