Name: market-research
Rating: 71.2 (1 reviews)
Author: alirezarezvani

market-research

Use when doing upstream market-research methodology — sizing a market as TAM/SAM/SOM computed BOTH top-down and bottoms-up (never a single unsourced number), planning a survey sample size with finite-population correction and per-segment minimums, or scoring candidate market segments against Kotler's measurable/substantial/accessible/differentiable/actionable criteria. Outputs always show the method and the assumptions. For market-research analysts and product-marketing at the sizing/survey/segmentation moment. Distinct from marketing-skill (campaign analytics, attribution, demand-gen) — this is the evidence-building methodology, not live-campaign optimization.

Quality

88%

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

The canonical home for this skill is market-research in alirezarezvani/claude-skills

Quality

Content

77%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-organized, actionable methodology skill body: clear Purpose, a numbered Workflow with reconciliation gates, a Scripts table, and disciplined Anti-patterns. It earns high marks for structure and concrete commands, with minor deductions for inlined forcing-question detail, missing explicit retry feedback loops, and referenced bundle files (references/, scripts/) that are not actually present in the skill.

Suggestions

Add an explicit validate->fix->retry feedback loop in the Workflow (e.g., 'if tam_divergence exceeds threshold, revise inputs and re-run market_sizer.py') to push workflow_clarity to 5.

Move the full forcing-question library (recommended answer + canon citation per item) into references/ and keep a short pointer in SKILL.md to improve conciseness and progressive_disclosure.

Either ship the referenced references/*.md and scripts/*.py files or mark them as to-be-created, since progressive_disclosure scoring depends on the bundle structure actually existing.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient — tight Purpose, Workflow, Scripts table, and Anti-patterns sections with little concept padding — but the Distinct-from table, forcing-question library with full recommended-answer + canon-citation per item, and dual onboarding explanation add length beyond the minimum a competent Claude needs; it is not 5 because several sections could be trimmed without losing actionability.	4 / 5
Actionability	Provides concrete, runnable commands with real flags (--input, --profile, --sample, --output), a Scripts table mapping tool to purpose/profiles, and quick examples; it is not 5 because most examples reference --sample/--input files rather than showing complete copy-paste-ready inputs for the common cases (e.g., a sample market.json structure is not shown).	4 / 5
Workflow Clarity	The five-step Workflow is clearly sequenced with explicit reconciliation gates ('Reconcile the top-down/bottoms-up delta before quoting anything', 'Drop segments failing the substantiality/accessibility gate'), and the assumptions/anti-patterns surface validation concerns; it is not 5 because there is no explicit re-run/retry feedback loop (validate->fix->retry) shown as a checklist for the iterative sizing reconciliation.	4 / 5
Progressive Disclosure	Well-structured overview with one-level-deep references clearly signaled (References section lists three canon files, Scripts table points to three scripts, onboarding and autoresearch sections are isolated); however the referenced references/ and scripts/ files are not present in the bundle, so navigation cannot be fully verified, and the forcing-question library is inlined content that arguably belongs in a separate reference.	4 / 5
	Total	16 / 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.

A highly specific, well-triggered description that names concrete methods (top-down + bottoms-up TAM/SAM/SOM, FPC sample planning, Kotler criteria) and explicitly scopes when and for whom it applies while contrasting against neighboring skills. The third-person voice is mostly maintained, though a couple of second-person phrasings ('you need') and one conditional ('have you computed') slightly soften the voice consistency.

Suggestions

Tighten voice to consistent third person: 'sizing a market...' and 'planning a survey...' are good, but 'you need a defensible' / 'have you computed both ways' reads as second person and the rubric penalizes that in specificity.

Consider adding explicit file-type or artifact triggers (e.g., '.xlsx sizing model', 'survey.json') to match the tool's actual inputs and strengthen trigger_term_quality further.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete, specific actions — sizing TAM/SAM/SOM via top-down AND bottoms-up, planning survey sample size with finite-population correction and per-segment minimums, and scoring segments against Kotler's five named criteria — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (sizing/survey/segmentation methodology with named methods) and 'when' ('Use when doing upstream market-research methodology...'), with concrete trigger phrases and an explicit audience/decision moment; it is not below 5 because both halves are present and concrete, and not a partial case.	5 / 5
Trigger Term Quality	Captures natural analyst phrasing — 'sizing a market as TAM/SAM/SOM', 'planning a survey sample size', 'scoring candidate market segments' — alongside methodology synonyms and concrete trigger phrases a user would actually say when needing this skill.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — upstream evidence-building methodology — and explicitly disambiguates from marketing-skill (campaign analytics/attribution/demand-gen) and distinguishes itself as methodology rather than live-campaign optimization, minimizing wrong-skill triggering.	5 / 5
	Total	20 / 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
referenced_paths_exist	Referenced path issues: 13 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/market-research/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours 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.