nolte-shared

Draft or refine an audience-tailored documentation artifact (README, release notes, MkDocs pages, or any doc whose governing spec lives under spec/project/) against an existing audience artifact from `audience-identify`. Invoke when the user asks to write, draft, or refactor a doc for specific audiences; also German requests. Needs an existing audience artifact — dispatch `audience-identify` first. Don't use for plugin skills/agents (`claude-plugin-developer`), spec authoring (`spec`), or a greenfield README (`readme-structure-apply`, which then dispatches this agent). Supports resume per `spec/claude/resumable-work/`.

Read-only review of an existing audience-analysis artifact against `spec/project/audience-identification/` (and, for release notes, release-notes-audience-analysis); produces a structured findings report, no edits. Invoke when the user asks to review, audit, validate, or check completeness of an audience list, or when a downstream gate (release-automation, readme-structure) must confirm a project's audience artifact is still compliant; also German requests. Don't use to create a new audience list — that's the `audience-identify` skill.

Draft a new nolte-shared plugin artifact (skill or agent) or refine an existing one in strict conformance with every spec under spec/claude/. Invoke when the user asks to author, scaffold, or draft a spec-compliant skill or agent; also German requests. Returns the drafted/edited files, the skill-vs-agent rationale, and a release checklist. Don't use for spec authoring (`spec`), pure structural validation, or interactive name/purpose scaffolding (`skill-management`, which chains here).

Scaffolds or refactors a Cookiecutter template (and its pre_prompt/pre_gen/post_gen hooks plus a pytest-cookies harness) so the rendered project conforms to the bound nolte spec corpus. Typically dispatched by the `cookiecutter-template-manage` skill for the authoring step. Returns created/edited files, a conformance audit, and a caller checklist. Supports resume on re-invocation per `spec/claude/resumable-work/`.

Read-only prose scanner that flags Markdown passages better expressed as a Mermaid diagram. Walks the in-scope set (default docs/<lang>/**/*.md), matches prose against the `spec/project/mermaid-diagrams/` diagram catalog (flowchart, C4Component, classDiagram, sequenceDiagram, erDiagram), and returns JSON findings (suggestion/info) persisted under .audits/diagram-opportunity/. Twin of `mermaid-diagram-reviewer`, which audits existing diagrams; this one audits prose for missing ones. Invoke when the user asks to review docs for missing diagrams or find visualization candidates; also German requests. Don't use to generate diagrams (`mermaid-diagrams-apply`) or rewrite prose (read-only).

Audits the repository's `README.md` against the canonical-language file under spec/project/readme-structure/ and, with per-item user approval, scaffolds or patches the file: H1 + tagline, CI badges, six required sections in order (Purpose, Usage, Structure, Related repositories, Status, License), the consumer-first ordering rule, the ≤200-line length budget, and link rules. Three operations: `audit` (read-only conformance report), `scaffold` (greenfield), `patch` (additive fix). Invoke when the user asks to apply, audit, scaffold, or patch the README against the spec; also handles equivalent German-language requests. Don't use for docs/ page content (`audience-doc-author`), MkDocs nav (`mkdocs-structure-apply`), Vale prose linting (`prose-vale-curator`), or the audience artefact (`audience-identify`). Supports resume on re-invocation per `spec/claude/resumable-work/`.

Augments the open release-drafter draft on develop with project-context-aware sections per the canonical-language file under spec/project/release-skill-layer/ §"Skill A — Draft notes curation". Reads the project's audience artefact, derives a section bundle from the detected project type, wraps the augmentation in stable HTML-comment markers so re-runs update in place, and writes the body back via `gh release edit` for a release tag. Invoke when the user asks to "curate the release notes", "shape the release notes for this repo", or the German "kuratiere die Release-Notes", "reichere den Release-Draft mit Projektkontext an". Don't use to publish the release (use `release-publish-trigger`), to identify audiences (use `audience-identify`), to draft notes from scratch (use the `audience-doc-author` agent), or to scaffold issue / PR templates (use `github-issue-templates-apply`). Supports resume on re-invocation per `spec/claude/resumable-work/`.

Review a Claude Code agent against spec/claude/agent-management/ and spec/claude/skill-vs-agent/, and emit an actionable review plan per spec/claude/review-plan/ under .audits/agent-review/ keyed by the target agent's name. Invoke when the user asks "review this agent", "audit a specific agent file", "check whether this agent is spec-compliant", or "agent review for a specific agent". Also handles closing an existing review plan once every item is addressed — "close the agent review plan for a specific agent". Also handles equivalent German-language requests. Do NOT use for skill review (use skill-review) or for pull-request-level review (`review` skill). Supports resume on re-invocation per `spec/claude/resumable-work/`.

Runs the audience-identification methodology from spec/project/audience-identification/ against a bounded context (software module, service, library, or whole project) and produces an authoritative audience artifact. Invoke when the user says things like "identify audiences for this module", "who are the consumers/users of X", "stakeholder identification for X", "audience analysis before I write the README / SLA / threat model", "list the audiences of this library", or equivalent German-language requests. Also triggers when another spec or skill (readme-structure, future SLA or threat-modeling specs) needs to reference an audience list that does not yet exist for the current context. Don't use to review an existing audience artifact for compliance (use audience-review). Supports resume on re-invocation per `spec/claude/resumable-work/`.

Generates a schema-valid Backstage catalog-info.yaml from an existing software project, conforming to spec/project/backstage-catalog-generation/. Inspects the repo (language/structure, remote slug, CODEOWNERS, OpenAPI/AsyncAPI/GraphQL/gRPC specs, colocated docs), infers the per-kind MUST-floor fields, confirms what it cannot infer (owner, spec.system, dependsOn, lifecycle) with the operator, writes the descriptor at the repo root, and self-validates. Invoke when the user asks to "generate a catalog-info.yaml", "onboard this repo into Backstage", "create a Backstage Software Catalog entity", "add this service to our developer portal", or German equivalents ("erzeuge eine catalog-info.yaml", "nimm dieses Repo in Backstage auf"). Optionally emits a Tech Radar TechRadarLoaderResponse JSON (never a catalog entity). Don't use to configure a Backstage backend / catalog.providers, install the Tech Radar UI plugin, or ingest Group/User org entities. Single-shot; resume not applicable.