Content
88%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 high-quality, action-dense skill body with concrete tool calls, CLI fallbacks, explicit validation checkpoints, and clear risk-gating guidance. The only real slack is minor verbosity in a few explanatory paragraphs and the lack of any reference split (which the skill does not need).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and assumes competence (no padding about what git/MCP/worktrees are), with every section earning its place via concrete tool calls; a few explanatory prose blocks (the UNKNOWN rationale, the worktree false-clean explanation) could be tightened, keeping it just below the lean anchor. | 4 / 5 |
Actionability | It provides fully executable, copy-paste-ready tool calls with full parameter objects, CLI fallback commands, and concrete example outputs covering the common single-repo and multi-repo cases, matching the fully-executable anchor. | 5 / 5 |
Workflow Clarity | It gives a numbered 0-4 workflow, an explicit checklist, and strong validation/feedback loops for a safety-gating task (staleness checks, partial/truncated re-run guidance, 'stop on UNKNOWN', confirm-the-diffed-checkout), matching the clear-sequence-with-explicit-validation-and-checklists anchor. | 5 / 5 |
Progressive Disclosure | No bundle files exist and none are needed; the single file is cohesive single-skill content with clear section headers and easy navigation, but it is a dense ~120-line file rather than the under-50-line simple-skill case, so it sits at good-structure rather than the top anchor. | 4 / 5 |
Total | 18 / 20 Passed |