Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured operational skill with executable commands at every step, explicit validation and recovery checkpoints for destructive operations, and clean section-based organization. It assumes Claude's intelligence and earns its length through real gotchas rather than concept explanation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body assumes Claude's competence — it never explains git/worktree concepts — and every section earns its place; the repeated 'cd <main-working-tree> &&' chaining rule is deliberate safety emphasis for a footgun rather than filler, matching the lean score-3 anchor and staying above the score-2 'could be tightened' bar. | 3 / 3 |
Actionability | Every step gives fully executable, copy-paste-ready commands with concrete flags (e.g. 'git -C <worktree-path> status --porcelain', 'gh pr list --head <branch-name> --state open --json number --jq length'), matching the score-3 anchor with no pseudocode or missing details that would drop it to score 2. | 3 / 3 |
Workflow Clarity | Steps 1–5 form a clear sequence with explicit validation checkpoints (uncommitted-change check, open-PR check before branch deletion) and a 'Recovery: Dead CWD' feedback loop, plus a Red Flags Never/Always checklist — matching the score-3 anchor for destructive operations rather than the checkpoint-gap score 2. | 3 / 3 |
Progressive Disclosure | As a single-file skill with no bundle files, it is well-organized into clear sections (Overview, Process, Red Flags, Quick Reference, Integration) with easy navigation and nothing that obviously belongs in a separate file, satisfying the well-organized-sections path to score 3 rather than the inline-bloat score 2. | 3 / 3 |
Total | 12 / 12 Passed |