Content
40%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 well-structured with clear sections and clearly signaled references, but it is mostly descriptive: it defers all substantive guidance to external links and relies on generic boilerplate instructions, leaving it low on actionability and workflow clarity.
Suggestions
Replace the generic 'Instructions' boilerplate with domain-specific, actionable steps or a concrete explanation workflow (e.g., how to walk through a Decker-Wattenhofer invalidation tree, with a small diagram or example).
Inline a few concrete, copy-paste-ready details (key parameters, an example MuSig2/Taproot script path, or a short worked example) instead of only linking to the external repo.
De-duplicate the topic list across Purpose and Key Topics, and remove concepts Claude already knows, to tighten conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient and sectioned, but the same topic list is repeated across the description, Purpose, and Key Topics sections, and the 'Instructions' section is generic boilerplate ('Apply relevant best practices and validate outcomes') that could be trimmed. | 3 / 5 |
Actionability | Provides only high-level hints and external links rather than concrete, executable steps; the 'Instructions' are abstract directives with no code, commands, or specific procedures tied to the domain. | 2 / 5 |
Workflow Clarity | The 'Instructions' offer a rough abstract three-step sequence (clarify -> apply -> provide) that is generic boilerplate, poorly defined for this domain, and lacks any validation checkpoints. | 2 / 5 |
Progressive Disclosure | Well-organized with clear section headers and clearly signaled (external) references one level deep; the minor gap is that all detail is deferred to external URLs rather than bundled local reference files. | 4 / 5 |
Total | 11 / 20 Passed |