org-deps
Cross-Repo Dependency Audit
Check how packages in an org depend on each other and flag version mismatches.
Run from ~/code/{org}/ or pass the org name as an argument.
Can also run across multiple orgs (e.g. /org-deps epinowcast epiforecasts).
Helper script
A pre-built script at ~/.claude/scripts/org-deps.sh collects all dependency info in one pass.
Run it first to avoid spending tokens on file parsing.
~/.claude/scripts/org-deps.sh <org-name> [org-name2 ...] > /tmp/org-deps.json
If the script is missing or not executable, flag this to the user and stop.
The script outputs a JSON array with per-repo entries containing:
repo,org,gh_org,type,version,latest_release_tagdependenciesobject with R fields (depends,imports,suggests,remotes) or Julia fields (julia_deps,julia_compat)
Phase 1: Build dependency graph
From the script output, build a graph of which local packages depend on which other local packages.
Phase 2: Check for issues
Version mismatches
- Package A requires
primarycensored >= 1.0but local copy is on0.9.5 Remotespointing to branches that no longer exist[compat]bounds that exclude the latest release
Breaking changes
For each dependency edge, check if the upstream package has commits since the version pinned downstream that include:
- Breaking changes (search NEWS.md for "breaking", "removed", "deprecated")
- API changes (renamed exports, changed function signatures)
Stale pins
Downstream packages pinning old versions when newer ones are available on CRAN or in the org.
Phase 3: Report
Present:
- Dependency graph (text format showing who depends on whom)
- Table of issues found with severity (breaking/outdated/info)
- Suggested fixes
Phase 4: Fix (with confirmation)
For each confirmed fix:
- Create a worktree branch
- Update version constraints
- Run tests to verify compatibility
- Create a PR
Auto-Exit When Standalone
IMPORTANT: If this command is being run as a standalone request, automatically exit after completing all phases successfully.
More from seabbs/skills
analyzing-research-papers
Expert methodology for analyzing and summarizing research papers, extracting key contributions, methodological details, and contextualizing findings. Use when reading papers from PDFs, DOIs, or URLs to create structured summaries for researchers.
227academic-writing-standards
Expert knowledge of academic writing standards for peer-reviewed papers, including citation integrity, style compliance, clarity, and scientific writing best practices. Use when reviewing or editing academic manuscripts, papers, or research documentation.
54taskfile-automation
Expert guidance for using Task (taskfile.dev) automation tool to discover and execute project development commands
18issue-reply
Post a helpful reply to a GitHub issue
8paper-summary
Summarise an academic paper from URL, DOI, or file path
7literature-search
Search local bibliography files and Paperpile for relevant papers
7