product-discovery

Use when validating product opportunities, mapping assumptions, planning discovery sprints, or testing problem-solution fit before committing delivery resources.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

78%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-organized, appropriately split discovery guide with a real executable script and clear references. Main improvements would be deduplicating the OST content and adding explicit validation/feedback-loop steps in the workflow.

Suggestions

Remove the redundant Opportunity Solution Tree structure block, or consolidate it with step 2 of the Core Discovery Workflow to avoid restating the same outcome->opportunities->solutions->experiments hierarchy.

Add explicit validate-then-proceed checkpoints in the workflow (e.g., 'Only advance to solution validation once problem evidence meets the threshold: same pain across multiple target users plus observable workaround behavior').

Make the assumption-mapping step more copy-paste actionable by showing an example CSV row or inline --assumption invocation alongside the existing command.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the Opportunity Solution Tree structure is restated after already appearing in the Core Discovery Workflow, a minor redundancy that could be trimmed; it is not a 5 because of that duplicated content.	4 / 5
Actionability	Provides one executable command ('python3 scripts/assumption_mapper.py assumptions.csv') backed by a real script, plus concrete quantitative thresholds ('At least 3 distinct opportunities', 'At least 2 experiments per top opportunity'); it is not a 5 because most workflow steps remain methodology-level guidance without copy-paste-ready execution detail.	4 / 5
Workflow Clarity	The 6-step Core Discovery Workflow and 10-day sprint structure are clearly sequenced with checkpoints ('End with decision: proceed, pivot, or stop', 'Daily evidence reviews'); it is not a 5 because explicit validate-then-proceed feedback loops and error-recovery steps are mostly implied rather than spelled out.	4 / 5
Progressive Disclosure	SKILL.md acts as a clear overview with well-signaled, one-level-deep references to real bundle files ('See references/discovery-frameworks.md', 'scripts/assumption_mapper.py'), and content is appropriately split across the script and reference file; it is not a 4 because navigation is clean and nothing is inlined that belongs elsewhere.	5 / 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.

The description is well-constructed: it states concrete discovery actions, uses natural trigger terms, and explicitly pairs a 'what' with a 'Use when' clause. Minor gains are available only through additional synonyms and more granular action phrasing.

Dimension	Reasoning	Score
Specificity	Names the discovery domain and several concrete actions ('validating product opportunities, mapping assumptions, planning discovery sprints, testing problem-solution fit'), but these are process-level verbs rather than fully concrete deliverable operations, leaving minor coverage gaps versus a comprehensive 5.	4 / 5
Completeness	Explicitly answers both what (validate opportunities, map assumptions, plan sprints, test problem-solution fit) and when ('Use when ... before committing delivery resources') with concrete trigger phrases, matching the 5 anchor; it is not a 4 because the 'when' clause is explicit and specific rather than weakly implied.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a product practitioner would say ('product opportunities', 'assumptions', 'discovery sprints', 'problem-solution fit'), but misses common synonyms like 'user research' or 'customer discovery' that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear product-discovery niche with distinct triggers ('problem-solution fit', 'discovery sprints', 'assumption mapping') and minimal overlap risk; it is not a 4 because the triggers are specific enough to avoid firing for adjacent research or delivery skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: product-team/skills/product-discovery/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.