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 highly actionable, well-structured skill body with concrete arguments, examples, and validation checkpoints. The main gaps are mild verbosity in the 'When to use' blockquote and reference-style rather than sequential workflow presentation.
Suggestions
Tighten the 'Prefer a dashboard or insight subscription first' blockquote and the longer Pitfalls clauses to remove repetition with the description.
Add an explicit numbered end-to-end create workflow (check gates -> gather args -> Slack 3-step if needed -> create -> verify) so the reference sections hang off a single sequence.
Consider splitting the detailed Pitfalls into a references file once the skill grows, to keep SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense and information-rich, assuming Claude knows PostHog/HogQL, but the long 'Prefer a dashboard or insight subscription first' blockquote and some explanatory clauses in Pitfalls could be trimmed. | 4 / 5 |
Actionability | Provides exact tool names, required and optional arguments as yaml, a 3-step Slack target procedure, and two copy-paste-ready yaml examples covering the email and Slack common cases. | 5 / 5 |
Workflow Clarity | Pre-flight gates ('stop and tell the user... re-calling the tool will not help') and an 'After it lands' verification checklist give explicit validation, but the body is reference-style sections rather than one end-to-end numbered sequence. | 4 / 5 |
Progressive Disclosure | Well-organized into clear headers in a single ~178-line file with no external bundle references, but there is no file-splitting and the under-50-line simple-skill exception does not apply. | 4 / 5 |
Total | 17 / 20 Passed |