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.
A well-structured, lean, and actionable instruction-only skill body. Its only soft spot is workflow clarity, which stops at clear checkpoints rather than full validate/retry feedback loops — appropriate for a read-only finding skill but short of a 5.
Suggestions
Add a brief explicit verification loop for the no-match and multiple-match cases (e.g., re-query with broader terms or check archived before reporting 'no matches'), to push workflow clarity toward a 5.
Consider a short checklist after resolving an ID (confirm name + status with the user) so the confirm-before-destructive gate is consistently applied.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient: it names the tool, the returned fields, and the matching criteria without explaining what PostHog or experiments are; every section earns its place. The two opening framing lines are brief and non-redundant in context. | 5 / 5 |
Actionability | Fully actionable for an instruction-only MCP-tool skill: it specifies the exact tool (`experiment-list`) and server, enumerates returned fields, gives matching strategies, a one/multiple/none decision tree, and a concrete worked example. | 5 / 5 |
Workflow Clarity | The find → disambiguate → confirm/get-details sequence is clear with checkpoints (one/multiple/none branches, confirm-before-destructive, no-match suggestions), but it lacks explicit error-recovery feedback loops or checklists that would lift it to a 5. | 4 / 5 |
Progressive Disclosure | A self-contained SKILL.md under 50 lines with no external reference files needed; sections are well-organized and the Related-skills pointers are one level deep and clearly signaled. | 5 / 5 |
Total | 19 / 20 Passed |