jfrog

Create JFrog project lifecycle policies that check for evidence existence on promotion or release events for applications with specific labels. Use when the user asks to create a policy, evidence policy, promotion policy, lifecycle policy, compliance check, or evidence validation for application promotions. Triggers on mentions of policy, evidence policy, promotion policy, lifecycle policy, compliance check, evidence validation, AppTrust promotion.

Detect existing project and repository naming patterns on the JFrog Platform before onboarding. Queries all projects and repos, analyzes naming conventions, and presents the user with a choice between following detected patterns or using the standard naming rules. Use before creating new projects or repositories.

Create Artifactory repositories (local, remote, virtual) for npm, Maven, PyPI, Go, Docker, and Helm ecosystems within a JFrog project. Supports ecosystem-based auto-generation, explicit custom repository definitions, or a smart merge of both. Use when the user needs to set up Artifactory repos, create package repositories, or configure artifact storage for a project.

Create users and groups on the JFrog Platform via REST API. Use when onboarding discovers missing users or groups, or when the user wants to create JFrog platform users/groups. Supports assigning users to groups during creation and setting a default password.

Set up JFrog Curation with protection policies on an existing JFrog Platform instance. Checks if Curation is enabled, collects a notification email, then creates security, license, and operational risk policies on remote repositories. The "Block Malicious" policy blocks downloads; all others run in dry-run (audit) mode. Use when the user wants to set up curation, onboard curation, enable curation protection, or block malicious packages.

Delete a JFrog project and all its repositories. Use when the user wants to remove, delete, or clean up a JFrog project, or mentions deleting JFrog resources.

Add users and groups to a JFrog Platform project with role assignments. Use when the user wants to manage project membership, add developers to a JFrog project, or assign roles to teams.

Configure OpenID Connect (OIDC) integration between GitHub Actions and JFrog Platform for secretless CI authentication. Checks subscription compatibility, creates OIDC providers, and sets up identity mappings per repository. Use when setting up OIDC for GitHub Actions workflows.

Identify Folio books with low on-hand stock so the operator can replenish before the title goes out of stock. Use whenever the user asks about books running low, low stock, restock list, what's almost gone, stock audit, or which titles need reordering.

Customer support and order operations for the Folio bookstore. Use whenever the user asks about a book, an order, a refund, a return, store credit, or anything else customer-facing. All canonical data lives behind the `folio` MCP server - never invent prices, stock counts, customer details, or order history.

Identify and surface every order currently in the `processing` state, so the operator can chase down stalled fulfilment. Use whenever the user asks about stalled orders, processing backlog, things stuck in processing, or orders that haven't shipped yet.

Look up customer orders through the orders_db MCP server. Use whenever the user asks about an order, a tracking number, a delivery, or a customer's purchase history.

Operate the belt CLI to evaluate headless coding agents (Claude Code, Cursor, Codex, Gemini, and others) end to end. Use when the user asks to write or run eval scenarios, compare agents, score outputs with rules or LLM judges, register a new agent adapter, interpret reports or benchmark cards, or set up evals in CI. Also use when the user mentions agent-belt, scenario JSON, BELT_ env vars, llm_scorer_instruction, llm_scorer_evidence_files, TurnExpectation, or benchmark cards.

Use when writing or debugging Python scripts for DAP blueprints — from dell import ctx, ctx_parameters, runtime_properties, NonRecoverableError, RecoverableError, REST client. Triggers — blueprint script, dell ctx.

Use when the user says "write a blueprint", "fix my blueprint", "create a deployment", "what node type", "how do I deploy", "blueprint won't validate", "lint this", "review this yaml", "add an input", "which plugin", "help me with TOSCA", "add update support", "support deployment update", "support drift", "add check_drift", "add reinstall", "make this updatable", "day 2", "babysit", "monitor", "did it pass", "did it fail", "last run", "any failures", "check status", "how to", "tutorial", "guide", "help me get started", "walk me through", "what are plugins", "how do I delete", "how do I create secret", or any request to write, review, debug, test, or get step-by-step help with blueprint YAML or DAP workflows. Also known as "Blueprint Assist" — triggers on "blueprint assist", "blueprint-assist", or "Blueprint Assist".

Use when composing services — ServiceComponent sub-deployments, SharedResource, chaining blueprints, get_environment_capability. Triggers — service component, sub-deployment, dell.nodes.ServiceComponent, or requests to chain deployments.

Use when updating a deployment — blueprint version bumps, input changes, skip_install/uninstall/reinstall, reinstall_list, force_reinstall, preview mode, drift check. Triggers — deployment update, node reinstall.

Discover, install, manage, and publish agent skills hosted in the JFrog AI Catalog (Artifactory skills repositories) using the JFrog CLI (`jf skills`) and the JFrog Agent Guard. Lists and searches available skills (catalog-wide or scoped to a project), shows a skill's versions and which repos host it, installs the latest or a pinned version, verifies the install, lists installed skills, updates and removes them, and publishes (uploads) a local skill bundle and releases new versions. Use when the user asks what skills are available or installed, to search/browse the catalog, to install/update/uninstall a skill, to see a skill's versions, or to publish/upload/release a skill to JFrog / Artifactory / the AI Catalog.

Interact with the JFrog Platform via the JFrog CLI, JFrog MCP server and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name. Do NOT use this skill to install, add, remove, list, or manage MCP servers.

Check JFrog Public Catalog and stored packages for a version, interpret catalog security signals, and download through Artifactory (JFrog Platform locations, remote cache, curation-aware package managers, or repo proxy). Use when the user asks whether a package is safe, allowed, curated, or wants to download npm, Maven, PyPI, Go, or similar packages via JFrog. Do NOT use for pure CVE or vulnerability lookups (e.g. "details on CVE-2021-23337") — those are handled by the jfrog skill's Public security domain queries without this workflow.

Discover, install, manage, and publish agent skills hosted in the JFrog AI Catalog (Artifactory skills repositories) using the JFrog CLI (`jf skills`) and the JFrog Agent Guard. Lists and searches available skills (catalog-wide or scoped to a project), shows a skill's versions and which repos host it, installs the latest or a pinned version, verifies the install, lists installed skills, updates and removes them, and publishes (uploads) a local skill bundle and releases new versions. Use when the user asks what skills are available or installed, to search/browse the catalog, to install/update/uninstall a skill, to see a skill's versions, or to publish/upload/release a skill to JFrog / Artifactory / the AI Catalog.

Interact with the JFrog Platform via the JFrog CLI, JFrog MCP server and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name. Do NOT use this skill to install, add, remove, list, or manage MCP servers.

Interact with the JFrog Platform via the JFrog CLI, JFrog MCP server and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name. Do NOT use this skill to install, add, remove, list, or manage MCP servers.