Automate Intercom tasks via Rube MCP (Composio): conversations, contacts, companies, segments, admins. Always search tools first for current schemas.
68
53%
Does it follow best practices?
Impact
92%
1.55xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/intercom-automation/SKILL.mdQuality
Discovery
57%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 identifies a clear niche (Intercom automation via Composio/Rube MCP) and lists relevant entity types, giving it good distinctiveness. However, it lacks specific concrete actions beyond 'automate tasks' and is missing an explicit 'Use when...' clause that would help Claude know when to select this skill. The entity list (conversations, contacts, etc.) provides some trigger terms but misses common user language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Intercom, customer messaging, support conversations, or managing contacts/companies in Intercom.'
Replace the vague 'Automate Intercom tasks' with specific actions like 'Search and manage Intercom conversations, create and update contacts, list companies and segments, look up admin details.'
Include natural user-facing trigger terms like 'customer support', 'help desk', 'messaging platform', or 'Intercom API' to improve matching.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Intercom via Rube MCP/Composio) and lists entity types (conversations, contacts, companies, segments, admins), but doesn't describe specific concrete actions like 'create contacts', 'list conversations', or 'update segments'. | 2 / 3 |
Completeness | The 'what' is partially addressed (automate Intercom tasks with listed entities), but there is no explicit 'Use when...' clause. The operational instruction ('Always search tools first') is helpful but doesn't serve as a trigger guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Intercom', 'conversations', 'contacts', 'companies', 'segments', 'admins', and 'Composio', but misses common user phrasings like 'customer support', 'messaging', 'tickets', 'CRM', or action-oriented terms users might say. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Intercom', 'Rube MCP', and 'Composio' creates a very specific niche that is unlikely to conflict with other skills. The platform-specific terminology makes it clearly distinguishable. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive Intercom automation reference that covers many workflows with useful pitfalls and a handy quick reference table. However, it suffers from verbosity through repetition (especially around admin ID requirements), lacks complete executable examples of actual MCP tool invocations, and misses validation/error-recovery checkpoints for non-idempotent operations. The content would benefit from being split across multiple files and tightened to eliminate redundancy.
Suggestions
Add complete, executable MCP tool call examples showing exact parameter objects (e.g., a full RUBE_SEARCH_TOOLS call followed by INTERCOM_CREATE_CONVERSATION with all required params) rather than just listing parameter names.
Add explicit validation checkpoints to workflows, especially for non-idempotent operations like creating conversations and replies (e.g., 'Verify conversation was created by calling GET_CONVERSATION with the returned ID before proceeding').
Consolidate repeated information — the admin ID requirement is stated in at least 4 places; state it once prominently and reference it elsewhere.
Move the detailed quick reference table and per-workflow pitfalls into separate bundle files (e.g., REFERENCE.md, PITFALLS.md) to keep the main SKILL.md lean and focused on core workflows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but quite verbose for what it covers. There's significant repetition (e.g., 'admin_id is required' appears in multiple sections and again in Known Pitfalls), and the detailed parameter listings and pitfalls for each workflow section add bulk that could be tightened. The quick reference table at the end duplicates information already covered in the workflows. | 2 / 3 |
Actionability | The skill provides concrete tool names, parameter names, and JSON examples for search filters, which is helpful. However, there are no complete executable examples showing actual MCP tool calls with full parameter objects. The tool sequences are descriptive rather than showing exact invocation syntax, and the setup steps lack concrete command examples. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with numbered steps and labeled as Required/Optional/Prerequisite, which is good. However, there are no explicit validation checkpoints or error recovery feedback loops. For operations like creating conversations or replying (which the skill itself notes are not idempotent and can cause duplicates), there's no validate-then-proceed pattern — just a warning in pitfalls. | 2 / 3 |
Progressive Disclosure | The content is structured with clear sections and headers, but it's a monolithic document with no bundle files to offload detailed reference material. The quick reference table, detailed pitfalls per workflow, and common patterns could be split into separate files. The single external link to Composio docs is appropriate but the skill itself is quite long for a single file. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
d065ead
Table of Contents
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.