home / skills / vladm3105 / aidoc-flow-framework / doc-ears-audit
This skill runs validator and reviewer then merges results into a single audit report for fixer-ready output.
npx playbooks add skill vladm3105/aidoc-flow-framework --skill doc-ears-auditReview the files below or copy the command above to add this skill to your agents.
---
name: doc-ears-audit
description: Unified EARS audit wrapper that runs validator then reviewer and produces a combined report for fixer consumption
metadata:
tags:
- sdd-workflow
- quality-assurance
- ears-audit
- layer-3-artifact
- shared-architecture
custom_fields:
layer: 3
artifact_type: EARS
architecture_approaches: [ai-agent-based]
priority: primary
development_status: active
skill_category: quality-assurance
upstream_artifacts: [EARS]
downstream_artifacts: [Audit Report, Fix Cycle]
version: "1.0"
last_updated: "2026-02-26"
versioning_policy: "tracks EARS-MVP-TEMPLATE schema_version"
---
# doc-ears-audit
## Purpose
Run a **single EARS audit workflow** that executes:
1. `doc-ears-validator` (structural/schema gate)
2. `doc-ears-reviewer` (semantic/content quality gate)
Then emit one **combined report** optimized for `doc-ears-fixer` input.
**Layer**: 3 (EARS Quality Gate Wrapper)
**Upstream**: EARS file(s)
**Downstream**:
- Combined Audit Report: `EARS-NN.A_audit_report_vNNN.md`
- Optional Fix Cycle trigger for `doc-ears-fixer`
---
## Why This Skill Exists
Use this wrapper to avoid user confusion between validator and reviewer while preserving separation of concerns.
| Concern | Owner Skill |
|---------|-------------|
| Schema/template compliance | `doc-ears-validator` |
| Content quality and testability | `doc-ears-reviewer` |
| Single user-facing audit command | `doc-ears-audit` |
---
## When to Use
Use `doc-ears-audit` when:
- You want one command for EARS quality checks
- You need a combined report for `doc-ears-fixer`
- You are running QA before BDD generation
Do NOT use when:
- EARS does not exist (use `doc-ears` / `doc-ears-autopilot` generation first)
- You only need one specific check domain (use validator or reviewer directly)
---
## Execution Contract
### Input
- EARS path (`docs/03_EARS/EARS-NN_*/...`)
- Optional: threshold (default review threshold: 90)
### Sequence (Mandatory)
```text
1) Run doc-ears-validator
2) Run doc-ears-reviewer
3) Normalize and merge findings
4) Write EARS-NN.A_audit_report_vNNN.md
5) If auto-fixable findings exist, hand off to doc-ears-fixer
```
### Combined Status Rules
- `PASS`: Validator PASS AND Reviewer score >= threshold AND no blocking issues
- `FAIL`: Validator FAIL OR Reviewer score < threshold OR blocking/manual-required issues present
---
## Combined Report Format (for doc-ears-fixer)
Output file: `EARS-NN.A_audit_report_vNNN.md`
Required sections:
1. `## Summary`
- EARS ID, timestamp (EST), overall status
- Validator status, reviewer score
2. `## Score Calculation (Deduction-Based)`
- Formula: `100 - total_deductions`
- Threshold comparison (`>=90` pass gate)
3. `## Validator Findings`
- List by severity/code
4. `## Reviewer Findings`
- List by severity/code
5. `## Coverage Findings`
- EARS syntax compliance summary
- Threshold quantification coverage summary
- Traceability/tag coverage summary
6. `## Fix Queue for doc-ears-fixer`
- `auto_fixable`
- `manual_required`
- `blocked`
7. `## Recommended Next Step`
- `run doc-ears-fixer`
- or `manual update required`
### Fix Queue Normalization
Each finding MUST include:
- `source`: `validator` | `reviewer`
- `code`: issue code
- `severity`: `error|warning|info`
- `file`: relative path
- `section`: heading/anchor if known
- `action_hint`: short imperative guidance
- `confidence`: `high|medium|manual-required`
---
## Hand-off Contract to doc-ears-fixer
`doc-ears-fixer` MUST accept combined audit report as equivalent upstream input:
- `EARS-NN.A_audit_report_vNNN.md` (preferred)
- `EARS-NN.R_review_report_vNNN.md` (legacy compatibility)
Precedence rule:
1. Select newest timestamp.
2. If timestamps are equal, prefer `.A_audit_report` over `.R_review_report`.
---
## Example Invocation
```bash
/doc-ears-audit docs/03_EARS/EARS-01_f1_iam/EARS-01_f1_iam.md
```
Expected outcome:
1. validator runs
2. reviewer runs
3. combined audit report generated
4. fixer can execute directly from combined report
---
## Version History
| Version | Date | Changes |
|---------|------|---------|
| 1.0 | 2026-02-26 | Initial EARS audit wrapper; validator→reviewer orchestration; combined report contract for fixer with `.A_` preferred and `.R_` legacy compatibility |
This skill runs a unified EARS audit workflow that executes the structural validator then the semantic reviewer and emits one combined audit report optimized for automatic fixing. It simplifies QA by providing a single command and a normalized output format consumable by doc-ears-fixer. The wrapper preserves separation of concerns while delivering a clear pass/fail status and a prioritized fix queue.
The wrapper first invokes the doc-ears-validator to check schema and template compliance, then runs doc-ears-reviewer to score content quality and testability. Findings from both tools are normalized, merged, and deduplicated into a single combined report with a standardized fix queue. The report includes a deduction-based score, coverage summaries, and actionable fix items annotated with source, severity, file, section, action_hint, and confidence.
What inputs does the skill require?
A path to the EARS file or directory (e.g., docs/03_EARS/EARS-01_...); an optional reviewer threshold (default 90).
How is overall PASS/FAIL determined?
PASS requires validator PASS, reviewer score >= threshold, and no blocking/manual-required issues. Any validator FAIL, low score, or blocking items yields FAIL.