Automate HubSpot CRM operations (contacts, companies, deals, tickets, properties) via Rube MCP using Composio integration.
Install with Tessl CLI
npx tessl i github:Lingjie-chen/MT5 --skill hubspot-automation72
Quality
58%
Does it follow best practices?
Impact
96%
1.37xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/hubspot-automation/SKILL.mdDiscovery
40%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 domain (HubSpot CRM) and lists relevant entity types, providing reasonable distinctiveness. However, it lacks specific action verbs beyond 'automate operations' and critically omits any 'Use when...' guidance, making it difficult for Claude to know when to select this skill over others.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks about HubSpot, CRM contacts, sales deals, customer tickets, or managing company records'
Replace vague 'automate operations' with specific actions like 'create, update, search, and delete contacts; manage sales deals and pipelines; track customer tickets'
Include natural user phrases like 'add a contact', 'update a deal', 'check ticket status', 'look up company info'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (HubSpot CRM) and lists entity types (contacts, companies, deals, tickets, properties) but doesn't describe concrete actions beyond the vague 'automate operations'. Missing specific verbs like 'create', 'update', 'search', 'delete'. | 2 / 3 |
Completeness | Describes what it does (automate HubSpot operations) but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance should cap completeness at 2, and this has no 'when' component at all. | 1 / 3 |
Trigger Term Quality | Includes 'HubSpot', 'CRM', and entity names which are relevant keywords users might say. However, missing common variations like 'customer relationship', 'sales pipeline', 'lead management', or action-oriented terms users would naturally use. | 2 / 3 |
Distinctiveness Conflict Risk | HubSpot is a specific platform with distinct terminology. The combination of 'HubSpot CRM' with specific entity types creates a clear niche that's unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill document with excellent workflow clarity and efficient use of tokens. The main weakness is the lack of executable code examples - all guidance is descriptive rather than copy-paste ready. The document would also benefit from progressive disclosure by splitting detailed workflows into separate reference files.
Suggestions
Add executable code examples showing actual tool calls with sample parameters and expected response structures (e.g., a complete RUBE_SEARCH_TOOLS call followed by HUBSPOT_CREATE_CONTACT)
Include a concrete example of filterGroups syntax for search operations, as this is a common source of errors mentioned in pitfalls
Consider splitting the 5 core workflows into separate reference files (e.g., CONTACTS.md, DEALS.md) with SKILL.md serving as a concise overview with links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of what HubSpot or CRM systems are. Every section provides actionable information without padding, and the quick reference table is an excellent token-efficient summary. | 3 / 3 |
Actionability | While tool sequences and key parameters are clearly listed, there are no executable code examples or copy-paste ready commands. The guidance is specific but remains at the parameter/description level rather than showing actual API call syntax or response handling. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with labeled steps (Prerequisite, Required, Optional, Alternative, Fallback). Validation checkpoints are present (verify connection first, search before creating to avoid duplicates, auth verification cascades). The pitfalls sections provide error recovery guidance. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and a quick reference table, but it's a monolithic document with no references to external files for detailed information. The 200+ lines could benefit from splitting detailed workflows into separate files with the main SKILL.md as an overview. | 2 / 3 |
Total | 10 / 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 | |
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.