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.
The body is a tight, well-sequenced workflow with concrete Jira identifiers and explicit guards, assuming Claude's competence throughout. The main gap is that branch creation and Jira transitions are described abstractly rather than as executable commands.
Suggestions
Provide an executable git command for branch creation (e.g. `git checkout -b <target-key>`) instead of describing it in prose.
Add a verification step after transitions and branch creation to confirm the expected state before entering plan mode.
Specify how Jira is fetched/transitioned (API endpoint or CLI invocation) so the actionability gap closes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~45-line body is lean and assumes competence: no explanation of what Jira is, tables for transitions, and only purposeful prose such as the autocreate note, so every token earns its place. | 5 / 5 |
Actionability | Concrete identifiers are given throughout (issue-type IDs 10004/10001/10002/10153, transition IDs 41/61/21, the regex pattern), but git and Jira API steps are described rather than given as executable commands, leaving minor gaps. | 4 / 5 |
Workflow Clarity | The sequence (Resolve → Prerequisites → Target → Parent → Child → Branch → Plan) is explicit with guards and a refetch-until-appears feedback loop, but lacks post-transition/post-branch verification steps. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no external references needed, the content is organized into clearly labeled sections that make navigation trivial, satisfying the simple-skill exception. | 5 / 5 |
Total | 18 / 20 Passed |