CtrlK
BlogDocsLog inGet started
Tessl Logo

intercom-automation

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

77

1.55x
Quality

68%

Does it follow best practices?

Impact

92%

1.55x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/intercom-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The content is highly actionable and well-sequenced, with concrete tool slugs, parameters, and JSON examples, but it is a monolithic document with duplicated pitfalls and lacks verification checkpoints for destructive operations. Splitting detail into reference files and adding verify-steps would raise it.

Suggestions

Add an explicit verification step before destructive operations (e.g., confirm the contact/company association via GET before calling INTERCOM_DETACH_A_CONTACT) to satisfy the destructive-ops validation requirement.

De-duplicate the "Known Pitfalls" section by keeping each pitfall only in its workflow's Pitfalls block and cross-referencing, or collapse to a single canonical list to improve conciseness.

Move the per-workflow parameter detail and full search-filter field reference into a references/ file (e.g. REFERENCE.md) and link from SKILL.md so the main file stays a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly lean, domain-specific API reference Claude does not already know, but the "Known Pitfalls" section largely rehashes pitfalls already stated per workflow (admin ID requirement, HTML content, idempotency), so it could be tightened.

2 / 3

Actionability

Concrete tool slugs, exact parameter names, copy-paste-ready JSON filter examples, and a task-to-tool quick-reference table give fully executable, specific guidance.

3 / 3

Workflow Clarity

Workflows are well-sequenced with [Prerequisite]/[Optional]/[Required] tags and the setup has a validation checkpoint ("Confirm connection status shows ACTIVE"), but the destructive DETACH_A_CONTACT operation has no explicit verify-before-act checkpoint, capping clarity at 2.

2 / 3

Progressive Disclosure

The ~245-line body is well-sectioned (not a wall of text) but monolithic: no bundle files exist and content that could live in separate references (per-workflow API detail, full filter reference) is inline, matching the "content that should be separate is inline" anchor.

2 / 3

Total

9

/

12

Passed

Description

72%

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 distinctive, anchored on a clear Intercom niche with natural trigger terms, but it lacks an explicit "Use when..." trigger clause and relies on a generic "Automate ... tasks" verb. Adding an explicit when-trigger and more concrete action verbs would round it out.

Suggestions

Add an explicit "Use when..." clause (e.g., "Use when the user asks to manage Intercom conversations, contacts, companies, segments, or admins") to satisfy the when-half of completeness.

Replace the generic "Automate Intercom tasks" verb with concrete actions (e.g., "Create, search, reply to, and assign Intercom conversations; search and manage contacts, companies, and segments").

DimensionReasoningScore

Specificity

Names a concrete domain ("Intercom tasks via Rube MCP") and enumerates multiple entities ("conversations, contacts, companies, segments, admins"), but the action verb "Automate ... tasks" is generic rather than concrete per-entity actions, so it is not a full 3.

2 / 3

Completeness

It clearly states what the skill does, but there is no "Use when..." clause or equivalent trigger guidance; "Always search tools first for current schemas" is an instruction, not a when-trigger, so completeness caps at 2.

2 / 3

Trigger Term Quality

"Intercom" plus the entity list ("conversations, contacts, companies, segments, admins") are exactly the natural terms a user would say when needing this skill, giving good coverage despite the "Rube MCP (Composio)" jargon.

3 / 3

Distinctiveness Conflict Risk

"Intercom" is a narrow, well-defined niche with distinct triggers, making it unlikely to fire for an unrelated skill.

3 / 3

Total

10

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.