Tessl • The package manager for agent skills

SkillPublic

intercom-automation

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

1.55x

Quality

66%

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

57%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 body is a well-structured, highly actionable API reference for the Intercom toolkit, with real strengths in concrete tool names, parameters, and copy-paste query examples. Its weaknesses are systematic duplication (table + workflows + pitfalls repeat the same facts), missing validation checkpoints around destructive operations, and a monolithic single-file layout with no progressive disclosure.

Suggestions

Add validation checkpoints before destructive or non-idempotent operations (e.g., fetch and confirm the conversation state before DETACH_A_CONTACT or close, verify the reply was not already sent before retrying).

De-duplicate: the Quick Reference table and the Known Pitfalls section largely restate the per-workflow tool lists and pitfalls — keep one canonical form and trim the rest.

Move the Quick Reference table and per-tool parameter details into a references/ file (e.g., references/tools.md) and keep SKILL.md as a concise overview with clearly signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is dense reference material with no padding about concepts Claude already knows, but it is systematically redundant: the Quick Reference table repeats each workflow's tool list, and the admin-ID requirement is stated in workflows 1, 2, and 4 and again under Known Pitfalls. This fits 'mostly efficient but could be tightened' better than anchor 4, which expects only minor trims.	3 / 5
Actionability	Concrete tool slugs (INTERCOM_REPLY_TO_CONVERSATION), named parameters (conversation_id, admin_id, assignee_id), copy-paste JSON filter examples, and explicit pagination cursor guidance make the guidance mostly executable. It falls short of anchor 5 only because no complete end-to-end invocation example with a full parameter payload is shown.	4 / 5
Workflow Clarity	Each workflow has a clearly labeled tool sequence with [Prerequisite]/[Optional] markers, and setup includes a checkpoint ('Confirm connection status shows ACTIVE before running any workflows'). However, destructive and batch operations — DETACH_A_CONTACT, close/reopen, and non-idempotent create/reply — lack validation or verification steps, which per the rubric guidelines caps workflow clarity at 3.	3 / 5
Progressive Disclosure	There are no bundle files at all, and the ~245-line body inlines the full API detail (per-tool parameter lists plus a 20-row Quick Reference table) that belongs in a separate reference file. Section headers give it real structure, but content that should be separate is inline — matching anchor 3 rather than anchor 4's 'most content appropriately placed'.	3 / 5
	Total	13 / 20 Passed

Description

61%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 names a specific, well-bounded domain with natural object-level trigger nouns, but it relies on a single generic verb ('Automate ... tasks') and omits any 'Use when...' trigger guidance, which both caps completeness and weakens its usefulness as a router. Adding concrete action verbs and an explicit trigger clause would raise most dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to manage Intercom conversations, contacts, companies, or segments.'

Replace the generic 'Automate Intercom tasks' with concrete operations: 'Reply to, close, assign, and search conversations; create and manage contacts, companies, and segments.'

Include common action synonyms users would say (reply, close, reopen, assign, tag, search) to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Intercom) and five concrete object areas ('conversations, contacts, companies, segments, admins'), but the only action stated is the generic 'Automate Intercom tasks' — no specific operations like reply, close, assign, or search are listed. This matches the anchor for naming the domain with only minimal actions, and falls short of the level above, which requires several specific actions.	3 / 5
Completeness	The 'what' is clear (automating Intercom objects via Rube MCP), but there is no 'when' — 'Always search tools first for current schemas' is an instruction, not a trigger clause. Per the judging guidelines, a missing 'Use when...' clause or equivalent caps completeness at 3.	3 / 5
Trigger Term Quality	'Intercom', 'conversations', 'contacts', 'companies', 'segments', and 'admins' are exactly the nouns users would naturally say. A few natural terms are missing — action phrases like 'reply', 'close', 'assign', 'tag', or 'search' — so it does not reach comprehensive anchor-5 coverage but sits comfortably above the partial-keyword anchor.	4 / 5
Distinctiveness Conflict Risk	'Intercom' carves a clear niche that is unlikely to fire for unrelated skills, but the 'Automate X tasks via Rube MCP (Composio)' shape is shared by sibling Composio toolkit skills (e.g., Zendesk or HubSpot via Rube), creating minor overlap risk with closely related skills — matching anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	14 / 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
Revision: 868d035

Reviewed: 20 days ago

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.

intercom-automation

Table of Contents

Is this your skill?