- Home
- Skills
- Vladm3105
- Aidoc Flow Framework
- Doc Ears Audit
doc-ears-audit_skill
- Python
9
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
3 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill vladm3105/aidoc-flow-framework --skill doc-ears-audit- SKILL.md4.3 KB
Overview
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.
How this skill works
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.
When to use it
- When you want one command to run both structural and semantic EARS checks
- When you need a single combined report formatted for doc-ears-fixer consumption
- Before BDD generation to ensure EARS files are high quality and testable
- When you want to automate a fix cycle for auto-fixable issues
- Avoid using when EARS files are not present or when only one domain check is required
Best practices
- Provide the EARS path using the repository-relative docs/03_EARS location
- Use the default reviewer threshold (90) or tune for stricter/looser gates
- Inspect the combined report summary and fix queue before auto-applying fixes
- Treat 'blocking' or 'manual-required' items as highest priority for human review
- Keep EARS files in the expected structure so validator findings are precise
Example use cases
- Run a pre-merge quality gate that enforces schema and content quality with a single command
- Generate a combined audit for doc-ears-fixer to automatically remediate low-risk issues
- Run QA on a batch of EARS files before generating BDD assets
- Produce traceability and coverage summaries for compliance or handoff meetings
- Quickly identify whether an EARS file needs manual edits or can be auto-fixed
FAQ
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.