Content
75%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.
Highly actionable, well-structured content with executable examples and a verified workflow. The main weakness is repetition of the full CLI invocation across many examples, which inflates the token budget.
Suggestions
Define the base command once (e.g. 'All examples run: emblemai --agent --profile default -m "..."') and shorten subsequent examples to just the message argument to cut repetition.
Add an explicit error-recovery step to the swap workflow (e.g. if splBuyIntent fails or quotes a slippage above threshold, re-quote or abort).
Move the DeFi Patterns example catalog into a references/ file (e.g. PATTERNS.md) and link to it from the body to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Tables are dense and efficient, but the full 'emblemai --agent --profile default -m "..."' command is repeated verbatim across Quick Start, Workflow, and DeFi Patterns sections, adding padding Claude could infer. | 3 / 5 |
Actionability | Copy-paste ready commands cover the common cases — research, position checks, balance verification, swaps, and rug-pull checks — with exact tool names and parameters. | 5 / 5 |
Workflow Clarity | A clear 5-step sequence (Research → Positions → Balances → Swap → Verify) includes a verification checkpoint and a confirmation note for the destructive swap, but lacks an explicit error-recovery feedback loop. | 4 / 5 |
Progressive Disclosure | Well-organized sections with one real one-level reference to scripts/yield-scan.sh, but all detail lives inline with no separate reference files for the larger pattern catalog. | 4 / 5 |
Total | 16 / 20 Passed |