hubspot-crm-data-hygiene

Use when auditing HubSpot data quality for missing fields, stale records, duplicates, associations, owners, or cleanup tasks.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%Weight 40%Scale 1-3

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

A tight, highly actionable audit skill body that names exact tools and filters and stays free of fluff. The main gap is the absence of an explicit result-verification checkpoint in the batch audit workflow.

Suggestions

Add an explicit verification step before producing output — e.g., reconcile per-issue counts against the total record count and spot-check that example records actually exhibit the flagged issue.

Include a feedback/retry loop for common failure modes, such as when a search_crm_objects count query hits a filter limit or returns no results, so Claude adjusts filters and re-runs instead of reporting gaps.

Add a scope-coverage checkpoint between discovery (steps 3-4) and example fetching (step 6) so incomplete coverage of the requested object types surfaces early.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no filler or explanations of concepts Claude already knows (e.g., what HubSpot or CRM objects are); every line carries actionable content.	3 / 3
Actionability	It names exact tools and parameters ("get_user_details", "search_properties", "get_properties", "search_crm_objects", "get_crm_objects", "NOT_HAS_PROPERTY", "HAS_PROPERTY", "associatedWith") plus per-object-type property lists, giving concrete executable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	The six-step sequence is clear with a read-access checkpoint (step 1) and a sampling fallback (step 5), but the batch audit lacks an explicit verification/feedback loop (e.g., reconciling per-issue counts to the total or confirming examples before reporting), which caps it at anchor 2.	2 / 3
Progressive Disclosure	Under 50 lines and well-organized into Workflow, Issue Classes, and Output sections, with one clearly signaled one-level reference ("Follow [../hubspot/SKILL.md] ... for access, URLs, pagination, and write approvals") and no nested references.	3 / 3
	Total	11 / 12 Passed

Description

90%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, well-structured description with an explicit Use-when trigger, natural trigger terms, and a clear HubSpot data-hygiene niche. Its only weakness is that it conveys a single audit action applied to several targets rather than multiple distinct actions.

Dimension	Reasoning	Score
Specificity	It names a clear domain ("HubSpot data quality") and enumerates concrete audit targets ("missing fields, stale records, duplicates, associations, owners, or cleanup tasks"), but the only action verb is "auditing" — multiple distinct actions are not listed, matching anchor 2 rather than the multi-action anchor 3.	2 / 3
Completeness	It answers both what ("auditing HubSpot data quality for ...") and when via the explicit "Use when ..." trigger clause, satisfying the anchor for clearly answering both what and when.	3 / 3
Trigger Term Quality	Phrases like "HubSpot data quality", "missing fields", "stale records", "duplicates", "associations", and "cleanup tasks" are natural terms a user would say when they need this skill, giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	"HubSpot CRM data hygiene" is a clear niche with distinct triggers (HubSpot data quality, duplicates, stale records) that are unlikely to fire for unrelated skills.	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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/hubspot/skills/hubspot-crm-data-hygiene/SKILL.md
Commit: 11c74d6

Reviewed: 17 days 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.