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.
The body is a model of a minimal single-purpose skill: exact tool invocation, expected behavior, the precise user-facing message, and a fallback path, all in ~20 lines with no padding. Its only blemish is one promotional line about sign-in and pricing that could be cut.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and imperative ("Call the `ctx_insight` MCP tool (no parameters)", "Display the tool's output"), assuming Claude's competence with no concept explanations. It falls short of 5 because "The landing page at context-mode.com/insight is the single source of truth for sign-in and pricing details" is marketing filler that does not earn its tokens. | 4 / 5 |
Actionability | Fully executable guidance: exact tool name (`ctx_insight`), explicit "no parameters", the URL it opens, the expected return ("a confirmation line"), the exact message to relay, and a fallback branch if the browser fails. Nothing is left to inference. | 5 / 5 |
Workflow Clarity | This is a simple single-task skill with an unambiguous three-step sequence (call tool → display output → tell the user X), which qualifies for the simple-skill exception to score 5. It even includes an error-recovery branch ("If the browser did not open automatically, share the URL"), and no destructive or batch operations require validation. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no bundle files (references/, scripts/, assets/ are absent and nothing in the body cites them), so per the rubric's simple-skill note a well-organized single-file layout earns 5. The title, one-line summary, and Instructions section are cleanly organized with no content that belongs in a separate file. | 5 / 5 |
Total | 19 / 20 Passed |