Everything in CAP

The repository the package declares has been deleted — verified against the GitHub API, not just a failed fetch. The package is still on npm, so it installs; the source it was published from is no longer readable, which is a harder thing to discover than a stale version number.

Provisioned per plan and per component, so capacity and cost are decisions taken before any model exists. And it is the database, not a warehouse — modelling, loading and cataloguing are the products above it, and reaching it directly bypasses every semantic they add.

The tools are documented as meant for AI models and not a stable API, so anything built to parse `cds-mcp` output rather than to feed a model can break between releases. Its corpus is the CAP documentation, so Fiori elements, BTP service or ABAP questions are not in what `search_docs` indexes.

It reads a UI5 project and the framework's own documentation, not a running system or a backend: a question about the service behind the app is answered somewhere else. Node.js v20.17 or v22.9 and above.

If your tool reads the open skill standard directly, install [capire/skills](artifact:capire-skills) and skip the wrapper.

No license Neither the package manifest nor the repository tree declares a licence.

Functional boundary There is no licence, so there is no grant to use or redistribute it. Everything else is secondary to that. Note too that its 'verified' claim means the skill text was checked against itself by an evaluation suite — not that the advice was run against a CAP version.

Local scaffolding only. Its own Out of Scope list names deployment to Cloud Foundry or Kyma, XSUAA and IAS configuration or any other BTP service binding, the SaaS Registry and subscription flow to real tenants, and automatic migration from the legacy `@sap/cds-mtx`. For the concepts rather than the scaffolding step, the README points at the `multitenancy` skill in [skillOverflow](artifact:dankromp-skilloverflow) by [Daniel Krompaß](actor:dankromp), which covers the MTX sidecar, `xs-security.json`, tenant lifecycle hooks and the deployment path and runs no commands at all.

Host-specific: outside Kiro the automatic context activation is the part that does not come with it, and what remains is prose you would have to wire in yourself. Breadth over depth by design — thirty-five skills across six product areas is an orientation layer, not a substitute for the focused sets in each.

GPL-3.0, which is a licence to read before vendoring any of it into something you ship. Forty plugins is also a lot of always-available surface — the ledger is there because breadth and verification pull in opposite directions, and it does not resolve that so much as report it.

Provisioned per plan and per component, so capacity and cost are decisions taken before any model exists. And it is the database, not a warehouse — modelling, loading and cataloguing are the products above it, and reaching it directly bypasses every semantic they add.

It says so itself, in bold, and the atlas repeats it: not legal advice and not a compliance decision. Only SAP, your contract, or SAP support can answer bindingly, and the skill routes legal, commercial and roadmap questions there rather than guessing at them. Treat the output as evidence gathered, not as a verdict.

SAP's own guidance is narrower than the service's reach: it names standalone, single-tenant applications that do not connect to other applications as the fit, and says to stay on [the HTML5 Application Repository](artifact:btp-html5-application-repository) and the application router where those meet your needs better. Four hard limits decide it before taste does — 300 requests per second per subaccount, ten retained versions per application, 100 MB per application and 400 MB for the deployment archive.

The tools are documented as meant for AI models and not a stable API, so anything built to parse `cds-mcp` output rather than to feed a model can break between releases. Its corpus is the CAP documentation, so Fiori elements, BTP service or ABAP questions are not in what `search_docs` indexes.

It reads documentation, never a system: nothing in it opens a package.json, a CDS model or an ABAP client, so a question about what your own project does has to be answered elsewhere. The offline half is only as fresh as the submodules the last build pinned, and the index answers where something is written down rather than which of two packages fits a task.

Neither suite has been run against an ABAP system: the reference backends are the framework transpiled to Node and cap2UI5 on CAP, so what a check does on a real system is open. The portable profile is a subset of 61 controls, filled from a census of 247 core apps of which 64.8 % run unchanged, so an app outside it renders placeholders in the terminal and Adaptive Cards renderers.