publisher profilecommunity

underbench2-gif

underbench2-gif publishes 6 tracked skills in DriftBot.

Catalog decision: Mixed but usable publisher: there is meaningful evidence here, but reputation still needs to be earned skill by skill.

6

indexed skills

62

average score

0

manual reviews

0

high-risk labels

catalog evidence snapshotno baseline-v3 receipts yetno functionality-v2 receipts yetno manual reviews yetno high-risk labels

Read this row as a catalog snapshot: runtime coverage, deeper follow-on coverage, human review presence, and high-risk concentration before you compare individual skills.

📊 Runtime quality summary

Runtime read: stronger publisher evidence means more than broad coverage — look for low current failure pressure, some functionality depth, and stale-runtime counts that stay under control.

eligible runtime skills: 6latest touch: n/ano current regressions

Baseline coverage

00% of eligible skills have baseline-v3 receipts

Baseline pass rate

0%0 passed · 0 currently failing

Functionality coverage

00% of baseline-cleared skills have functionality-v2

Fixture-backed rate

0%0 functionality-v2 rows have richer fixture/example proof

Stale baseline rows

0baseline receipts older than 7 days

Functionality failures

0current failed functionality-v2 rows in the latest publisher state

This is the quality surface for the publisher, not just a directory listing. It shows how much of the catalog has real receipts, how often those receipts are passing, whether richer fixture-backed proof exists, and whether the publisher currently carries regressions, reproduced failures, or stale runtime evidence.

Latest runtime touch: n/a. Publisher-level summaries do not replace skill-level review, but they do make reputation more earned: a publisher with broader coverage, stronger pass rates, and fixture-backed proof looks different from one living on thin smoke tests.

If you want the system-wide view, open the runtime dashboard. If you want the scoring logic, read the methodology.

Fresh runtime slice Stale runtime slice

No runtime receipts for this publisher yet.

Skills from this publisher

Showing 6 of 6 skills

Label mix on this page

Trusted: 5Use Caution: 0Insufficient Evidence: 1High Risk: 0

This distribution is a quick provenance cue, not a verdict. A publisher can have a mix of safer and riskier skills, so the useful move is to compare patterns here and then open the individual scorecards.

Publisher profiles are best for spotting catalog patterns: repeated shell access, common external services, whether manual review exists, and whether higher-risk labels are isolated or widespread.

On this page: 6 source-scanned, 0 catalog-only, and 0 manually reviewed entries in the current slice.

If you want the scoring logic, read the methodology. If you want the broader landscape, go back to the full index.

ub2-smart-file-organizer

underbench2-gif · vsource-scanned

A skill that enables Claw to scan a directory, categorize files by type and content, and reorganize them into a clean, logical folder structure.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ub2-web-research-assistant

underbench2-gif · vsource-scanned

A skill that enables Claw to perform structured web research on any topic, synthesize findings from multiple sources, and produce a well-organized summary with citations.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ub2-csv-data-analyzer

underbench2-gif · vsource-scanned

A skill that enables Claw to load, explore, analyze, and visualize CSV datasets, providing statistical insights and answering questions about the data.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ub2-markdown-report-generator

underbench2-gif · vsource-scanned

A skill that enables Claw to compile information from multiple sources into a polished, well-structured Markdown report with tables, sections, and optional PDF export.

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

glowskin-promo

underbench2-gif · vsource-scanned

Generate viral marketing content for skincare affiliate products

Trustedconfidence: source evidencesource-scanned

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ub2-api-health-checker

underbench2-gif · vsource-scanned

A skill that enables Claw to test API endpoints, verify their responses, measure performance, and generate a health report.

Insufficient Evidenceconfidence: source evidencesource-scanned

Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

Page 1 / 1

Trust reading guide

Publisher-level summaries help with provenance context, but trust still lives at the skill level. Use this page to compare patterns across the publisher’s catalog, then inspect the raw findings on individual skill pages.

Back to the full index