Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with concrete executable commands and a clear safety/guardrail framing, but its monolithic length works against conciseness and progressive disclosure, and destructive/batch workflows lack explicit validation checkpoints.
Suggestions
Add explicit validation/confirmation checkpoints to destructive and batch workflows (e.g. dry-run describe → user confirm → execute → verify result) to lift workflow clarity.
Split the exhaustive command catalogs (REST API, metadata deployment, bulk tree import) into reference files and link to them from a leaner SKILL.md overview to improve both conciseness and progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient copy-paste commands with light comments and avoids explaining concepts Claude already knows, but it runs ~370 lines of fairly exhaustive CLI examples that exceed what a lean overview needs and could be tightened or moved to references. | 2 / 3 |
Actionability | Nearly every section gives concrete, executable `sf` commands with real flags and realistic example values, organized by task — copy-paste ready with no pseudocode. | 3 / 3 |
Workflow Clarity | Sequencing for setup (install → login → query) is clear and Guardrails add validation, but destructive/batch operations (delete, bulk delete, bulk import, deploy) lack explicit validate→confirm→execute checkpoints with error-recovery loops, so the workflow cannot reach 3. | 2 / 3 |
Progressive Disclosure | Content is well-sectioned, but it is a single monolithic SKILL.md with no bundle files and no one-level-deep references; much of the exhaustive command catalog (REST API, metadata deploy, tree import) could be split into reference files. | 2 / 3 |
Total | 9 / 12 Passed |