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 thorough, highly actionable skill body with executable examples, explicit pre-call gates, and a post-creation verification step. It is slightly verbose in the disambiguation guidance and pitfall prose, and a small amount of edge-case detail could be offloaded to a reference file.
Suggestions
Tighten the 'Prefer a dashboard or insight subscription first' blockquote and the re-enable pitfall to their decision-relevant essentials to reduce token load.
Consider moving the transient-vs-permanent failure and re-enable-precondition detail into a short reference file linked from Pitfalls, keeping the inline version to the rule of thumb.
Add an explicit 'if the create call returns 400, check the three gates in order before retrying' recovery loop to raise workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean and assumes Claude's competence (no explaining of PostHog/cron/HogQL basics), but the 'Prefer a dashboard or insight subscription first' blockquote and the re-enable pitfall prose run long and could be trimmed. | 4 / 5 |
Actionability | Provides a concrete tool table, fully specified required/optional argument YAML, a three-step Slack-target procedure with named tools, and two copy-paste-ready example YAML blocks covering the common email and Slack cases. | 5 / 5 |
Workflow Clarity | Clear sequence from pre-call gates through args, Slack setup, creation, and an 'After it lands' verification checklist, with explicit stop-on-failure feedback ('If any of the three is missing, stop ... re-calling will not help'); a fully realized error-recovery loop would push it to 5. | 4 / 5 |
Progressive Disclosure | Well-organized into clearly headed sections with one-level-deep, clearly signaled pointers to related skills (`managing-subscriptions`, `building-a-dashboard`) and no nested references; some Pitfalls detail (re-enable preconditions, transient-vs-permanent failure semantics) is dense enough that it could optionally live in a reference file. | 4 / 5 |
Total | 17 / 20 Passed |