intercom-automation
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 trigger terms cover Intercom entities but miss natural user language around customer support workflows.
Suggestions
Add a 'Use when...' clause with trigger terms like '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 such as 'Create and search contacts, list and reply to conversations, manage companies and segments, look up admins.'
Include common user-facing synonyms like 'customer support', 'help desk', 'messaging platform', or 'tickets' to improve trigger term coverage.
| 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 instruction to 'always search tools first' is operational guidance rather than a trigger condition. Per rubric, missing 'Use when' caps completeness at 2. | 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 distinct niche that is unlikely to conflict with other skills. The specific platform and integration method make 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 with good structural organization, concrete tool names, and useful JSON examples for query filters. Its main weaknesses are redundancy across sections (admin_id pitfalls repeated 4+ times), lack of validation/error-recovery checkpoints in workflows, and a monolithic structure that could benefit from splitting detailed content into separate reference files.
Suggestions
Add explicit validation checkpoints to workflows (e.g., 'Verify conversation was created by checking response for conversation ID before proceeding to reply')
Deduplicate pitfalls — consolidate repeated warnings (admin_id requirement, HTML content, idempotency) into the Known Pitfalls section only, with brief cross-references from workflows
Split detailed per-workflow parameter lists and the quick reference table into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with links
Add a complete example of an actual MCP tool invocation (e.g., a full RUBE_SEARCH_TOOLS call followed by a conversation creation) to make the skill more actionable
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy — pitfalls are repeated across sections (e.g., admin_id requirement appears in workflows 1, 2, 4, and the Known Pitfalls section). The quick reference table duplicates information already covered in the workflows. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | Tool names and parameter lists are concrete and specific, and the JSON filter examples are copy-paste ready. However, the skill explicitly tells users to call RUBE_SEARCH_TOOLS first for current schemas, meaning the documented parameters may not be authoritative. No executable code examples show actual MCP tool invocations with complete parameter structures. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with labeled steps and prerequisite/optional annotations. However, there are no explicit validation checkpoints or error recovery loops — for operations like conversation creation (which is noted as non-idempotent) or connection setup, there's no 'verify success before proceeding' step or feedback loop for handling failures. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a useful quick reference table, but it's quite long (~200+ lines) with all content inline. The detailed per-workflow pitfalls, common patterns, and known pitfalls sections could be split into referenced files. The single external link to Composio docs is helpful but insufficient for progressive disclosure. | 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 | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.