Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Content Verification Layer (Phase 4 Turn 2) — measured AI agent skill | DecimalAI

ethanyoq/content-verification-layer

SkillScore100Maintained

Phase 4 Turn 2 of disease-market-sizing-orchestration (A6' upgrade). Audits compose output via Cite-or-Block strict — every anchor must reverse-resolve to an actual file in sources/, every fact claim must have an anchor. Returns verdict (ok/blocked) + violations list. Use AFTER cite-bound-content-generator (Turn 1), BEFORE report-bundle-builder (phase 5).

by ethanyoq

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

decimalai skills pull ethanyoq-content-verification-layer

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/ethanyoq-content-verification-layer/SKILL.md

Raw file: /s/ethanyoq-content-verification-layer/SKILL.md ↗ · machine-readable summary at /s/ethanyoq-content-verification-layer.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 41h ago

Yes — +52% lift-32% tokens0% turns100% of whole cases pass with skill (23/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	689%	0%
case-02	✗→✓	▲ Improved	-45%	0%
case-03	✗→✓	▲ Improved	-62%	0%
case-04	✗→✓	▲ Improved	-38%	0%
case-06	✗→✓	▲ Improved	-50%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ethanyoq / skill-hub

skills/10-business-industry/content-verification-layer/SKILL.md

View on GitHub ↗

License Cite-or-Block strict (P0 iron law, see ../../CLAUDE.md)Imported 8/2/2026Version v1Bundled 1 file · scripts

Skill contents

scripts/

SKILL.md

Content Verification Layer (Phase 4 Turn 2)

Strict Audits

enforce_citations_in_text(html) — flag fact-bearing claims without anchors
anchor existence reverse-lookup — every anchor source_id must have a backing file in sources/
(Future T13: route drug claims to A5' verifier; route treatment claims to A1' locate_section)

Functions

verify_section(section_html, sources_dir) -> Verdict
verify_full_report(html, sources_dir) -> Verdict
enforce_citations_in_text(html) -> list[Violation]

P0 守门

Tests grep skill source for hardcoded drug names / disease names — CI blocks on hit.

Want to see if ethanyoq/content-verification-layer would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.