Content
85%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.
A well-architected index skill: clear phased workflow with strong validation/safety gating and excellent progressive disclosure into a real bundle. The main improvement area is trimming redundant asset-count and tree sections that duplicate information already present.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient tables and pointers that assume Claude's competence, but the '数据资产规模' table repeats counts already in the description and the '引用/跨链结构' tree partly duplicates the reference tables above, which could be trimmed. | 4 / 5 |
Actionability | Provides concrete inline guidance — specific tools (amass/subfinder/httpx/ffuf), dorks ('site:target.com inurl:/admin'), and exact reference paths — with minor gaps since payloads are deliberately deferred to bundled files. | 4 / 5 |
Workflow Clarity | Clear 5-phase sequence (Intake→Recon→Enum→Hunt→Report) with explicit validation checkpoints via the ACTION REQUIRED gating (scope/auth granted check, tool-index verification), safety red-lines for destructive ops, and a completion self-check checklist providing feedback loops. | 5 / 5 |
Progressive Disclosure | SKILL.md is a lean overview that points one level deep to a verified, well-organized bundle (methodology/playbooks/industry/dictionaries/templates/tools/payloader all exist), with references clearly signaled via tables and markdown links for easy navigation. | 5 / 5 |
Total | 18 / 20 Passed |