Audit Hard Stops

Walk the H1-H11 hard-stops catalog systematically against an audit scope. Use as the FIRST audit phase after audit-method completes. Runs detection commands for each hard stop class and reports FOUND / NOT FOUND with evidence. If any hard stop is found, the audit verdict locks to 🛑 DO NOT LAUNCH.

41 stars 1 forksOther

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add wolverin0/claude-skills --skill audit-hard-stops
Manual install
git clone --depth 1 https://github.com/wolverin0/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/audit/audit-hard-stops ~/.claude/skills/audit-hard-stops

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Skill: Audit Hard Stops (H1-H11)

This skill walks the eleven hard-stop conditions from
`@.claude/context/audit-hard-stops.md` and produces a structured report
of findings. It runs FIRST in the audit pipeline because hard stops
override every other consideration.

## What this skill does

For each of H1 through H11:

1. Run the detection commands documented in
   `@.claude/context/audit-hard-stops.md`
2. Read the output
3. For each match, **read the actual code** at the cited path:line to
   verify (R2 — quote before cite). A grep match alone is not a finding;
   a confirmed pattern at a specific line is.
4. Classify: `FOUND` / `NOT FOUND` / `UNABLE TO CHECK (and why)`
5. Capture evidence in the structured shape below

## What this skill does NOT do

- Write fix code (that's `audit-fix-generator`)
- Soften any finding ("technically present but probably fine" — no, R3)
- Skip hard stops because the codebase is "small" or "demo" (no, the
  conditions don't care about scale)
- Halt the audit on first finding — keep walking H1-H11 to surface ALL
  hard stops

## Process

### Pre-flight (load context once)

```
Read @.claude/context/audit-rules.md       # R1-R7
Read @.claude/context/audit-hard-stops.md  # H1-H11 detection details
```

### Walk H1-H11 in order

For each, follow this template:
Read the full skill on GitHub

Details

Skill name
audit-hard-stops
Path
skills/audit/audit-hard-stops/SKILL.md
Repo updated
17 November 2026

FAQ

What does the Audit Hard Stops skill do?

Walk the H1-H11 hard-stops catalog systematically against an audit scope. Use as the FIRST audit phase after audit-method completes. Runs detection commands for each hard stop class and reports FOUND / NOT FOUND with evidence. If any hard stop is found, the audit verdict locks to 🛑 DO NOT LAUNCH.

How do I install the Audit Hard Stops skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add wolverin0/claude-skills --skill audit-hard-stops. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Audit Hard Stops popular?

It lives in wolverin0/claude-skills, which has 41 GitHub stars and 1 forks.

Related skills

UI UX Pro Max

41

wolverin0/claude-skills

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism,

Frontend & Design

Audit Blind Spots

41

wolverin0/claude-skills

Walk the B1-B19 AI-to-AI blind-spot catalog systematically. Use during the audit pipeline AFTER hard-stops and Tambon hunt and BEFORE the 13 domain audits. Output: PRESENT / NOT PRESENT for each B-class with evidence. Findings flow into the appropriate domains.

AI, LLMs & Agents

Audit Decisions

41

wolverin0/claude-skills

Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

Marketing, Sales & Business

Audit Loop

41

wolverin0/claude-skills

Orchestrate the full audit improvement cycle: audit, roadmap, remediation, rerun, delta comparison, and skill patching for missed findings until convergence or a terminal blocked state.

Other

Audit Domain 12 Missing

41

wolverin0/claude-skills

Audit what a normal production app at this scale would have but is absent — health checks, error tracking, feature flags, audit logs, on-call. Run as part of /audit Phase E.

Other

Beneficial Owner Check

43

AlsKozlov/ru-legal

Identify бенефициарных владельцев юр.лица. 115-ФЗ ст.3 — физ.лицо, в конечном счёте владеющее > 25% или иным образом контролирующее. РФ specifics: 215-ФЗ (с 2022) — публичный реестр бенефициаров; ст.93.3 НК — декларация ФНС.

Other

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.