# SnailSploit/Claude-Red

claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.

Repository: https://github.com/SnailSploit/Claude-Red
Canonical: https://ross.abutalabs.com/products/claude-red
Language: Python
License: MIT
License Family: permissive
Topics: claude-ai, claude-skills, redteam, redteam-tools, skills, claude-pt
Last push: 2026-08-26T04:48:57+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 42, longevity 13
- inputs: {"age_days": 182, "days_push": 7, "days_rel": 178, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2976, forks 484 (observed 2026-08-28T04:07:32.979677+00:00)

## What it is
A curated library of 58 offensive security skill files (SKILL.md) for the Claude skills system, covering attack surfaces from SQL injection and Active Directory abuse to EDR evasion and exploit development. Each skill primes Claude with expert-level red team methodology that loads on demand via conversational triggers.

## Use cases
- run authorized red team engagements with AI assistance
- prepare for CTF competitions
- triage bug bounty findings
- learn offensive security methodology for specific attack surfaces
- train security operators on exploitation techniques
- explore attack surfaces methodically during security research

## When to choose
- you use Claude or Claude Code and want drop-in offensive security expertise
- you need structured methodology for a specific attack surface like SQLi, ADCS, or wireless attacks
- you want skills that load on demand without consuming context
- you are doing authorized penetration testing or security training

## When to avoid
- you need actual working exploit tools rather than LLM methodology prompts
- you do not use Claude or a compatible skills system
- you require guaranteed up-to-date vulnerability data
- you cannot legally or ethically use offensive security tooling

## Facets
- artifact type: learning-resource
- maturity: active
- function: security, penetration-testing, prompt-engineering, mcp
- domain: security, penetration-testing, artificial-intelligence, developer-tools
- platform: cli, cross-platform
- tags: red-team, claude-skills, offensive-security, skill-library, llm-prompting, exploit-development, ctf, bug-bounty

## Member repositories
- SnailSploit/Claude-Red (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.979677+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:31:34.231124+00:00, confidence not recorded.
  - readme: https://github.com/SnailSploit/Claude-Red (fetched 2026-08-28T04:07:32.979677+00:00, sha 0158bb245fa6)
- Data as of 2026-08-30T08:39:29.467469+00:00.