active-directory-attacks
Provide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and domain dominance for red team operations and penetration testing.
78
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-active-directory-attacks/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent specificity and domain-relevant trigger terms that clearly carve out a distinct niche around Active Directory offensive security. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill over others. Adding trigger guidance would elevate this from good to excellent.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about attacking Active Directory, AD exploitation, red teaming Windows domains, or Kerberos-based attacks.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and domain dominance. These are well-defined, concrete categories of activity. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with the list of attack techniques, but lacks an explicit 'Use when...' clause. The context of red team/penetration testing is mentioned but not framed as trigger guidance. Per rubric guidelines, missing 'Use when...' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Active Directory', 'Kerberos attacks', 'lateral movement', 'privilege escalation', 'credential harvesting', 'red team', 'penetration testing', 'domain dominance', 'reconnaissance'. These cover the natural vocabulary of the domain well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Microsoft Active Directory attack techniques for red team operations. The combination of AD-specific terminology (Kerberos, domain dominance) and offensive security context makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, command-ready guidance for AD attack techniques with good tool coverage and multiple alternatives per attack vector. Its main weaknesses are the lack of validation checkpoints between attack steps (critical for destructive operations like ZeroLogon and DCSync), some redundancy between the detailed sections and the quick reference table, and a monolithic structure that would benefit from splitting into referenced sub-files. The content is well-organized with clear headers but could be tighter.
Suggestions
Add explicit validation/verification steps between attack phases (e.g., 'Verify ticket is valid with klist before proceeding' after ticket forging, 'Confirm relay captured hash' before exploitation steps)
Split the credential attacks, Kerberos ticket attacks, NTLM relay, and CVE sections into separate referenced files to reduce the main skill's length and improve progressive disclosure
Remove the Quick Reference table since it duplicates commands already shown in detail above, or keep only the table and remove the detailed sections for less common attacks
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly efficient with command-focused content, but includes some unnecessary sections like the 'Inputs/Prerequisites' and 'Outputs/Deliverables' lists that are obvious, the 'When to Use' boilerplate at the end, and the Essential Tools table which largely duplicates information shown in context throughout. The Quick Reference table at the end also duplicates commands already shown in detail above. | 2 / 3 |
Actionability | Nearly every technique includes fully executable, copy-paste-ready commands with specific tool invocations, flags, and argument patterns. Multiple tool alternatives are provided for each attack type, and the examples section shows complete end-to-end attack chains with numbered steps. | 3 / 3 |
Workflow Clarity | The core workflow has numbered steps for reconnaissance, and the examples show sequenced attack chains. However, validation checkpoints are largely missing — there's no explicit 'verify this worked before proceeding' between steps, no feedback loops for failed attacks (the troubleshooting table is separate and disconnected from the workflow), and the ZeroLogon section's 'Restore password (important!)' is the only real safety checkpoint in a skill full of destructive operations. | 2 / 3 |
Progressive Disclosure | The content references 'references/advanced-attacks.md' for advanced techniques, which is good progressive disclosure, but no bundle files exist to support this reference. The main document is quite long (~300 lines) and could benefit from splitting credential attacks, Kerberos attacks, and CVEs into separate referenced files rather than inlining everything. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- boisenoise/skills-collections
- Commit
431bfad
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.