Content
82%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 content is highly actionable and well-structured with concrete code and per-path verification, with only minor conciseness trims and feedback-loop gaps preventing a top score.
Suggestions
Add an explicit validate→fix→retry loop for the pinning and jailbreak-detection paths (e.g. 'if Burp shows no decrypted traffic, re-check the Gadget attachment and re-run').
Move the longer JavaScript hook scripts into a references/ file referenced one level deep to tighten the main SKILL.md body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is code- and command-heavy and assumes Claude's competence with Frida/ObjC, but a few prose lines (e.g. 'Most enterprise and bounty-program iOS testing falls here') could be trimmed, matching anchor 4. | 4 / 5 |
Actionability | Provides copy-paste-ready objection REPL commands, frida --codeshare invocations, complete JavaScript hook scripts, and a one-liner, covering the common cases fully. | 5 / 5 |
Workflow Clarity | Each path (A–E) is sequenced with explicit 'Verify in Burp' / 'check Burp proxy' checkpoints and a ZFP two-method evidence checklist, but explicit validate→fix→retry feedback loops are only implied. | 4 / 5 |
Progressive Disclosure | Well-organized into headed sections (Prerequisites, Paths A–E, Evidence, OPSEC, References) with a one-level cross-reference to ios-static; no bundle files exist so content is inline, but navigation is clear. | 4 / 5 |
Total | 17 / 20 Passed |