intercom-automation

Automate Intercom tasks via Rube MCP (Composio): conversations, contacts, companies, segments, admins. Always search tools first for current schemas.

1.55x

Quality

67%

Does it follow best practices?

Impact

92%

1.55x

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/intercom-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.

The content is well-structured and highly actionable with concrete tool slugs, typed parameters, and worked JSON examples, and progressive disclosure is excellent for a self-contained skill. Its main weaknesses are duplicated pitfall content and missing post-action verification checkpoints for destructive and batch operations.

Suggestions

Add explicit post-action validation steps for destructive/batch operations, e.g. after CREATE_CONVERSATION or CLOSE_CONVERSATION, fetch the conversation to confirm the intended state before proceeding.

Remove the redundant 'Known Pitfalls' section or reduce it to a one-line pointer to each workflow's inline Pitfalls, since Admin ID requirement, HTML content, and idempotency are already stated per-workflow.

Consider trimming or collapsing the Quick Reference table so each tool slug and its params appear in only one place, reducing token cost without losing discoverability.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining concepts Claude already knows, but the 'Known Pitfalls' section reiterates pitfalls already stated in each workflow (Admin ID requirement, HTML content, idempotency) and the Quick Reference table duplicates tool slugs and params already listed in the workflow sections, leaving noticeable redundancy that could be tightened.	3 / 5
Actionability	Provides concrete tool slugs, typed parameter definitions, real JSON filter examples, pagination cursor instructions, and a full task-to-tool-to-params table that a model can execute directly, falling just short of a 5 only because no complete example MCP invocation is shown.	4 / 5
Workflow Clarity	Each workflow has an explicit numbered tool sequence with [Prerequisite]/[Optional]/[Required] markers and the setup includes a validation checkpoint (confirm ACTIVE), but destructive/batch operations (CREATE_CONVERSATION, DETACH_A_CONTACT, CLOSE_CONVERSATION) lack post-action verification steps despite noted idempotency risk, which caps workflow clarity at 3 per the rubric's feedback-loop rule.	3 / 5
Progressive Disclosure	No bundle files exist or are referenced, and the inline content is cleanly organized into Prerequisites, Setup, six Core Workflows, Common Patterns, Known Pitfalls, and a Quick Reference table, which per the rubric earns a 5 for a skill with no need for external references.	5 / 5
	Total	15 / 20 Passed

Description

70%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.

The description is specific and clearly distinct within the Intercom niche, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger term coverage is good but leans on product jargon alongside the natural 'Intercom' keyword.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to automate Intercom support workflows — creating or replying to conversations, searching contacts, managing companies or segments.'

Lead with the natural trigger ('Intercom support') before the technical 'Rube MCP (Composio)' phrasing so the description reads as something a user would actually say.

Convert object nouns into action verbs where possible (e.g. 'create and reply to conversations, search contacts, list companies') to strengthen capability specificity.

Dimension	Reasoning	Score
Specificity	Names the Intercom domain and enumerates concrete object categories ('conversations, contacts, companies, segments, admins') plus a concrete procedural instruction ('Always search tools first for current schemas'), though these are object nouns rather than action verbs, leaving minor gaps in coverage.	4 / 5
Completeness	The 'what' is clear (automate Intercom tasks across listed object types) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes the dominant natural keyword 'Intercom' alongside concrete object terms users would say, but omits common phrasings like 'support tickets' or 'Intercom inbox' and leads with technical jargon ('Rube MCP (Composio)') users would not naturally say.	4 / 5
Distinctiveness Conflict Risk	'Intercom' with its enumerated object types (conversations, contacts, companies, segments, admins) is a clear, distinct product niche with minimal overlap risk against other skills.	5 / 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/intercom-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.