测试与安全技能

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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).

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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).

中文简介正在准备中。当前显示原文说明。

Top-level orchestrator for the Gaia Skill Tree evidence verification pipeline. Run this when you want to do a full evidence pass — collecting raw sources, verifying live GitHub star counts, running Phase 2B benchmark-source verification, adversarially auditing for quality/formatting issues, and checking that every URL is reachable — all in one coordinated sequence. Trigger phrases: "run the evidence pipeline", "full evidence pass", "verify evidence", "evidence verification pipeline", "run ev-pipeline", "check all evidence", "audit the data lake", "evidence quality sweep", "refresh evidence", "validate evidence sources". Also aliased as /evidence-verification-pipeline. Use the individual sub-skills (ev-collection, ev-star-verification, ev-adversarial-audit, ev-link-validation) only when you need to re-run one phase in isolation; for end-to-end work, always start here.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

Comprehensive, reusable playbook for multi-component suite intake under Yggdrasil III. Audits component installability, maps origin candidates to generic capabilities, ingests named components with shared-repo baseline caps, manifests suites via gaia dev fuse, calibrates capstone and component ranks, and closes out via Class S regeneration.

中文简介正在准备中。当前显示原文说明。

Generate a prioritized review queue of registry skills and catalog items that need attention. Use this skill whenever someone asks: "what needs review?", "what's overdue for audit?", "where are the weak spots in the registry?", "what should I audit next?", "run a health check on the registry", "show me flagged skills", "find problems in the registry", "what skills need fixing?", or "triage the registry". This is the triage layer — it surfaces candidates ranked P0–P4 so that focused work (via /gaia-audit) targets the right things first. Run this before any audit pass. Also invoke proactively when a PR changes registry/named/ at scale, or before a release, to catch regressions early.

中文简介正在准备中。当前显示原文说明。

Run this skill for Phase 3 of the evidence verification pipeline — the adversarial audit step. Use when you need to check the evidence data lake for bad data before ingestion: dead links, wrong URL formats (tree/ vs blob/), subjective wording ("elite", "high-quality"), stale migration notes, benchmark catalog misuse/vendor-claim leakage, or skills whose star evidence conflicts with classified evidence level. Triggers on phrases like: "audit the data lake", "adversarial check", "ev-adversarial-audit", "check for noise in evidence", "flag bad evidence", "run the audit phase", "quality check the by-type files", or any reference to Phase 3 of the pipeline.

中文简介正在准备中。当前显示原文说明。

Phase 2B of the Gaia evidence verification pipeline. Verifies benchmark-result rows and benchmark-source candidates against registry/benchmark-sources.json before adversarial audit, link validation, catalog promotion, or ingestion. Use when running /ev-pipeline, checking benchmark-result evidence, reviewing benchmark-source candidates, or preparing benchmark rows for /gaia-ingest-batch.

中文简介正在准备中。当前显示原文说明。

Audit and repair Gaia user-tree timelines so every skill's current rank is explained by a chain of Hero's Journey events. Trigger this skill when: a contributor's profile chart shows a stale rank (e.g. still shows 3★ after a demotion to 1★); someone asks to "trace what happened" to a skill's rank; `validate_timelines.py` is failing in CI; you need to backfill missing `demote` or `rank_up` events before cutting a release; a skill was reclassified or Star-Bar-reset and the user tree was never updated; or any time the registry node and user tree disagree on a skill's current level. Uses `scripts/trace_timeline.py` (dry-run + apply) and `scripts/validate_timelines.py` (CI gate). Do NOT hand-edit `timeline[]` arrays — the script synthesises properly labelled events with `previousValue`/`newValue` so the rank chart plots correctly.

中文简介正在准备中。当前显示原文说明。