posthog-automation
Automate PostHog tasks via Rube MCP (Composio): events, feature flags, projects, user profiles, annotations. Always search tools first for current schemas.
68
51%
Does it follow best practices?
Impact
100%
1.44xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/posthog-automation/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is concise and specific about the tool ecosystem (PostHog via Rube MCP/Composio) and lists concrete task categories. Its main weakness is the absence of an explicit 'Use when...' clause and missing natural trigger terms users might say (e.g., 'analytics', 'tracking', 'A/B testing'). Adding these would make it significantly more effective for skill selection.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about PostHog analytics, tracking events, managing feature flags, or working with Composio/Rube MCP.'
Include additional natural trigger terms users might say, such as 'analytics', 'tracking', 'A/B testing', 'experimentation', or 'product analytics'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: events, feature flags, projects, user profiles, annotations. Also includes a concrete procedural instruction ('Always search tools first for current schemas'). | 3 / 3 |
Completeness | Clearly answers 'what' (automate PostHog tasks via Rube MCP with specific task types), but lacks an explicit 'Use when...' clause. The 'when' is only implied by the mention of PostHog and Composio. Per rubric guidelines, missing 'Use when...' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'PostHog', 'feature flags', 'events', 'annotations', 'user profiles', and 'Rube MCP (Composio)', but misses common user variations like 'analytics', 'tracking', 'A/B testing', or 'experimentation' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of PostHog + Rube MCP (Composio). This is a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is well-structured with clear workflow sequences and a useful quick reference table, but is severely undermined by extreme verbosity — including what appears to be the evaluation rubric duplicated multiple times within the content itself. The actual PostHog-specific content provides reasonable guidance but lacks executable examples and validation checkpoints in workflows. Significant content could be trimmed or split into reference files.
Suggestions
Remove the duplicated rubric/prompt text that appears embedded within the skill content — this accounts for the majority of the token waste.
Add concrete tool call examples with actual parameters (e.g., a complete POSTHOG_CAPTURE_EVENT call with sample event name, distinct_id, and properties) rather than just listing parameters.
Consolidate the repeated pitfalls — event naming conventions and project ID requirements are stated in multiple sections; move to a single 'Known Pitfalls' section and remove duplicates.
Add validation steps to core workflows, e.g., after creating a feature flag, verify with RETRIEVE_FEATURE_FLAG_DETAILS; after capturing events, verify with LIST_AND_FILTER_PROJECT_EVENTS.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with massive repetition — the entire rubric/prompt text is duplicated multiple times within the skill content itself (appears to be a formatting error). Even ignoring the duplicated prompt text, the actual skill content is bloated with explanations Claude already knows (e.g., what ISO 8601 is, what pagination means, that event properties are 'freeform'). Many pitfall sections repeat the same information across workflows and the 'Known Pitfalls' section. | 1 / 3 |
Actionability | The skill provides specific tool names, parameter lists, and a JSON example for feature flag targeting filters. However, there are no executable code examples — the ID resolution patterns use pseudocode-style numbered steps rather than actual tool call examples with concrete parameters. The quick reference table is useful but the skill lacks copy-paste-ready tool invocation examples. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with numbered steps and tool names marked as Required/Optional. However, there are no validation checkpoints or feedback loops — for example, after creating a feature flag, there's no step to verify it was created correctly. The setup section has a good validation step (confirm ACTIVE status), but core workflows lack error handling guidance. | 2 / 3 |
Progressive Disclosure | The content has good structural organization with clear sections (Setup, Core Workflows, Common Patterns, Quick Reference). However, it's monolithic — all the detailed parameter lists, pitfalls, and patterns are inline in a single very long file. The detailed workflow sections and common patterns could be split into separate reference files, especially given the document's length. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
74c7031
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.