Content
86%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 well-structured, highly actionable single-file skill: concrete gh commands, a clear six-step sequence with a user-confirmation gate, and tight token efficiency. The only gaps are minor — slight redundancy between the Guidelines and Step 2, and no error-recovery guidance for command failures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and imperative with no explanations of concepts Claude already knows — every step is a command or a concrete instruction. It falls just short of the 5 anchor because the Guidelines section ("Research before concluding; never state guesses as facts") partially restates Step 2, a minor instance of content that could be trimmed. | 4 / 5 |
Actionability | Fully executable throughout: exact `gh issue view ... --json title,body,labels,comments,author,state` commands, verbatim disclaimer text, a decision table with exact label names, and a copy-paste heredoc pattern for posting the comment. This matches the score-5 anchor of copy-paste-ready commands covering the common cases. | 5 / 5 |
Workflow Clarity | Steps 1–6 are clearly sequenced with explicit checkpoints: the author.login check conditionally prepends a disclaimer, and Step 5 requires drafting and waiting for user confirmation before any post — a real validation gate for the outward-facing actions. It sits at anchor 4 rather than 5 because there is no error-recovery guidance (e.g. what to do if gh fails or a label does not exist). | 4 / 5 |
Progressive Disclosure | No bundle files exist (no references/, scripts/, or assets/), and none are needed: the ~70-line body is a well-organized single-purpose overview with clear sections, a table, and command blocks, with nothing inlined that belongs in a separate file. Under the simple-skill guidance this earns a 5. | 5 / 5 |
Total | 18 / 20 Passed |