Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →miosa-osa/audit
Multi-domain audit with weighted scoring. Spawns parallel subagents per audit domain. Each check has severity weight and category weight. Produces a quantified health score (0-100) with prioritized findings. Supports security, code quality, performance, compliance, and custom domains.
Passed 11 of 18 test cases with the skill, and 6 of 18 without it.
and 10 more in the full report
10 fixed4 passed either way5 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
What are the three allowed depth setting values, and what scope of checks does the quick depth setting run?
| Checked | Without skill | With skill |
|---|---|---|
| Lists depth options quick, standard, and deep. | Missed | Passed |
| Defines quick depth as running top essential checks. | Passed | Passed |
The instructions your model reads when the skill loads.
Multi-domain audit with quantified scoring and prioritized findings.
Run a comprehensive, multi-domain audit of a workspace, codebase, or knowledge base. Each domain (security, quality, performance, compliance, etc.) gets its own audit pass — optionally parallelized via subagents. Every finding has a severity weight and category weight, producing a single quantified score (0-100) that represents overall health. Results are prioritized so you fix the most impactful issues first.
# Full audit (all domains)
/audit
# Audit specific domains
/audit --domains security,quality
# Audit a specific path
/audit path/to/project/
# Audit with parallel subagents
/audit --parallel
# Audit with custom weights
/audit --weight security:2.0 --weight quality:1.5
# Quick audit (essential checks only)
/audit --depth quick
# Export audit report
/audit --output report.md --format markdown
| Flag | Type | Default | Description |
|---|---|---|---|
<path> | positional | . | Target to audit |
--domains | string[] | all | Domains: security, quality, performance, compliance, knowledge, process |
--parallel | flag | false | Run domain audits as parallel subagents |
test cases passed, vs 6 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.