py-audit-bot
Performs independent compliance and quality audits for BioETL projects.
Install
mkdir -p .claude/skills/py-audit-bot && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13041" && unzip -o skill.zip -d .claude/skills/py-audit-bot && rm skill.zipInstalls to .claude/skills/py-audit-bot
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute BioETL py-audit-bot profile for role-specific workflow and constraints.Key capabilities
- →Read and apply `py-audit-bot.md` for audit profiles
- →Classify audits as `baseline`, `final`, or `targeted`
- →Ground every finding in file:line evidence or command results
- →Generate an audit report with findings ordered by severity
- →Explicitly report residual risk and skipped checks
- →Use the smallest suite that matches the audited surface for validation
How it works
The skill executes a read-only audit by applying a specific audit profile. It classifies the audit, grounds findings in evidence, and generates a report detailing findings and risks.
Inputs & outputs
When to use py-audit-bot
- →Final project audit
- →Check for architectural drift
- →Audit compliance with rules
About this skill
py-audit-bot
Source Of Truth
- Root runtime contract:
../../../AGENTS.md - Project rules:
../../../docs/00-project/RULES.md - Requirements:
../../../docs/01-requirements/REQUIREMENTS.md - Accepted ADRs:
../../../docs/02-architecture/decisions - Normative index:
../../../docs/00-project/NORMATIVE_SOURCES.md - Primary profile:
../../agents/py-audit-bot.md - Team orchestration:
../../agents/ORCHESTRATION.md - Shared wrapper contract: references/wrapper-contract.md
- Memory policy:
../../../docs/00-project/ai/agents/guides/MEMORY_USAGE.md - Shared project context:
../../../docs/00-project/ai/memory/agent-memory.md - Role memory:
../../../docs/00-project/ai/memory/memory-py-audit-bot.md
Trigger Scope
Use this wrapper for read-only baseline, final, or targeted audit work. It is not the implementation profile; return findings, risk calls, missing tests, architecture drift, and validation gaps.
Workflow
- Follow the shared wrapper contract.
- Read and apply
../../agents/py-audit-bot.md. - Classify the audit as
baseline,final,targeted,review,debt, orreproducibility. - Ground every finding in file:line evidence or a concrete command result.
- Do not raise technical-debt budgets or create new exemptions.
Expected Output
- Audit report path when a report is written:
reports/{LLM}/review_py-audit-bot_{YYYYMMDD}_{HHMM}_{phase}.md. - Findings first, ordered by severity, with exact references.
- Explicit residual risk and skipped checks.
review replaces the retired hierarchical review route; debt replaces the
retired architecture-debt route; reproducibility replaces the retired replay
audit route. Delegate only when the active runtime and the requested scope
permit it.
Validation
Use the smallest suite that matches the audited surface. Common gates include architecture tests, docs drift checks, config validators, and targeted pytest nodes named by the profile or touched files.
Fallback
If ../../agents/py-audit-bot.md is unavailable, stop and report runtime drift.
When not to use it
- →When the task is an implementation profile
- →When raising technical-debt budgets
- →When creating new exemptions
Limitations
- →Is a read-only audit
- →Does not raise technical-debt budgets
- →Does not create new exemptions
How it compares
This workflow provides a structured, evidence-based audit report for compliance checks, classifying audits and explicitly reporting risks, unlike a general code review.
Compared to similar skills
py-audit-bot side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| py-audit-bot (this skill) | 0 | 1mo | No flags | Intermediate |
| pr-review | 6 | 2mo | Review | Intermediate |
| django-verification | 5 | 4mo | Review | Intermediate |
| lint-and-validate | 6 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by SatoryKono
View all by SatoryKono →You might also like
pr-review
pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
django-verification
affaan-m
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
lint-and-validate
davila7
Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
moai-foundation-quality
modu-ai
Enterprise code quality orchestrator with TRUST 5 validation, proactive analysis, and automated best practices enforcement
s-lint
Falkicon
>
code-quality-enforcer
T-rav
>