Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
Actionable and well-sequenced, but the body is a monolithic wall of text with some conceptual padding and no validation feedback loops for batch operations, and it makes no use of separate reference files.
Suggestions
Trim explanations of Burp feature mechanics Claude already knows and remove 'Result:'/'Finding:' narration to tighten conciseness toward a lean reference.
Add explicit validation/checkpoint steps to the Intruder and automated-scan workflows (e.g. verify scope and rate limits before launching, confirm findings aren't false positives before reporting) to introduce feedback loops.
Move reference material such as the Common Testing Payloads, keyboard shortcuts, and editions comparison into separate files under references/ and link to them from SKILL.md so the body stays an overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly practical but explains Burp feature mechanics (e.g. 'When ON: Requests pause... When OFF: Requests pass through, logged to history') and adds 'Result:'/'Finding:' narration that Claude largely already knows and could be trimmed. | 2 / 3 |
Actionability | Provides concrete UI navigation paths, copy-paste HTTP request examples (e.g. the /cart price manipulation), payload lists, Intruder § positions, and a keyboard-shortcut table — directly executable. | 3 / 3 |
Workflow Clarity | Six phases are clearly sequenced with numbered steps, but batch/destructive operations (Intruder attacks, automated scans) lack explicit validation or verify-then-proceed checkpoints, which caps clarity at 2. | 2 / 3 |
Progressive Disclosure | No bundle files exist and the >250-line body is monolithic; reference material (payloads, keyboard shortcuts, editions table) sits inline and could be split into linked files, though section organization is good. | 2 / 3 |
Total | 9 / 12 Passed |