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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/opencode/src/skill/builtin/.bundle/sales/workflows/hubspot/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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 tightly written, action-oriented operational guide with a clear workflow, explicit approval/verification gates, and well-organized sections plus output templates for each mode. It falls short of top marks mainly due to missing full executable code examples and feedback loops stated as explicit retry cycles.

Suggestions

Add a short validate→fix→re-verify retry loop to the 'Approved HubSpot Write' workflow so the batch/destructive feedback loop is explicit rather than implied.

Include one or two minimal copy-paste connector call examples (e.g. a search_crm_objects filter snippet) to lift actionability toward fully executable.

Normalize the cross-skill references into clean one-level-deep markdown links (e.g. [Cross-Skill Best Practices](...)) instead of inline path strings.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with little padding about concepts Claude already knows, though a few rule bullets ('Do not write inferred data...', 'Do not imply support...') repeat or overlap ideas already implied elsewhere. Efficient but with minor trims possible, landing just below the lean level-5 anchor.	4 / 5
Actionability	Names specific connector calls (get_user_details, search_properties, get_properties, search_crm_objects, get_crm_objects, manage_crm_objects) with concrete usage constraints ('at most five focused keywords', 'Batch at most 10 objects'), giving mostly executable guidance. It lacks full copy-paste example payloads/calls, which keeps it just below the fully-executable level-5 anchor.	4 / 5
Workflow Clarity	A clear three-step sequence (Resolve access and target → Discover properties and records → Draft, approve, and verify) with explicit approval and verification checkpoints for writes ('Write only after the user explicitly approves', 'Verify with a narrow read'). It is a notch below level 5 because the validate→fix→retry feedback loop for batch/destructive operations is implied rather than spelled out as an explicit loop.	4 / 5
Progressive Disclosure	Well-structured into clearly signaled sections (Operation Ranking, Workflow Guidance, Rules, Connector Boundary, Modes with per-mode output formats), and it defers detail to the parent index skill via explicit cross-references. With no local bundle files, organization is strong; it sits just below level 5 because several external references are invoked by inline path strings rather than clean one-level-deep link pointers.	4 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 precise, trigger-rich, and cleanly scopes activation with an explicit negative condition, strongly answering both 'what' and 'when'. It is slightly short of top marks because the capability list is less comprehensive than the body and a few natural trigger terms are absent.

Dimension	Reasoning	Score
Specificity	Names the HubSpot CRM domain and several concrete capabilities ('reads, drafts, notes, or reviewed record changes'), but stops short of enumerating the fuller action set (search, properties, writes, verification) that the body covers. It is a notch below the comprehensive multi-action level-5 anchor.	4 / 5
Completeness	Explicitly answers both what ('reads, drafts, notes, or reviewed record changes') and when ('Use only when a focused Sales workflow has selected a connected HubSpot CRM, or the user explicitly asks'), plus a clear exclusion clause ('Do not use when another CRM is authoritative').	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('HubSpot guidance, reads, drafts, notes, or reviewed record changes') plus the brand name, but lacks common synonyms and file/object extensions (e.g. 'CRM', 'deal', 'contact', 'ticket') that appear in the body. Good coverage with a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The HubSpot-specific framing and the explicit 'Do not use when another CRM is authoritative' exclusion give it a clear niche with minimal conflict risk, though the surrounding 'Sales workflow' framing leaves slight overlap with sibling CRM skills rather than the near-zero risk of a level-5 anchor.	4 / 5
	Total	17 / 20 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: ec3f989

Reviewed: 5 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.