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.

1.16x

Quality

—

Does it follow best practices?

Impact

98%

1.16x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and operationally concrete, with clear per-workflow structure, but it is monolithic and redundant rather than progressively disclosed, and it lacks executable examples and feedback loops. Splitting reference detail into bundle files and adding concrete payloads with validate/retry steps would lift the weaker dimensions.

Suggestions

Add at least one executable example per core workflow — e.g., a SEGMENT_BATCH JSON payload showing type/userId/event/properties — to move actionability toward copy-paste ready.

Introduce explicit feedback loops for batch and ALIAS operations (verify response per message, retry failures; confirm previousId→userId before the one-way alias).

Move detailed per-tool parameter and pitfall reference material into a references/ file, keeping SKILL.md as a concise overview, to improve progressive disclosure and reduce the inline redundancy.

Dimension	Reasoning	Score
Conciseness	The body is operational and avoids explaining concepts Claude already knows, but it carries notable redundancy — per-section 'Pitfalls' are restated in a 'Known Pitfalls' block and the 'Quick Reference' table repeats the tool list — so it could be tightened rather than earning the lean anchor.	2 / 3
Actionability	Concrete tool names and parameter lists are provided, but there are no executable code or copy-paste examples (e.g., a sample SEGMENT_TRACK or SEGMENT_BATCH JSON payload), leaving guidance specific yet not fully executable.	2 / 3
Workflow Clarity	Sequences and some checkpoints exist (confirm ACTIVE in Setup; check batch responses for per-message errors), but there are no validate→fix→retry feedback loops for batch and destructive (ALIAS) operations, which the rubric caps at 2.	2 / 3
Progressive Disclosure	The skill is a single well-sectioned ~230-line file with no bundle references; everything is inline and the detailed per-tool parameter and pitfall material could live in separate reference files, so it does not reach the clear one-level-deep reference structure of the top anchor.	2 / 3
	Total	8 / 12 Passed

Description

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 specific and distinct, naming six concrete Segment operations, but it omits an explicit 'Use when…' trigger clause and blends natural terms with MCP/Composio jargon. Adding a usage-trigger sentence and trimming the jargon would raise completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when automating Segment customer-data workflows — sending events, identifying users, grouping, or batching calls.'

Soften the leading jargon ('Rube MCP (Composio)') so natural user terms like 'send events to Segment' lead the description.

Consider adding common variations a user might say ('CDP', 'send data to destinations') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'track events, identify users, manage groups, page views, aliases, batch operations' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when…' or equivalent explicit trigger clause; the trailing 'Always search tools first for current schemas' is an instruction, not a trigger, so completeness is capped at 2 per the guideline.	2 / 3
Trigger Term Quality	Natural Segment vocabulary is present ('track events', 'identify users', 'page views', 'batch operations') but it is mixed with technical jargon ('Rube MCP (Composio)') and lacks common phrasings a user might say; not the level-above 'good coverage' anchor.	2 / 3
Distinctiveness Conflict Risk	Scoped to a specific Segment customer-data-platform niche via Rube MCP, making it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Commit: 366e45b

Reviewed: about 23 hours ago

Table of Contents

Discovery Implementation Validation

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.