Content
78%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-structured, highly actionable skill body: executable commands and exact env-var names throughout, a clear scope in/out table, a real verification command, and exemplary progressive disclosure into three purpose-built reference files. The main cost is redundancy in the security sections, where the policy-mutation separation is explained three times and the Security/Security-model sections overlap.
Suggestions
Collapse the 'Where mutation recipes live' section into a single sentence within 'Policy mutation': the mount-path explanation repeats the refusal guidance already given in 'What the agent must never do'.
Merge the 'Security' bullet list into the 'Security model' section — both make the same managed-providers-recommended / raw-keys-local-only point, and the duplication costs tokens on every load.
Promote `opensea wallet info` into the quick start as an explicit post-setup validation step (e.g. step 3: 'Run `opensea wallet info` and confirm the per-tx cap warnings are absent before executing trades') so the checkpoint is part of the workflow rather than a side note.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient — tables, executable commands, and no explanations of concepts Claude already knows — but the policy-mutation separation is restated three times (the 'What the agent must never do' refusals, the 'Policy mutation' section, and the long 'Where mutation recipes live' section), and the 'Security' bullet list overlaps the 'Security model' introduction. It could be meaningfully tightened, matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean level above. | 3 / 5 |
Actionability | Guidance is copy-paste ready throughout: an export block for env vars, a complete `opensea swaps execute` invocation with real flags and address, all four `--wallet-provider` variants, exact env-var names per provider in a table, and `opensea wallet info` as a concrete verification command. Specific examples cover the common cases. | 5 / 5 |
Workflow Clarity | The quick start is a numbered sequence (set env vars, then execute) and `opensea wallet info` provides an explicit checkpoint for both per-tx caps and the mutation gate. It falls short of a 5 because the verification step is presented in the security sections rather than wired into the setup sequence (no 'confirm via wallet info before executing trades'), and the full per-provider setup flow is deferred to the reference file. | 4 / 5 |
Progressive Disclosure | The body is a genuine overview with all detail correctly split into three real, one-level-deep reference files (wallet-setup.md, wallet-policies.md, wallet-funding.md), each signaled inline with a content summary and again in a consolidated References section. The out-of-mount ../docs/policy-administration.md reference is deliberate, well explained, and keeps mutation recipes out of agent context — navigation is easy and the split is appropriate. | 5 / 5 |
Total | 17 / 20 Passed |