← ClaudeAtlas

portfolio-assessmentlisted

Use when assessing AI literacy across multiple repositories — aggregates individual assessments into a portfolio view with level distribution, shared gaps, outliers, and a prioritised improvement plan grouped by organisational impact. Discovers repos from local paths, GitHub orgs, or topic tags.
Habitat-Thinking/ai-literacy-superpowers · ★ 35 · Code & Development · score 65
Install: claude install-skill Habitat-Thinking/ai-literacy-superpowers
# Portfolio Assessment Aggregate AI literacy assessments across multiple repositories into an organisational portfolio view. Identifies shared gaps, outliers, and stale assessments, then generates an improvement plan grouped by impact scope (organisation-wide, cluster, individual). This skill reads existing assessment documents from individual repos. It does not run `/assess` remotely — each repo must be assessed individually first, or the lightweight scan estimates a level from observable evidence. ## Discovery Modes The skill discovers repos through three entry points, which can be combined. ### Local mode (`--local <path>`) Scan directories under the given path. Each subdirectory with a `.git` directory is treated as a repo. Check each for an `assessments/` directory. ### GitHub org mode (`--org <name>`) Use the GitHub CLI to list repos: ```bash gh repo list <name> --json name,url,topics --limit 200 ``` ### GitHub topic mode (`--topic <tag>`) Filter by topic tag. When combined with `--org`, scopes to that org: ```bash gh repo list <name> --topic <tag> --json name,url,topics --limit 200 ``` When used alone, searches repos accessible to the authenticated user: ```bash gh search repos --topic <tag> --json fullName,url --limit 200 ``` ### Combining modes When both `--local` and GitHub modes are provided, local repos take precedence — avoid re-fetching what is already cloned. Deduplicate by repo name. ## Process ### Step 1: Discover Repos Based on the provide