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 a thin, mostly descriptive wrapper: well-structured and easy to navigate, but it restates the description, relies on an external repo, and provides little concrete or sequenced actionable guidance for actual channel-factory work.
Suggestions
Replace the generic 'Instructions' boilerplate with concrete, domain-specific steps (e.g. how to structure a Decker-Wattenhofer invalidation tree, MuSig2 key aggregation flow, or watchtower breach-handling procedure) — ideally with a small executable code or config snippet.
Add an explicit validation/checkpoint step for risky operations (e.g. 'Verify the timeout-tree commitment transactions are broadcastable before signing the factory transaction') to raise workflow clarity above 3.
Remove the redundant 'Purpose' and 'Key Topics' sections (they restate the description and frontmatter) and trim the promotional SuperScalar blurb so every remaining token earns its place.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and avoids over-explaining basics, but includes redundant padding — the 'Purpose' and 'Key Topics' sections restate the description, the 'Instructions' bullets are generic boilerplate, and the SuperScalar blurb repeats feature concepts — that could be tightened. | 3 / 5 |
Actionability | Concrete guidance is minimal: the 'Instructions' are abstract ('Clarify goals... Apply relevant best practices and validate outcomes') with no code, commands, or specific steps; the only concrete pointer is to an external GitHub repo, leaving the actual execution path undefined. | 2 / 5 |
Workflow Clarity | The three 'Instructions' bullets form only a rough, generic sequence that is not tied to channel-factory work, with poorly defined steps and no real validation checkpoints — just a vague 'validate outcomes' mention. | 2 / 5 |
Progressive Disclosure | The body is well-organized into clear sections ('Use this skill when', 'Do not use', 'Instructions', 'Purpose', 'Key Topics', 'References') and the references are clearly signaled one level deep; held below 5 by the Purpose/Key Topics redundancy and reliance on external URLs rather than a split bundle. | 4 / 5 |
Total | 11 / 20 Passed |