find-customer-quotes

Use when the user wants verbatim customer or prospect quotes, voice-of-customer evidence, theme validation, objection evidence, product-friction examples, or support for a product area, use case, or sales narrative. Retrieve from transcripts, call notes, supplied transcript-like recordings or exports, and other grounded call material using explicit speaker-confidence and provenance rules.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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 well-structured, highly actionable instruction skill with explicit thresholds, named fields, a concrete output template, and a properly signaled one-level-deep reference. Its only weakness is mild repetition across workflow steps that could be consolidated to tighten the token budget.

Suggestions

Consolidate the repeated "Do not search transcript evidence or draft a quote set until the user selects one" guidance in section 1 so it is stated once and referenced, reducing redundancy.

Fold the recurring coverage/fallback rules (sections 4 and 5) into the single Failure Handling section to avoid restating the same thin-coverage behavior.

Trim hedges like "modestly" / "around" where a concrete default is already given (e.g., relevance ~0.7 / 0.6) to make thresholds unambiguous and shorten the text.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely earns its tokens (concrete thresholds, field names, enums, a copy-paste output template), with a few repeated phrases such as "Do not search transcript evidence or draft a quote set until the user selects one" appearing twice and some recurring coverage/fallback rules that could be consolidated.	4 / 5
Actionability	Fully actionable for an instruction-only skill: explicit thresholds (customer_confidence >= 0.8, theme_relevance >= 0.75, ~0.7 relevance), named output fields (speaker_role_guess, customer_confidence, theme_relevance), enum values, default of five quotes per theme, and a concrete Markdown output template covering common cases.	5 / 5
Workflow Clarity	A clear five-step sequence (scope, search, extract, verify/rank, dedupe) with explicit validation checkpoints (confidence thresholds, "report 0/[target]," "prefer fewer quotes over lowering confidence") and feedback loops for thin coverage and poor formatting.	5 / 5
Progressive Disclosure	SKILL.md is an overview that points to a single one-level-deep, clearly signaled reference (references/extraction-and-output.md, verified to exist) with explicit conditions for when to consult it; content is appropriately split between overview and detailed rules.	5 / 5
	Total	19 / 20 Passed

Description

100%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 comprehensive and concrete: it states the triggering need, the evidence sources, the actions performed, and the governing quality rules in third person. It is slightly dense but every clause carries load, so verbosity is not a meaningful concern.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (retrieve verbatim quotes, voice-of-customer evidence, theme validation, objection evidence, product-friction examples, support for a narrative) plus the governing method of speaker-confidence and provenance rules.	5 / 5
Completeness	Explicitly answers both what ("Retrieve ... using explicit speaker-confidence and provenance rules") and when ("Use when the user wants verbatim customer or prospect quotes ...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms users would say — "verbatim customer or prospect quotes," "voice-of-customer evidence," "theme validation," "objection evidence," "product-friction examples" — with several synonyms and variations; no file-extension terms needed for this domain.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — verbatim customer/prospect quotes from transcript-like evidence with confidence/provenance rules — making it unlikely to trigger the wrong skill; it is clearly distinguished from call analytics and paraphrase workflows.	5 / 5
	Total	20 / 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/find-customer-quotes/SKILL.md
Commit: df9f3c9

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.