Content
81%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 body is a well-organized, highly actionable CLI reference: every command is executable with real examples, setup/verification checkpoints are explicit, and pitfalls candidly document rate limits and heuristic limitations. The main weakness is token efficiency — the absolute script path and environment facts are repeated many times — and the script reference uses an install path instead of a bundle-relative one.
Suggestions
State the script path once (e.g. "Script: scripts/solana_client.py (run as python scripts/solana_client.py ...)") and use a short form in the per-command examples instead of repeating the full ~/.hermes/... path ten times.
Deduplicate the stdlib/no-API-key and rate-limit details between the intro, Prerequisites, and Pitfalls sections — mention each fact once.
Reference the script by its bundle-relative path (scripts/solana_client.py) so the reference matches the actual bundle structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is operational with no padding about what Solana/blockchain is, but it repeats itself: the full absolute script path "~/.hermes/skills/blockchain/solana/scripts/solana_client.py" is spelled out ~10 times, and the stdlib/no-API-key and rate-limit facts each appear in both the intro/Prerequisites and Pitfalls sections. This matches anchor 3 ('mostly efficient but could be tightened') rather than anchor 4, since the repetition is systematic, not minor. | 3 / 5 |
Actionability | Every command is copy-paste ready with real example addresses and mints (e.g. wallet 9WzDXwBbmkg8ZTbNMqUxvQRAyrZzDsGYdLVL9zYtAWWM, BONK mint DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263), documented flags (--limit, --all, --no-prices, --min-sol), and stated expected outputs. The Quick Reference block covers the full command surface, matching anchor 5's 'fully executable, copy-paste ready, specific examples covering common cases'. | 5 / 5 |
Workflow Clarity | The skill is a set of single read-only commands, each unambiguous, with an explicit "Setup Check" (connectivity confirmation via stats), a "When to Use" section mapping user intents to commands, a Verification section stating expected output, and error-recovery guidance in Pitfalls (429 retry with exponential backoff, --no-prices fallback). No destructive or batch operations, so no cap applies; this matches anchor 5's explicit validation and feedback-loop criteria. | 5 / 5 |
Progressive Disclosure | Structure is good: a lean overview plus clearly headed sections (When to Use, Quick Reference, Procedure, Pitfalls, Verification) and a single one-level-deep bundle reference to scripts/solana_client.py, which exists and implements all 8 documented commands. It falls short of anchor 5 because the script is referenced via an absolute install path (~/.hermes/skills/...) rather than a bundle-relative path (scripts/solana_client.py), slightly obscuring the reference against the actual bundle layout. | 4 / 5 |
Total | 17 / 20 Passed |