Content
93%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.
An exemplary lean, command-driven skill body: every command is executable with realistic flags, the workflow is sequenced with an inspect-first checkpoint and mutation guardrails, and the single-file organization fits the content's size. The only gap is a missing post-action verification step in the core workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and efficient — every section (First Step, CLI workflow, what belongs in Beads, Rules) adds non-obvious operational knowledge with zero padding or explanation of concepts Claude already knows, matching the 'every token earns its place' anchor. | 5 / 5 |
Actionability | Fully executable, copy-paste-ready commands with realistic arguments (e.g., 'bd create "Short title" --description=… --type=task --priority=2', 'bd update <id> --claim', 'bd close <id> --reason="Completed"') covering the common cases, matching the top anchor. | 5 / 5 |
Workflow Clarity | A clear numbered sequence (find → inspect → claim → create follow-ups → close) with a first-step fallback ('bd prime' then 'bd where' if it prints nothing) and guardrails ('Inspect before editing', 'Do not auto-close or mutate tasks unless the work is actually complete'), but no explicit post-action verification step (e.g., re-running 'bd show' after an update), fitting anchor 4 rather than 5. | 4 / 5 |
Progressive Disclosure | A single-file skill with no bundle files and no need for any: the content is compact and well-organized into clear sections with nothing that belongs in a separate reference file, so the structure is fully appropriate for one-level navigation. | 5 / 5 |
Total | 19 / 20 Passed |