hubspot-automation

Automate HubSpot CRM operations (contacts, companies, deals, tickets, properties) via Rube MCP using Composio integration.

1.37x

Quality

83%

Does it follow best practices?

Impact

96%

1.37x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete tool sequences, parameter shapes, and validation checkpoints, and is well-organized for navigation. Its main weakness is mild redundancy between the per-workflow pitfalls and the consolidated Known Pitfalls / Quick Reference sections.

Suggestions

Remove pitfalls already detailed per-workflow from the consolidated 'Known Pitfalls' section, or replace that section with a one-line pointer so each pitfall appears exactly once.

Consider trimming the 'Quick Reference' table to tasks not already covered by the workflow tool sequences, keeping only entries that add lookup value.

For batch workflows, add an explicit validate-then-retry note (e.g. on a 400 'Property values were not valid', call READ_ALL_PROPERTIES to confirm internal names then retry) to strengthen the existing feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the consolidated 'Known Pitfalls' and 'Quick Reference' sections duplicate pitfalls and tool slugs already listed per-workflow, so it could be tightened; it is not 3 due to this redundancy.	2 / 3
Actionability	Exact tool slugs, concrete parameter shapes (filterGroups, inputs arrays, max 100, paging.next.after) and specific error strings make the guidance copy-paste ready, matching anchor 3; per the scoring notes, absence of code is not penalized for an actionable instruction skill.	3 / 3
Workflow Clarity	Workflows are numbered with Prerequisite/Required/Optional labels and include explicit validation (confirm connection ACTIVE, search-before-create duplicate prevention, auth-link feedback loop), satisfying anchor 3; the batch-operation cap does not apply because verification steps are present.	3 / 3
Progressive Disclosure	No bundle files exist, and the single file is well-sectioned (Setup, Core Workflows, Common Patterns, Quick Reference) with a navigation table, giving clear organization and easy navigation per anchor 3.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 is specific and distinctive with strong natural trigger terms, but it omits an explicit 'Use when...' clause so the 'when to use' half of completeness is only implied. Adding trigger guidance would round it out.

Suggestions

Append a 'Use when...' clause naming the situations that should activate this skill, e.g. 'Use when automating HubSpot CRM tasks like creating contacts, tracking deals, or searching tickets via Rube MCP.'

Mirror the natural user phrasings (e.g. 'create contacts in HubSpot', 'search HubSpot deals') in the trigger clause so the 'when' guidance aligns with the strong trigger terms already present.

Dimension	Reasoning	Score
Specificity	Enumerates five concrete CRM object types (contacts, companies, deals, tickets, properties) tied to a specific platform, which is more concrete than anchor 2's 'some actions'; it is not below 3 since multiple specific materials are named.	3 / 3
Completeness	It clearly states what the skill does but lacks any explicit 'Use when...' trigger guidance, so per the rubric guidelines completeness is capped at 2; it is not 3 because the 'when' is never stated.	2 / 3
Trigger Term Quality	Natural user-facing terms ('HubSpot CRM', 'contacts', 'companies', 'deals', 'tickets') give good coverage of what a user would actually say, matching anchor 3.	3 / 3
Distinctiveness Conflict Risk	The niche (HubSpot CRM via Rube MCP/Composio) is highly specific with distinct triggers, making conflict with other skills unlikely; it is not 2 because the scope is unambiguous.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Commit: 3c94e0c

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.