voice-of-customer-miner

Mine public reviews, app stores, and forums for unmet needs, competitor weaknesses, and switching triggers — with quoted evidence. Use when you want customer voice without waiting on interviews.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/voice-of-customer-miner/SKILL.md

Quality

Content

62%

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

A well-structured workflow skill with a clear sequenced process and explicit output schema, but it is somewhat over-explained and its progressive-disclosure references point to bundle files that are not present, undermining actionability and navigation.

Suggestions

Ship the referenced bundle files (template.md, examples/sample.md, examples/sample-industrial.md) referenced in the body, or remove the references so navigation points only to material that exists.

Tighten Key Concepts and Common Pitfalls by cutting elaboration a competent model already knows (e.g. why vocal reviewers skew negative) to lift conciseness toward the lean anchor.

Add concrete executable guidance to the sweep/capture step (specific search phrasings, source-handling commands, or a verbatim-capture snippet) rather than only describing it, to move actionability toward copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but carries elaboration a competent model already knows (e.g. 'public voice skews toward the angry and the vocal', extensive Key Concepts prose, and a long Common Pitfalls section); matches 'Mostly efficient but includes some unnecessary explanation or could be tightened' rather than the lean anchor at 3.	2 / 3
Actionability	It gives a concrete numbered process and an exact output schema, but the sweep step ('Sweep mixed voice sources') and verbatim capture are described as instructions rather than executable code/commands, and several referenced references (template.md, examples/) are missing from the bundle; matches 'Some concrete guidance but incomplete' rather than copy-paste-ready at 3.	2 / 3
Workflow Clarity	The Application section is a clearly sequenced 4-step process with a search-plan gate, an explicit output schema, and an integrity discipline ('Never fabricate quotes, ratings, review counts') acting as a validation checkpoint; matches 'Clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	It signals one-level-deep references (template.md, examples/sample.md, examples/sample-industrial.md) but those files are absent from the bundle, so navigation points to missing material; matches 'references present but not clearly signaled / could be better organized' rather than the well-structured anchor at 3.	2 / 3
	Total	9 / 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.

A strong description that clearly states what the skill does and when to use it, with natural trigger terms and a distinctive niche. The only soft spot is specificity — the named actions are category-level rather than a fully itemized concrete list.

Dimension	Reasoning	Score
Specificity	It names the domain and several actions ('Mine public reviews, app stores, and forums for unmet needs, competitor weaknesses, and switching triggers') but the actions are high-level categories rather than a comprehensive concrete list, matching the 'Names domain and some actions, but not comprehensive' anchor; not a 3 because it stops short of itemizing multiple distinct concrete operations.	2 / 3
Completeness	Explicitly answers both what ('Mine public reviews... for unmet needs, competitor weaknesses, and switching triggers — with quoted evidence') and when ('Use when you want customer voice without waiting on interviews'), matching the 'Clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Strong coverage of natural terms a user would say ('reviews', 'app stores', 'forums', 'unmet needs', 'competitor weaknesses', 'switching triggers', 'customer voice', 'interviews'); matches 'Good coverage of natural terms users would say' and not a 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Clear niche (public customer-voice mining with quoted evidence) anchored to distinct triggers; unlikely to conflict with adjacent skills, matching 'Clear niche with distinct triggers; unlikely to conflict'.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing, 12 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/voice-of-customer-miner/SKILL.md
Commit: 9971018

Reviewed: 3 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.