hubspot-automation
Automate HubSpot CRM operations (contacts, companies, deals, tickets, properties) via Rube MCP using Composio integration.
67
51%
Does it follow best practices?
Impact
96%
1.37xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/hubspot-automation/SKILL.mdQuality
Discovery
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 niche (HubSpot CRM) with relevant entity types, giving it good distinctiveness. However, it lacks specific action verbs describing what operations can be performed, includes implementation details (Rube MCP, Composio) that don't help with skill selection, and critically omits any 'Use when...' guidance for trigger matching.
Suggestions
Add a 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about managing HubSpot contacts, updating deals, creating tickets, or any CRM pipeline operations.'
Replace vague 'automate operations' with specific actions like 'Create, update, search, and delete contacts, companies, deals, and tickets in HubSpot CRM; manage custom properties and pipeline stages.'
Remove implementation details ('via Rube MCP using Composio integration') as users won't reference these when requesting HubSpot tasks.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (HubSpot CRM) and lists entity types (contacts, companies, deals, tickets, properties) but doesn't describe specific actions beyond the vague 'automate operations'. What operations? Create, update, delete, search, sync? | 2 / 3 |
Completeness | Describes what it does (automate HubSpot CRM operations) but has no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when...' clause should cap completeness at 2, and since the 'what' is also somewhat vague, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes good keywords like 'HubSpot', 'CRM', 'contacts', 'companies', 'deals', 'tickets', and 'properties' that users might naturally say. However, it includes technical implementation terms ('Rube MCP', 'Composio integration') that users wouldn't use, and misses common variations like 'lead management', 'pipeline', 'sales tracking'. | 2 / 3 |
Distinctiveness Conflict Risk | HubSpot CRM is a very specific niche. The mention of specific HubSpot entities (contacts, companies, deals, tickets) makes it clearly distinguishable from other skills and unlikely to conflict with non-HubSpot tools. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
62%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 with clear workflow sequences and good labeling of step dependencies (Prerequisite/Required/Optional). Its main weaknesses are the lack of concrete executable examples (no actual JSON payloads or tool call examples) and significant content repetition between individual workflow pitfalls and the consolidated Known Pitfalls section. Trimming redundancy and adding 1-2 concrete tool call examples would significantly improve it.
Suggestions
Add at least one concrete, copy-paste-ready tool call example per major workflow (e.g., a complete HUBSPOT_SEARCH_CONTACTS_BY_CRITERIA call with actual filterGroups JSON structure)
Consolidate pitfalls into the single 'Known Pitfalls' section and remove duplicated pitfall entries from individual workflows to reduce token usage
Consider splitting the detailed workflow sections into a separate WORKFLOWS.md reference file, keeping SKILL.md as a concise overview with the quick reference table and setup instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-organized but contains significant repetition — the 'Known Pitfalls' section largely restates pitfalls already listed under each workflow. The 'Common Patterns' section also repeats pagination and batch info mentioned in individual workflows. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and sequences, which is good. However, it lacks any concrete executable examples — no actual JSON payloads for tool calls, no example filterGroups structures, no sample responses. It describes what to pass but doesn't show copy-paste-ready invocations. | 2 / 3 |
Workflow Clarity | Each workflow has a clearly sequenced tool chain with labeled steps (Prerequisite, Required, Optional, Alternative, Fallback). Validation is addressed through prerequisite checks (search before create, verify auth first), and error recovery guidance is provided in pitfalls sections. The duplicate prevention and auth verification steps serve as validation checkpoints. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a quick reference table, but it's quite long (~200 lines of dense content) with no references to external files for detailed API schemas or examples. The repeated pitfalls across sections and the monolithic structure suggest some content could be split into separate reference files. | 2 / 3 |
Total | 9 / 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.