segment-automation
Automate Segment tasks via Rube MCP (Composio): track events, identify users, manage groups, page views, aliases, batch operations. Always search tools first for current schemas.
67
51%
Does it follow best practices?
Impact
98%
1.16xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/segment-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 does a good job listing specific capabilities and identifying its niche (Segment automation via Composio/Rube MCP), making it distinctive and specific. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms could also be expanded to include more natural user language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Segment analytics, customer data tracking, or Composio integrations.'
Include additional natural trigger terms users might say, such as 'analytics', 'customer data platform', 'CDP', 'Segment API', or 'user tracking'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'track events, identify users, manage groups, page views, aliases, batch operations.' Also specifies the tooling context (Rube MCP, Composio) and includes a procedural instruction ('search tools first for current schemas'). | 3 / 3 |
Completeness | The 'what' is well-covered (automate Segment tasks with specific actions listed), but there is no explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied by the domain context. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Segment', 'track events', 'identify users', 'groups', 'page views', 'aliases', 'batch operations', and 'Composio'. However, it misses common user variations like 'analytics', 'user tracking', 'Segment API', or 'customer data platform' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to Segment via Rube MCP (Composio), which is a clear niche. The combination of 'Segment', 'Composio', and 'Rube MCP' makes it very 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 sections and a useful quick reference table, but suffers from significant verbosity and repetition — the same pitfalls and parameter descriptions are restated across multiple sections. Actionability is moderate: tool names and parameters are specified but no executable invocation examples with real payloads are provided. The document would benefit substantially from deduplication and adding concrete tool call examples.
Suggestions
Deduplicate repeated pitfalls (userId/anonymousId requirement, ISO 8601 timestamps, async processing) into a single shared section instead of repeating in every workflow.
Add at least one concrete, copy-paste-ready tool invocation example (e.g., a full RUBE_SEARCH_TOOLS call followed by a SEGMENT_TRACK call with actual parameters) to improve actionability.
Add explicit error-recovery steps for batch operations: what to check in the response, how to retry failed messages, and when to abort.
Move detailed per-tool parameter lists to a separate reference file or collapse them, keeping only the most critical parameters inline to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Highly repetitive content — the same pitfalls (userId/anonymousId required, ISO 8601 timestamps) are restated across nearly every workflow section. The 'Known Pitfalls' section largely duplicates per-workflow pitfalls. Many parameters and explanations (e.g., what ISO 8601 is, that events are async) are things Claude already knows. The document could be cut by 40-50% without losing actionable information. | 1 / 3 |
Actionability | Tool names and key parameters are clearly listed, and the instruction to always call RUBE_SEARCH_TOOLS first is concrete. However, there are no executable code/command examples — the 'Common Patterns' section uses pseudocode-style numbered lists rather than actual tool invocation examples with real payloads. No copy-paste-ready tool call examples are provided. | 2 / 3 |
Workflow Clarity | Setup steps are sequenced with a connection verification checkpoint. The User Lifecycle pattern provides a clear multi-step sequence. However, batch operations — a potentially risky bulk workflow — lack explicit validation/error-recovery feedback loops. The batch section says 'check response for any individual message errors' but doesn't specify what to do on failure. | 2 / 3 |
Progressive Disclosure | The document has clear section headers and a quick reference table, which aids navigation. However, at ~180 lines with significant repetition, much of the per-tool detail could be split into separate reference files or condensed. There are no bundle files to offload detail into, and the single external link (Composio toolkit docs) is mentioned but not leveraged for reducing inline content. | 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
c911a92
- 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.