Skip to content

gaia-research/gaia-skill-tree / .agents/skills/ev-link-validation

ev-link-validation

Verified

Phase 4 of the Gaia evidence verification pipeline. Checks every URL in the evidence data lake for HTTP liveness — catches dead links (404, 403, timeout, connection errors) before evidence is ingested into the registry. Use this skill when running the full /ev-pipeline, asked to "validate links", "check evidence URLs", "run link validation", "find dead links in the data lake", "check HTTP status of evidence sources", or "verify evidence links still work". Wraps validate_sources.py as a temporary coexistence URL-health shim.

Link Validation (ev-link-validation)

Phase 4 validates URL health after by-type collection, live star verification, Phase 2B benchmark-source verification, and adversarial audit.

Type-First Evidence Lake Contract (#1148)

The evidence lake is type-first. The primary working set is evidence/by-type/<canonical-evidence-type>.md. Legacy evidence/tier_*.md files may still exist as coexistence artifacts, but they are not the semantic routing key.

Coexistence Shim

evidence/scripts/validate_sources.py intentionally remains a temporary coexistence URL-health shim. It reads evidence/by-type/*.md (primary, type-first) and evidence/tier_*.md (compatibility-only) by default (#1786).

python3 evidence/scripts/validate_sources.py

For benchmark rows, include every row/source URL plus catalog-level sourceUrl, methodologyUrl, harnessUrl, attestor URLs, and any candidate manifest methodology/attestor links in the URL-health pass.

For a small sample:

python3 evidence/scripts/validate_sources.py --limit 10

Targeting an intake's candidate rows (not yet in the lake)

A pre-registry intake's candidate rows aren't in evidence/by-type/ yet, so the default lake scan won't see them. Point the validator at them directly instead:

# Plain URL list, one per line
python3 evidence/scripts/validate_sources.py --urls /tmp/intake-urls.txt

# JSON/YAML candidate manifest — bare URL list, {"url": ...} objects, or an
# object with a urls/candidates/entries/rows list of either shape (same
# shape generate_source_dump.py's --candidate-manifest accepts, see
# ev-pipeline)
python3 evidence/scripts/validate_sources.py --manifest /tmp/intake-candidates.json

--urls and --manifest are mutually exclusive; --limit N and --report <path> apply in every mode.

Output

Write Firecrawl validation findings to the verification report and append a summary to the source report. Benchmark-source candidates remain candidate-only until Phase 2B findings, adversarial findings, and link-health results are reviewed by a human. For #1418 scratch multi-target peer-review partitions, validate the repeated URL once per reviewed skill row in peer-review.md when the source legitimately covers each target; the repetition is expected, not duplicate-noise by itself. Do not commit generated validation reports, scratch manifests, or generated partitions without human approval. Hand only live, correctly scoped rows to ingestion.

writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall