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 domain (HubSpot CRM) and lists relevant entity types, giving it reasonable distinctiveness. However, it lacks specific action verbs describing what operations can be performed and entirely omits a 'Use when...' clause, which significantly weakens its utility for skill selection. The inclusion of implementation details (Rube MCP, Composio) adds noise without helping Claude decide when to use the skill.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about HubSpot, CRM contacts, managing deals, sales pipeline, or customer records.'
Replace 'Automate operations' with specific concrete actions, e.g., 'Create, update, search, and delete HubSpot CRM records including contacts, companies, deals, and tickets.'
Consider removing or de-emphasizing implementation details like 'Rube MCP' and 'Composio integration' which are not natural user trigger terms, and replace with user-facing terms like 'sales pipeline', 'lead management', or 'customer data'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (HubSpot CRM) and lists entity types (contacts, companies, deals, tickets, properties) but doesn't describe specific concrete actions like 'create contacts', 'update deals', or 'search companies'. 'Automate operations' is somewhat vague. | 2 / 3 |
Completeness | It describes what the skill does (automate HubSpot CRM operations) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. 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 misses common variations like 'lead management', 'pipeline', 'sales', or 'customer data'. The terms 'Rube MCP' and 'Composio integration' are implementation details unlikely to be used by end users. | 2 / 3 |
Distinctiveness Conflict Risk | HubSpot CRM is a very specific platform, making this skill clearly distinguishable from other skills. The mention of specific HubSpot entities (contacts, companies, deals, tickets) creates a clear niche that is unlikely to conflict with other skills. | 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-organized HubSpot CRM automation skill with clear workflow sequences and good awareness of common failure modes. Its main weaknesses are the lack of concrete executable examples (no sample JSON payloads for tool calls) and significant content repetition, particularly around pitfalls. Adding example tool call payloads and reducing duplication would meaningfully improve it.
Suggestions
Add at least one concrete example tool call payload per workflow (e.g., a sample HUBSPOT_SEARCH_CONTACTS_BY_CRITERIA call with a complete filterGroups JSON structure) to move from descriptive to executable guidance.
Consolidate pitfalls into the 'Known Pitfalls' section only and remove the per-workflow 'Pitfalls' subsections to eliminate repetition and reduce token count by ~30%.
Add a concrete example of a filterGroups structure since it's the most common and error-prone parameter pattern across all search endpoints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but has significant repetition — the 'Known Pitfalls' section largely restates pitfalls already listed under each workflow, and some explanatory text ('When to use' descriptions) adds little value for Claude. The quick reference table is useful but duplicates information from the workflows above. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter names, and clear sequencing, which is good. However, it lacks any concrete executable examples — no actual JSON payloads for tool calls, no example filterGroups structures, no sample property objects. The guidance is specific but not copy-paste ready. | 2 / 3 |
Workflow Clarity | Each workflow has a clearly numbered sequence with prerequisite/required/optional/alternative annotations, explicit validation steps (e.g., verify connection first, search before creating to avoid duplicates), and error recovery guidance (auth failures cascade, property validation errors). The pagination pattern includes a clear termination condition. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a useful quick reference table, but it's a long monolithic document (~200 lines) with no references to external files. The repeated pitfalls and common patterns sections could be split out. For a skill of this complexity, some content decomposition would improve navigability. | 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
74c7031
- 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.