Content
82%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-organized, highly actionable investigation skill with concrete tool calls, scripts, and pattern-based workflows. Minor conciseness and workflow-validation gaps, and the referenced bundle files could not be confirmed present.
Suggestions
State the '_posthogUrl must always be surfaced' rule once in a single authoritative place (e.g. the Tips or UI-links section) and reference it elsewhere instead of repeating it three times.
Add an explicit verification checkpoint to the trace-debug workflow (e.g. confirm is_root_span / parent_span_id resolution before interpreting the tree) so the sequence has a hard validation gate.
Ensure the referenced ./references/spans-and-fields.md and ./scripts/*.py files ship with the skill bundle so the signaled navigation targets actually resolve.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense and mostly lean, but the instruction to always include '_posthogUrl' is repeated three times (lines 56, 155, 246) and a few gotchas restate earlier points; trimming those would reach 5. | 4 / 5 |
Actionability | Copy-paste-ready JSON tool-call examples and exact bash invocations with env vars (SPAN=, SEARCH=, MAX_LEN=) cover the common investigation cases fully. | 5 / 5 |
Workflow Clarity | Numbered workflows (debug from URL, each investigation pattern) are clearly sequenced with confirmation steps (re-run without filter, zoom on spike bucket), but these are analytical confirmations rather than hard pass/fail validation gates. | 4 / 5 |
Progressive Disclosure | Good one-level-deep structure with clearly signaled references (tool table, script table, markdown links) and appropriate content splitting, but the referenced ./references/spans-and-fields.md and ./scripts/*.py files are not present in the bundle to verify. | 4 / 5 |
Total | 17 / 20 Passed |