Content
44%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a comprehensive reference for PostHog automation via Rube MCP with good workflow structure and useful tool sequences, but suffers from significant verbosity and repetition. Content that Claude already knows (ISO 8601 format, case sensitivity, pagination concepts) inflates the token count. The monolithic structure with no external file references means all detail is inlined, and the lack of concrete tool call examples with actual parameters reduces actionability.
Suggestions
Remove redundant pitfalls repeated between individual workflow sections and the Known Pitfalls section; consolidate into one location or eliminate obvious items Claude already knows (ISO 8601 format, case sensitivity, defensive parsing).
Add at least one concrete, complete tool call example showing actual parameters and expected response structure (e.g., a full POSTHOG_CAPTURE_EVENT call with sample input and output).
Split detailed parameter lists and pitfalls into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with the quick reference table and setup instructions.
Remove the 'When to Use' section which adds no information, and trim explanatory text like 'Events are processed asynchronously; ingestion delay is typically seconds' that doesn't change Claude's behavior.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is noticeably verbose with significant repetition across sections. Many pitfalls are things Claude already knows (e.g., 'Date filters use ISO 8601 format', 'case-sensitive', 'parse defensively with fallbacks'). The Known Pitfalls section largely repeats information already stated in individual workflow pitfalls. The 'When to Use' section is a meaningless tautology. | 2 / 5 |
Actionability | The skill provides tool names, parameter lists, and a JSON example for feature flag targeting, which is useful. However, there are no executable code examples or complete tool call examples showing actual input/output. The ID resolution patterns use pseudocode-style numbered steps rather than concrete tool call examples with parameters. | 3 / 5 |
Workflow Clarity | The setup workflow includes a clear validation checkpoint (confirm ACTIVE status before proceeding). Each core workflow has a clear tool sequence with required/optional annotations. The setup has a feedback loop for auth. However, feature flag creation with 'active: true' immediately affecting users lacks an explicit validation/confirmation step, and there's no error recovery guidance for failed API calls. | 4 / 5 |
Progressive Disclosure | This is a long monolithic file (~200+ lines) with no references to external files. The detailed parameter lists, pitfalls for each workflow, common patterns, known pitfalls, and quick reference table could be split into separate files. All content is inlined with no bundle files to support it, making it a wall of reference material that would benefit from separation. | 2 / 5 |
Total | 11 / 20 Passed |