zoominfo

Use only when a focused Sales workflow has selected a present and connected ZoomInfo connector, or the user explicitly asks for ZoomInfo company search, contact search, enrichment, intent, similarity, recommendations, or research. Do not use when another enrichment source is selected.

Quality

86%

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

81%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.

A well-disciplined operational guide: connector-specific rules throughout, an ordered default resolution pattern with validation and error-recovery loops, and a concrete output template. Its main weaknesses are mild repetition across sections and the lack of worked examples with real values.

Suggestions

Consolidate the duplicated content: the action-lane enumeration appears in both 'Connector Boundary' and 'Credit-Aware Behavior', and the CRM-ground-truth warning appears twice (lines 23 and 53) — merging these would tighten the document without losing information.

Add one worked example per major lane (e.g., a sample lookup call for an intent topic, a translated ICP into search_companies filters, and a filled 'Qualified Matches' table row) to make the guidance copy-paste executable rather than structural.

Dimension	Reasoning	Score
Conciseness	The body is dense connector-specific rules with no explanation of concepts Claude already knows, but it has trims available: the action-lane list is duplicated between 'Connector Boundary' and 'Credit-Aware Behavior', and the 'do not present ZoomInfo as CRM ground truth' warning appears twice. This is the 'efficient; minor instances that could be trimmed' anchor, not the lean 5 anchor where every token earns its place.	4 / 5
Actionability	Concrete action names (`lookup`, `search_companies`, `enrich_contacts`, `find_similar_companies`), an exhaustive lookup value list (`management-levels`, `metro-regions`, `intent-topics`, ...), and a copy-paste-ready output format template provide mostly executable guidance; it falls short of the 5 anchor because no worked example with actual parameter values or a filled sample table is given.	4 / 5
Workflow Clarity	The 'Default Resolution Pattern' is an ordered 6-step sequence with an explicit validation checkpoint (step 5: 'Verify that returned rows actually satisfy the user's hard constraints'), and 'Failure Handling' supplies feedback loops (e.g., retry once with the corrected identifier shape, then report a connector contract mismatch), matching the clear-sequence-with-explicit-validation anchor.	5 / 5
Progressive Disclosure	Sections are clearly organized and cross-skill references are well signaled, but the skill is a single ~227-line monolith with no bundle files; per-lane playbooks (similarity/recommendation flows, lookup value lists) could arguably live in separate files. This is the 'good structure; minor organization gaps' anchor rather than the 5 anchor, which is reserved for a lean overview pointing to well-signaled separate references.	4 / 5
	Total	17 / 20 Passed

Description

92%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.

A tightly scoped, trigger-rich description that explicitly delimits both activation conditions and the capability surface, with an explicit negative trigger preventing conflicts with other enrichment skills. Its only weakness is the absence of common synonym phrasings that users might naturally use.

Dimension	Reasoning	Score
Specificity	The description enumerates seven concrete capability lanes ("company search, contact search, enrichment, intent, similarity, recommendations, or research") covering the connector's full operational surface, matching the comprehensive-coverage anchor rather than the 4 anchor's 'minor gaps in coverage'.	5 / 5
Completeness	It explicitly answers 'when' with concrete trigger phrases ("Use only when a focused Sales workflow has selected... or the user explicitly asks for...") and explicitly answers 'what' via the enumerated operation set; it is well above the 4 anchor where 'when' is only adequately explicit.	5 / 5
Trigger Term Quality	Natural phrases a user would say are present ("company search", "contact search", "enrichment", "research"), but common synonyms such as "lookalike", "prospect research", or "lead enrichment" are missing, matching the 'good keyword coverage; a few natural terms missing' anchor rather than the 5 anchor's synonym comprehensiveness.	4 / 5
Distinctiveness Conflict Risk	The clear ZoomInfo niche is reinforced by an explicit negative trigger ("Do not use when another enrichment source is selected"), minimizing conflict risk with sibling enrichment skills — a distinct case from the 4 anchor's residual overlap risk.	5 / 5
	Total	19 / 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: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/sales/workflows/zoominfo/SKILL.md
Commit: f0293bf

Reviewed: 2 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.