Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Hash cracking is an essential skill for penetration testers and security auditors to evaluate password strength. Hashcat is the world's fastest password recovery tool, supporting over 300 hash types w
.claude/skills/performing-hash-cracking-with-hashcat/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✓→✓ | = Same ✓ | — | — |
| case-11 | ✗→✗ | = Same ✗ | — | — |
| case-18 | ✗→✗ | = Same ✗ | — | — |
| case-22 | ✗→✗ | = Same ✗ | — | — |
| case-04 | ✗→✗ | = Same ✗ | — | — |
Hash cracking is an essential skill for penetration testers and security auditors to evaluate password strength. Hashcat is the world's fastest password recovery tool, supporting over 300 hash types with GPU acceleration. This skill covers using hashcat for authorized password auditing, understanding attack modes, creating effective rule sets, and generating hash analysis reports. This is strictly for authorized penetration testing and password policy assessment.
| Mode | Flag | Description | Use Case | |------|------|-------------|----------| | Dictionary | -a 0 | Wordlist attack | Known password patterns | | Combination | -a 1 | Combine two wordlists | Compound passwords | | Brute-force | -a 3 | Mask-based enumeration | Short passwords | | Rule-based | -a 0 -r | Dictionary + transformation rules | Complex variations | | Hybrid | -a 6/7 | Wordlist + mask | Passwords with appended numbers |
| Hash Mode | Type | Example Use | |-----------|------|-------------| | 0 | MD5 | Legacy web apps | | 100 | SHA-1 | Legacy systems | | 1000 | NTLM | Windows credentials | | 1800 | sha512crypt | Linux /etc/shadow | | 3200 | bcrypt | Modern web apps | | 13100 | Kerberos TGS-REP | Active Directory |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of -100 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.