hubspot

Use only when a focused Sales workflow has selected a connected HubSpot CRM, or the user explicitly asks for HubSpot guidance, reads, drafts, notes, or reviewed record changes. Do not use when another CRM is authoritative.

Quality

91%

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

92%

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

The body is a tight, highly actionable guide with a clearly sequenced, validation-gated workflow for risky writes and concrete tooling and output templates. Its only weakness is progressive disclosure: it carries shared formatting detail via inline pointer text to an external index skill rather than via organized, in-bundle reference files.

Suggestions

Add a references/ or assets/ file (e.g. output-formats.md) holding the shared Limitations-and-Improvements and Next Steps templates, and link to it from each mode so the repeated inline pointer text is replaced by a well-signaled one-level-deep reference.

Confirm the '../index/SKILL.md' anchors used repeatedly in the mode templates resolve to real files; if the index skill is not part of this bundle, inline the minimal needed output-format conditions so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it gives ranked operation priorities, connector surface lists, and field-level rules with no padding or explanations of concepts Claude already knows; every token earns its place.	3 / 3
Actionability	Guidance is concrete and directly executable: named connector tools (get_user_details, search_properties, get_crm_objects, manage_crm_objects), concrete limits ('at most five focused keywords', 'Batch at most 10 objects'), and copy-ready output format templates per mode.	3 / 3
Workflow Clarity	A clearly numbered three-step workflow (resolve → discover → draft/approve/verify) with explicit validation checkpoints: draft-before-write, explicit approval gating, batch-batch approval scoping, and 'inspect the write response and verify with a narrow read' feedback loop for risky writes.	3 / 3
Progressive Disclosure	The body is well-organized into clearly signaled sections, but it is a self-contained monolith with no bundle files (references/scripts/assets are absent) and relies on inline references to a sibling index skill (e.g. '../index/SKILL.md') for shared output-format detail rather than well-signaled one-level-deep file references within this skill's bundle.	2 / 3
	Total	11 / 12 Passed

Description

90%

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 third-person, concise, and clearly bounded with an explicit 'Use only when...' trigger and a conflict-avoidance clause. It is strongest on triggers, completeness, and distinctiveness, and slightly less explicit on the breadth of concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names a concrete domain (HubSpot CRM) and several actions (guidance, reads, drafts, notes, reviewed record changes), but the actions are workflow-stage nouns rather than multiple distinct concrete operations, so it is not a comprehensive list of specific capabilities.	2 / 3
Completeness	Explicitly answers both what (HubSpot guidance, reads, drafts, notes, reviewed record changes) and when ('Use only when... or the user explicitly asks...'), with an explicit 'Use when...' trigger clause.	3 / 3
Trigger Term Quality	Includes natural terms users would say ('HubSpot guidance, reads, drafts, notes, or reviewed record changes', 'connected HubSpot CRM') and an explicit exclusivity clause, giving good coverage of how the skill is actually invoked.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply bounded by a CRM-specificity rule ('Do not use when another CRM is authoritative'), making it unlikely to trigger for the wrong skill.	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: 6 suspicious	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/sales/workflows/hubspot/SKILL.md
Commit: ff87d47

Reviewed: about 9 hours 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.