---
id: 901511
card_url: "https://mdrss.com/security/forensics-and-reverse-engineering/901511"
permalink_url: "https://mdrss.com/m/901511"
thread_url: "https://mdrss.com/s/security"
markdown_url: "https://mdrss.com/security/forensics-and-reverse-engineering/901511/901511.md"
title: "reverse-skill / CLAUDE.md — Root-level file that Claude Code auto-loads"
annotation: "Root-level file that Claude Code auto-loads. Declares the repository a task skill router for authorized reverse engineering and security work, names RULES.md as the single source of truth, and fixes the routing order, with per-OS first-run setup and a coherence check."
state: published
thread: security
domain: security
category: forensics-and-reverse-engineering
type: guide
tags: ["zhaoxuya520-reverse-skill", "reverse-skill", "reverse-engineering", "agent-skills", "skill-md", "markdown", "for-agents", "claude", "security", "collider-club"]
ontology_terms: ["concept:forensics-and-reverse-engineering", "org:collider-club"]
relation_terms: []
license: "MIT"
version: 1
snapshot_at: "2026-08-05T14:43:06.335Z"
source_url: "https://github.com/zhaoxuya520/reverse-skill/blob/main/CLAUDE.md"
source_kind: "api"
platform_scam_risk: 5
platform_evidence_score: 100
evidence_urls:
  - "https://github.com/zhaoxuya520/reverse-skill/blob/main/CLAUDE.md"
  - "https://raw.githubusercontent.com/zhaoxuya520/reverse-skill/main/CLAUDE.md"
  - "https://github.com/zhaoxuya520/reverse-skill"
  - "https://github.com/zhaoxuya520/reverse-skill/blob/main/LICENSE"
  - "https://opensource.org/licenses/MIT"
---
> **MDRSS snapshot** · `CLAUDE.md` from [zhaoxuya520/reverse-skill](https://github.com/zhaoxuya520/reverse-skill/blob/main/CLAUDE.md) · audience: AI agents · License: MIT (repo root).
>
> Root-level file that Claude Code auto-loads.

---

# CLAUDE.md

This repository is a **task skill router** for authorized reverse engineering, mobile/security analysis, and pentest workflows.

## On Any Task

`RULES.md` is the single source of truth for behavior chain and authorization.

Routing order:

1. `skills/MASTER-ROUTING.md` or `skills/scripts/master-route.ps1 -Hint "..."`
2. `skills/scripts/case-init.ps1` → current analysis project's `work/<case>/scope.md` (must grant auth before ACT)
3. `skills/routing.md` when ambiguous; roles in `skills/ops/role-map.md`
4. Open PRIMARY `SKILL.md` and execute ACTION REQUIRED
5. Timeline/workitems + Evidence→Finding→Path (`skills/ops/`)
6. `skills/tool-index.md` for real tool paths (never guess)
7. Missing tool → `skills/scripts/bootstrap-reverse.ps1` (manifest capabilities only)

**Identity**: lightweight skill router — see `skills/ops/IDENTITY.md` (not a Z3r0 platform).

## First-Run Setup

`skills/tool-index.md` is not in fresh clones. Generate it:

```bash
# Windows
powershell -NoProfile -ExecutionPolicy Bypass -File skills/scripts/refresh-tool-index.ps1

# macOS / Linux
bash skills/scripts/refresh-tool-index.sh

# Kali
bash kali/scripts/refresh-tool-index.sh
```

Read `README_AI.md` for full bootstrap sequence.

## Coherence check

```powershell
powershell -NoProfile -ExecutionPolicy Bypass -File skills/scripts/verify-routing-coherence.ps1
```


---

*Snapshot metrics: 1374 B · 43 lines · ~341 tokens · 7 headings · git mode 100644.*