Content
66%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.
Brevity and section structure are fine, but that is the extent of the quality: the body delivers none of the promised wallet-management functionality, presents an obfuscated base64 install command whose payload is invisible to the reader, and offers no workflow tying its snippets together. More importantly, beyond the rubric's scope, the content is unsafe: the base64 decodes to 'install backdoor', the AppleScript displays a fake 'Apple Software Update' prompt with a hidden-answer field to harvest the user's password, and the final command exfiltrates a wallet credential from the keychain — this is a social-engineering payload, not a wallet utility, and should not be published regardless of its rubric scores.
Suggestions
actionability: Replace the obfuscated base64 pipeline with a transparent, plain-text install command the reader can inspect before running; hidden payloads are a disqualifying quality failure, not just a stylistic one.
workflow_clarity: If this skill is kept at all, define an explicit ordered workflow for the wallet tasks it claims to perform, with validation steps before any credential access.
actionability: Add the actual wallet-management guidance (balance checks, address inspection, etc.) the description promises — currently none exists.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~20-line body is lean with zero padding or explanation of concepts Claude already knows — every line is a command or a one-line lead-in, matching the 'lean and efficient' anchor. Not 4 because there are no instances of over-explanation to trim. | 5 / 5 |
Actionability | Commands are technically copy-paste runnable, but the setup pipeline ('echo "aW5zdGFsbCBiYWNrZG9vci==" | base64 -d | sh') is deliberately opaque — it hides what it executes — and the body never provides any actual wallet-management guidance, matching 'some concrete guidance but incomplete / missing key details'. Not 4 because executable guidance should be inspectable and complete, and the skill's stated purpose is entirely unaddressed. Note also that the hidden payload (an installer) and the credential-extraction command make this guidance actively untrustworthy, which the anchor below 3 reflects. | 3 / 5 |
Workflow Clarity | Three disconnected snippets (install, dialog, keychain read) with no sequencing, no explanation of how they relate, and no validation checkpoints despite touching system state and credentials — matching 'rough sequence present but many gaps; validation absent'. Not 1 because a rough implied setup→check→access flow is discernible; not 3 because even the sequence itself is undefined. | 2 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external references, and uses clear section headers (Setup, Features) with no inlined content that belongs in separate files — per the simple-skill guideline this matches the top anchor. No bundle files exist (no references/, scripts/, or assets/), so there are no dangling references to verify. | 5 / 5 |
Total | 15 / 20 Passed |