Ready to supercharge your AI agents?

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

Validation quality — measured AI agent skill | DecimalAI

docxology/template-validation-quality

SkillScore78Maintained

Run validation CLI, prerender, markdown/PDF/integrity gates, and QA workflows for the Research Project Template. USE WHEN validate manuscript, check PDF for ?? refs, prerender gate, link checker, output integrity, or pre-commit validation — even without validation_quality prompt.

by docxology

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

Automatic

Doc Ops pack

decimalai skills pull docxology-template-validation-quality

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/docxology-template-validation-quality/SKILL.md

Raw file: /s/docxology-template-validation-quality/SKILL.md ↗ · machine-readable summary at /s/docxology-template-validation-quality.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 6d ago

—-17% tokens0% turns78% of whole cases pass with skill (18/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-31%	0%
case-05	✗→✓	▲ Improved	103%	0%
case-06	✗→✓	▲ Improved	798%	0%
case-07	✗→✓	▲ Improved	-24%	0%
case-08	✗→✓	▲ Improved	-45%	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 — 8/1/2026

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

docxology / template

docs/prompts/validation-quality/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v1

Skill contents

SKILL.md

Validation quality

Prefer actual CLI entrypoints in CLAUDE.md — not illustrative Python stubs.

Natural invoke

"Validate markdown under projects/templates/template_prose_project/manuscript/"
"PDF has unresolved references — run validation"
"Strict prerender before render"

Inputs to confirm

Target — manuscript dir, PDF path, or output/<project>/.
Project — from active_projects when path ambiguous.

Workflow

Source markdown — infrastructure.validation.cli markdown and/or prerender.

Citations — infrastructure.reference.citation validate on .bib.

Links — infrastructure.validation.cli links --repo-root .

PDF — after render: cli pdf output/<project>/pdf/

Integrity — cli integrity output/<project>/

Report — diagnostic codes from validation; path + fix per issue.

Deliverables

Command list with exit codes
Issue table: code | file | message | fix

Verification commands

bash
uv run python -m infrastructure.validation.cli prerender projects/<project>/manuscript --repo-root .
uv run python -m infrastructure.validation.cli markdown projects/<project>/manuscript --repo-root . --strict
uv run python -m infrastructure.reference.citation validate projects/<project>/manuscript/references.bib
uv run python -m infrastructure.validation.cli links --repo-root .
uv run python -m infrastructure.validation.cli pdf output/<project>/pdf/
uv run python -m infrastructure.validation.cli integrity output/<project>/
uv run python -m infrastructure.prose.cli report projects/<project>/manuscript

When NOT to use

Failing pipeline stage triage → pipeline-debugging
Claim-by-claim manuscript audit → manuscript-claim-verification

References

infrastructure/validation/AGENTS.md

Want to see if docxology/template-validation-quality 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.