portfolio-auditlisted

Audits, renders, and bootstraps the cross-repository capability portfolio across `nolte/*` per `spec/portfolio/portfolio-management/`. Audit dispatches portfolio-manifest-collector agent for read-only inventory collection, then detects capability duplicates, surfaces gaps, verifies tech-stack consistency per `spec/portfolio/tech-stack/`, and writes a Findings-Report under `.audits/portfolio/` using Critical / Warning / Suggestion / Info severities. Render regenerates the aggregated inventory under the per-language docs/ portfolio subtree. Bootstrap creates a repository's first `project/portfolio.yml`. Invoke when the user asks to "audit the portfolio", "check for portfolio duplicates", "render the portfolio inventory", "discover the tech stack" (audit view), or equivalent German-language requests. Don't use to consolidate duplicates (operator opens cross-repo PRs), to author new capabilities, or for per-repo tech_stack capture or refresh (use tech-stack-capture). Supports resume on re-invocation.
nolte/claude-shared · ★ 0 · AI & Automation · score 76

Install: claude install-skill nolte/claude-shared

# Portfolio Audit Implements the `spec/portfolio/portfolio-management/` mechanics as a Claude Code skill in the `nolte-shared` plugin, plus the discovery half of `spec/portfolio/tech-stack-discovery/`. Four operations: **Audit** (the primary path, the reason the spec exists), **Render** (regenerate the docs-site portfolio inventory), **Bootstrap** (help a single repository author its first `project/portfolio.yml`), and **Discover tech stack** (run the tech-stack-discovery methodology against a single repository or across the portfolio). ## Why this is one skill, not four `spec/claude/skill-management/` §"Progressive disclosure & file references" generally favors keeping a skill to a single coherent unit of work. This skill bundles four operations because they share the same inputs (the per-repository `project/portfolio.yml` manifests collected via the GitHub API), the same domain vocabulary (capabilities, audiences, peers, ownership, portfolio scope), and the same output conventions (`review-plan`-format severities, the rendered inventory under `docs/<lang>/portfolio/`). Splitting them upfront would force four skills to re-implement the same manifest-collection plumbing and cross-validate the same vocabulary. If any of the four operations grows complex enough to need its own dedicated review surface — for example if "Render" sprouts a templating engine or "Bootstrap" needs an interactive multi-turn audience-mapping flow — split it into a sibling skill (`portfolio-inventor