agentsclimarketplace

Coverage

Skill opendatadiscovery/odd-team/.claude/skills/coverage

AI maintainer team for Open Data Discovery — coordinates audit, gap-closing, and sustainable maintenance across ODD repositories using navigation indexes, coverage-tracked scanners, and structured work items.

Install
npx -y skills add opendatadiscovery/odd-team --skill coverage

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Show scan coverage across all scanners — what's been analyzed, what remains, what changed since last scan.

SKILL.md

2.3 KB, 552 tokens by cl100k_base, as published. Nobody here has run it

Coverage Report

Show scan coverage status. If $ARGUMENTS is provided, show details for that specific scanner. Otherwise show summary across all scanners.

Protocol

Summary Mode (no arguments)

  1. List all manifests in state/coverage/
  2. For each, read and extract: scanner_id, total_items, scanned_items, coverage_pct, last_enumerated
  3. List scanners that have NO manifest yet (from scanners/ directory)
  4. Display:
## Scan Coverage

| Scanner | Coverage | Scanned | Total | Last Active | Stale? |
|---------|----------|---------|-------|-------------|--------|
| tests/collectors-adapters | 23% | 10 | 43 | 2026-04-20 | No |
| tests/collectors-sdk | 100% | 8 | 8 | 2026-04-19 | No |
| docs/accuracy/feature-behavior | 0% | 0 | 25 | - | - |
| ... | | | | | |

Not yet enumerated:
- scanners/docs/accuracy/architecture-drift.md
- scanners/docs/completeness/missing-limitations.md
- ...

Overall: X/Y items scanned across all scanners (Z%)
  1. Flag "stale" if last_enumerated is >7 days ago (repo may have new files)
  2. Recommend next action: enumerate un-manifested scanners, or continue scanning lowest-coverage ones

Detail Mode (scanner path provided)

  1. Read manifest for $ARGUMENTS
  2. Display:
    • Full item list grouped by status (scanned, not-scanned, changed-since-scan, new, error)
    • Dates and commit refs for scanned items
    • Suggested next batch (first 10-15 not-scanned items)
  3. Check if target repo has new commits since last enumeration:
    • git log --oneline {repo_commit_at_enumeration}..HEAD -- {scope paths}
    • If yes, recommend re-enumeration

Staleness Detection

A manifest is stale when:

  • last_enumerated is >7 days ago AND target repo has new commits since
  • Items marked scanned have files that changed (detected via git log)

Report: "N items may need re-scanning. Run /enumerate $ARGUMENTS to refresh."

Rules

  • This is read-only — never modify manifests, only report
  • If no manifests exist at all, explain the system and suggest starting with /enumerate
  • Show actionable next steps, not just numbers

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 327,069. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.