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

68%

Does it follow best practices?

Impact

98%

1.16x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/segment-automation/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

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

A well-structured, actionable reference for Segment via Rube MCP, with concrete tool sequences, parameters, and pitfalls. Its main gaps are the absence of explicit validation feedback loops for batch/destructive operations and no progressive-disclosure file splitting for a >50-line skill.

Suggestions

Add explicit validation feedback loops for risky operations: after SEGMENT_BATCH, instruct Claude to inspect the response for per-message errors and retry only the failed messages; before SEGMENT_UPDATE_SOURCE, validate the change against current schema settings and confirm intent.

For irreversible SEGMENT_ALIAS, add a pre-flight checkpoint (confirm previousId/userId and that the user has not already been aliased) before executing.

Move the detailed per-workflow parameter/pitfall reference into a separate REFERENCE.md and keep SKILL.md as a concise overview with quick-reference table, improving progressive disclosure for this >50-line skill.

Dimension	Reasoning	Score
Conciseness	Efficient reference-style content with concrete params and pitfalls; assumes Claude's competence without explaining basic concepts, though the 'Known Pitfalls' section duplicates several inline per-workflow pitfalls and could be trimmed.	4 / 5
Actionability	Concrete tool slugs, named parameters with types and ISO 8601 examples, numbered tool sequences, and a quick-reference table make the guidance mostly executable, with minor gaps like 'check schema for current limit' and no copy-paste examples.	4 / 5
Workflow Clarity	Setup steps are sequenced with a connection-status checkpoint, but batch and destructive operations (SEGMENT_BATCH, SEGMENT_UPDATE_SOURCE, irreversible ALIAS) lack explicit validate->fix->retry feedback loops, triggering the destructive/batch cap.	3 / 5
Progressive Disclosure	Well-organized with clear headers and a quick-reference table, but all content is inline in a single ~230-line file with no one-level-deep reference files, and per-workflow detail that could be split is kept inline.	3 / 5
	Total	14 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description that clearly names the Segment actions it covers, but it lacks an explicit 'Use when...' trigger clause, which limits its completeness score. Trigger-term coverage is good but could add synonyms and concrete trigger scenarios.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when the user wants to send or manage Segment analytics events, identify users, or batch Segment calls').

Include natural synonyms and trigger phrases users actually say, such as 'Segment analytics', 'sending events to Segment', or 'Segment CDP', to broaden trigger-term coverage.

Keep the existing concrete action list; consider trimming 'Always search tools first for current schemas' from the description since it is process guidance better suited to the body.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete Segment actions ('track events, identify users, manage groups, page views, aliases, batch operations'), giving comprehensive coverage of the domain's call types rather than just 1-2 generic actions.	5 / 5
Completeness	Has a clear, concrete 'what' but no explicit 'Use when...' / 'when' trigger clause; 'Always search tools first' is process guidance, not a trigger, so the missing-trigger cap applies.	3 / 5
Trigger Term Quality	Includes natural phrases a user would say ('track events', 'identify users', 'page views', 'batch operations'), but lacks synonyms and an explicit trigger scenario, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	Niched to 'Segment via Rube MCP (Composio)' with domain-specific terms, making it mostly distinct with only minor overlap risk against other analytics/MCP skills.	4 / 5
	Total	16 / 20 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
Path: plugins/all-skills/skills/segment-automation/SKILL.md
Commit: a9fa86d

Reviewed: about 19 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.