Content
92%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 lean, well-structured instruction-only skill: every section adds non-obvious operational guidance, the workflow is explicitly sequenced with validation and re-check steps, and the Boundaries section doubles as thorough error recovery for failure modes like missing tools and truncated deliveries. The only meaningful gap is the absence of a concrete example of a task_context payload or tool call, which keeps actionability at 4.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is ~40 lines with no padding: it never explains concepts Claude already knows ("Treat returned Rules as constraints, not as evidence that unobserved facts are true" is non-obvious operational guidance, not a tutorial), and even the tool-name alias list ("rule_search, openviking_rule_search, mcp__openviking__rule_search...") earns its tokens by handling real host variance. This matches the 'every token earns its place' anchor; it is not 4 because there is no section that could be trimmed without losing operational value. | 5 / 5 |
Actionability | Guidance is concrete and executable for an instruction-only skill: "Build task_context from the user's goal, the planned action or decision, and concrete facts", "Apply a Rule when its applies_when condition is supported by the task context and no exception applies", and specific handling of "delivery.complete=false". It falls short of 5 only because no example task_context payload or sample tool invocation is given, leaving a minor gap between 'mostly executable' and copy-paste ready. | 4 / 5 |
Workflow Clarity | Five clearly sequenced steps with explicit validation (step 3: "Review every returned Rule independently" against applies_when/exception conditions) and a re-check trigger (step 5: "Call the Rule search tool again when new information materially changes the task context"). The Boundaries section supplies error-recovery feedback loops for missing tools, failed requests, incomplete delivery, and compaction expiry ("If the remaining Rules cannot be retrieved, report the incomplete check and pause the action"), matching the anchor with explicit validation and feedback loops; no destructive/batch cap applies. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines, has no bundle files (references/, scripts/, assets/ are absent), and needs no external references; the body is well-organized into Goal, Workflow, and Boundaries sections. Per the simple-skill guideline this matches the top anchor; it is not 4 because there is no content that should have been split out or any organization gap. | 5 / 5 |
Total | 19 / 20 Passed |