datdang-dev/quality-audit
studio/services/quality-audit/SKILL.md
R18 prose quality audit service — 100-point scoring from pervert perspective across five categories with actionable revision feedback.
development
Updated May 5, 2026
$ install --global
skillsauthnpx skillsauth add datdang-dev/light-novel-development quality-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 5, 2026, 3:52 AM123.8s7 files scanned
SKILL.md
- name:
- quality-audit
- description:
- R18 prose quality audit service — 100-point scoring from pervert perspective
- - scene_tag:
- explicit|r18|sexual
- - path:
- {{project_root}}/studio/knowledge/packs/r18_sensory_pack.md
- modules:
- []
Quality Audit Service
Overview
The Quality Audit service performs comprehensive quality scoring of R18 prose using a pervert-perspective evaluation framework. Operated by Riko (Gooner Editor), it scores prose across five categories (A through E) on a 100-point scale, scans for banned words, validates sensory density, and generates actionable rewrite instructions when scores fall below the 85-point threshold.
The audit produces an audit-report.json containing the verdict (PASS/FAIL), category scores, continuity updates, and specific fix recommendations per failing paragraph.
On Activation
- Load the
draft-prose.jsonto audit - Load
continuity-ledger.jsonfor state consistency checking - Load audit framework from
{{project_root}}/studio/docs/GOONER_AUDIT_FRAMEWORK.md - Verify schema at
{{project_root}}/studio/schemas/audit-report.schema.json - Begin at
steps/step-01-load-prose.md
Steps
| Step | File | Purpose |
|------|------|---------|
| 1 | steps/step-01-load-prose.md | Load and parse draft prose |
| 2 | steps/step-02-banned-scan.md | Scan for banned words and formatting violations |
| 3 | steps/step-03-category-scoring.md | Score across categories A–E (100-point scale) |
| 4 | steps/step-04-generate-feedback.md | Generate actionable rewrite instructions |
| 5 | steps/step-05-verdict-report.md | Compile final audit-report.json with verdict |
Dependencies
- Agent: Riko (
QA—gooner-editor.agent.yaml) - Input Schema:
draft-prose.schema.json - Output Schema:
audit-report.schema.json - Modules:
gooner-audit-engine,style-enforcer - Framework:
docs/GOONER_AUDIT_FRAMEWORK.md - Upstream: Lewd Writer → Quality Audit
- Downstream: PASS → State Persistence | FAIL → Rewrite loop
Quick Reference
| Intent | Trigger | Route |
|--------|---------|-------|
| Full audit | /gooner-audit | Load steps/step-01-load-prose.md |
| Standalone audit | Provide draft-prose.json path | Execute all 5 steps independently |
| Re-audit after rewrite | Invoked by pipeline | Re-run from step 1 with revised prose |
Related Skills
datdang-dev/sillytavern-expert
development
VerifiedTrustedCommunity
SillyTavern framework engineering expert — Prompt Manager architecture, character card V3 optimization, context template engineering, lorebook design, and Vietnamese R18 roleplay configuration. Bridges LND Studio character bibles to high-fidelity ST deployments.
SKILL.mdUpdated May 29, 2026
datdang-dev/r18-researcher
documentation
VerifiedTrustedCommunity
Kuro's R18 Research & Downloader Engine. Harvests fetish references, downloads R18 assets (novels, manga, illustrations), and extracts natural Japanese R18 prose style guides from Syosetu.
SKILL.mdUpdated May 25, 2026
datdang-dev/novel-development
development
VerifiedTrustedCommunity
Ultimate Novel Development Pipeline — A slow-paced, deeply contextualized narrative engine. Orchestrated flow: Kana (Visuals) -> Luna (World/Pacing) -> Suki (Long-form Prose).
SKILL.mdUpdated May 5, 2026
datdang-dev/scene-prelude
data-ai
VerifiedTrustedCommunity
Luna's Scene Prelude engine — generates an erotic narrative context (micro-scenario) from Kana's forensic data, bridging raw visual analysis to Suki's caption writing. Outputs a structured scenario seed that maximizes erotic tension and narrative coherence.
SKILL.mdUpdated May 5, 2026