Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a tight, actionable overview that assumes competence, sequences risky workflows with explicit confirmation/validation checkpoints, and defers detail to real one-level-deep reference files. No verbosity or concept-explanation padding is present.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and dense — no preamble explaining what analytics or Sentry are; every section (naming rules, tracking patterns, key files, event pipeline) earns its place with tables instead of prose. Assumes Claude's competence throughout. | 3 / 3 |
Actionability | Concrete and copy-paste-ready: real file paths ('static/app/utils/analytics.tsx'), a working grep command, named APIs ('trackAnalytics', 'analyticsEventKey', 'AnalyticsArea'), and pipeline destinations with their query tools. The single inline code block is a grep example, with full trackAnalytics usage deferred to references, but the guidance is specific and executable. | 3 / 3 |
Workflow Clarity | Multi-step processes are explicitly sequenced with validation checkpoints: the 'How Many People' flow has Amplitude→grep fallback and a confirmation gate ('Do not proceed to instrumentation without explicit confirmation'), and 'Before Any Change: Search First' is gated by 'NEVER create a new event without checking'. Not level 2 because checkpoints and feedback loops are explicit, not implicit. | 3 / 3 |
Progressive Disclosure | SKILL.md is a concise overview with clearly signaled one-level-deep references to real bundle files (amplitude-mcp.md, tracking-patterns.md with section anchors, event-definitions.md, troubleshooting.md), all confirmed present in references/. Content is appropriately split and easy to navigate. | 3 / 3 |
Total | 12 / 12 Passed |