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 lean, well-structured reference body that gives concrete commands and paths for repo tooling and logging, deferring exhaustive detail to --help and linked READMEs. Minor tightening of the logging prose would push conciseness higher.
Suggestions
Tighten the process-logging section by leading with the preferred action (e.g. 'Prefer mcp__phrocs__get_process_logs when reachable; otherwise tail the files below.') before enumerating per-mode paths.
Consider a one-line quickstart showing a common command invocation so the most frequent action is copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient prose with concrete commands and paths; every line covers repo-specific knowledge Claude would not already have, though the process-logging explanation could be tightened slightly. | 4 / 5 |
Actionability | Provides concrete, executable commands ('hogli --help', 'hogli up -d', 'hogli dev:setup --log', 'hogli doctor:report', 'mcp__phrocs__get_process_logs') and specific file paths, with minor gaps since the full command list is deferred to --help. | 4 / 5 |
Workflow Clarity | The logging section clearly distinguishes the detached vs TUI launch paths with concrete file locations and a fallback preference; there is no destructive/batch workflow requiring validation checkpoints. | 4 / 5 |
Progressive Disclosure | A concise overview with well-organized sections and a clearly signaled, one-level-deep 'Key references' list pointing to repo files (hogli.yaml, tools READMEs) — appropriate split for a sub-50-line reference skill. | 5 / 5 |
Total | 17 / 20 Passed |