Content
76%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The playbook is highly actionable with executable commands and tight, operational prose, but its batch-oriented workflow lacks explicit validation checkpoints, capping workflow clarity. Structure is good and self-contained though slightly above the simple-skill line.
Suggestions
Add explicit verification checkpoints to the workflow (e.g., after step 2 confirm /tmp/kerb.hashes is non-empty, after step 3 confirm at least one hash cracked before promoting the credential) to lift workflow clarity above the batch-operation cap.
Consider splitting the 'Common services found' table and service-account heuristics into a reference file to keep SKILL.md as a lean overview, which would also bring progressive disclosure to a 5.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's knowledge of AD/Kerberos, with operational rather than padding prose; a few minor chatty bits ("yes, really", "Whatever the service account can reach is now yours") could be trimmed, keeping it just below a 5. | 4 / 5 |
Actionability | Provides fully executable, copy-paste-ready commands across tools (ldapsearch, GetUserSPNs.py, Rubeus, hashcat with modes 13100/19700, kg_add_node) covering the common RC4 and AES cases with clearly marked placeholders. | 5 / 5 |
Workflow Clarity | The five numbered steps form a clear sequence, but Kerberoasting is a batch-able operation (OPSEC notes warn against requesting all SPNs at once) and there are no explicit validation/verification checkpoints (e.g., confirm hashes were captured, confirm crack success), so the batch-operation cap of 3 applies. | 3 / 5 |
Progressive Disclosure | No bundle files exist and the skill is self-contained with clear section headers and logical organization; at ~80 lines it is slightly over the under-50-lines simple threshold, and content like the services table and heuristics could arguably be split out, so it sits at 4 rather than 5. | 4 / 5 |
Total | 16 / 20 Passed |