Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tightly written diagnostic skill: lean prose, executable commands and named MCP tools, a sequenced workflow with validation checkpoints, and clean progressive disclosure to verified per-platform references. Minor opportunity is the three unbuilt platform references, but they are honestly flagged.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: a one-sentence cross-platform framing of symbolication followed by a tight build→artifact→symbol-set→frame pipeline, with no padded library background or restatement of generic concepts. Every section earns its place. | 3 / 3 |
Actionability | Provides fully executable commands (the Vite config block, `posthog-cli symbol-sets extract` with npx/bunx variants), exact MCP tool names with parameters, and a verified helper script, plus concrete field-interpretation guidance. | 3 / 3 |
Workflow Clarity | A clear 5-step sequenced workflow with explicit validation checkpoints (fix the build before debugging the upload; download immediately; compare local/uploaded/served), a feedback loop, and a cross-platform failure-matrix checklist. | 3 / 3 |
Progressive Disclosure | The SKILL.md is a well-signaled overview that points one level deep to a verified `references/javascript.md` and `scripts/inspect_sourcemaps.py`, with platform detail appropriately split out and honest "_coming soon_" placeholders; navigation via the Platforms table and inline callouts is easy. | 3 / 3 |
Total | 12 / 12 Passed |