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

85%

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

82%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-structured, highly actionable workflow skill with a clear sequence, copy-paste-ready schema, and strong verification discipline. Its main weakness is that it advertises a template and two example files that are not present in the bundle, breaking some progressive-disclosure navigation.

Suggestions

Add the missing bundle files referenced in the body (template.md with the fill-in schema and quality checks, examples/sample.md, examples/sample-industrial.md), or remove the references if those artifacts are not intended to ship.

Tighten the Purpose paragraph and de-duplicate Common Pitfalls against Key Concepts (e.g., 'Rant amplification' restates 'Honest frequency'; 'Skew blindness' restates 'Every source has a known skew') to recover token budget.

Add an explicit post-sweep verification step (e.g., 'if a theme rests on a single source or a single thread, re-sweep to confirm or downgrade its frequency label') to turn the search-plan gate into a full validate→fix→retry feedback loop.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich with every section earning its place and no padding of concepts Claude already knows, but the Purpose paragraph editorializes and Common Pitfalls partly restates Key Concepts (rant amplification ≈ honest frequency; skew blindness ≈ known skew), giving minor instances of over-explanation that could be trimmed.	4 / 5
Actionability	Provides a numbered 4-step procedure, a copy-paste-ready output schema marked 'do not reorder', an explicit question budget, a fully worked labeled example, named sources, and a 4-option Final Step — fully executable, specific guidance that covers the common cases for an instruction-only skill.	5 / 5
Workflow Clarity	Clear 4-step sequence with an explicit search-plan gate checkpoint ('Continue unless revised') and embedded verification mechanisms (Fact/Inference/Assumption labels, honest-frequency taxonomy, per-source bias notes), so validation is not missing; falls short of 5 only because there is no explicit post-sweep validate→fix→retry error-recovery loop.	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references and a peer-skill reference list, but the three bundle paths it promises (template.md, examples/sample.md, examples/sample-industrial.md) do not exist on disk, so referenced navigation targets are missing and it cannot reach the 'appropriately split, easy navigation' anchor.	4 / 5
	Total	17 / 20 Passed

Description

87%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 strong description that clearly states what the skill does and when to use it with concrete, natural trigger language and a distinct niche. Minor room for improvement on action-verb variety and synonym coverage of trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain (public reviews, app stores, forums) and three concrete deliverables (unmet needs, competitor weaknesses, switching triggers) plus quoted evidence, but uses a single verb ('Mine') rather than a list of multiple distinct action verbs, so it lists several specific actions with minor coverage gaps rather than comprehensive coverage.	4 / 5
Completeness	Explicitly answers both 'what' ('Mine public reviews, app stores, and forums for unmet needs, competitor weaknesses, and switching triggers — with quoted evidence') and 'when' ('Use when you want customer voice without waiting on interviews') with concrete trigger phrases, matching the anchor that requires both to be clearly and explicitly stated.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('reviews', 'app stores', 'forums', 'customer voice', 'interviews', 'competitor weaknesses') with good coverage, but misses common synonyms (e.g., 'feedback', 'support tickets', 'NPS') and has no file-extension-style triggers, so it falls short of comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The voice-of-customer mining niche with its specific triggers (reviews, app stores, forums, customer voice, switching triggers) is clearly distinct and unlikely to fire for unrelated skills, giving it a clear niche with minimal conflict risk.	5 / 5
	Total	18 / 20 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: a03af68

Reviewed: 11 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.