Content
80%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A highly actionable, token-efficient CLI reference with strong safety guardrails, weakened by missing validation feedback loops for batch/destructive work and a monolithic structure with no progressive disclosure.
Suggestions
Add explicit validation checkpoints for risky workflows, e.g. after a deploy run 'sf project deploy report' and only proceed on success; after bulk import, query row counts to verify before declaring done.
Split the long reference into one-level-deep bundle files (e.g. references/soql-patterns.md, references/bulk-api.md, references/rest.md) referenced from SKILL.md so the main file stays an overview.
Add a short ordered 'first run' workflow (check `sf` present → authenticate → set target-org → query) so the entry sequence is explicit rather than implied across sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is almost entirely lean, copy-pasteable `sf` commands with terse comments and no padding or explanation of concepts Claude already knows; every token earns its place. | 3 / 3 |
Actionability | Commands are fully executable and specific (e.g. 'sf data query --query "SELECT Id, Name FROM Contact LIMIT 10" --json'), with concrete flag examples across query, bulk, Apex, and REST sections. | 3 / 3 |
Workflow Clarity | Sequencing exists (authenticate before touching data; confirm before destructive ops) and guardrails are present, but batch/destructive operations lack explicit validate-then-fix-then-retry feedback loops, capping workflow clarity at 2. | 2 / 3 |
Progressive Disclosure | The skill is a single ~375-line monolithic file with no bundle files in references/scripts/assets; well-sectioned but content that could live in separate references (SOQL patterns, REST, Apex) is all inline. | 2 / 3 |
Total | 10 / 12 Passed |