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 well-structured diagnostic skill body with executable commands, a sequenced workflow including validation checkpoints and a failure matrix, and clean one-level-deep references to a real platform file. Only mildly improvable on conciseness of the intro framing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense and mostly assumes Claude's competence without explaining basics, though the opening definitional paragraph and a few framing sentences could be trimmed. | 4 / 5 |
Actionability | Copy-paste-ready commands (posthog-cli symbol-sets extract with npx/bunx variants), exact MCP tool calls with arguments, concrete TS config, and specific row-field interpretations cover the common cross-platform cases. | 5 / 5 |
Workflow Clarity | A clearly sequenced 5-step pipeline with explicit checkpoints ('If local artifacts already look wrong, fix the build before debugging the upload'), a decision-matrix feedback loop in Step 4, and a failure matrix checklist for error recovery. | 5 / 5 |
Progressive Disclosure | SKILL.md is a clean cross-platform overview that defers platform specifics to a verified one-level-deep reference (./references/javascript.md) via a clearly signaled table, with bulk detail correctly split out. | 5 / 5 |
Total | 19 / 20 Passed |