opportunity-solution-tree

Build an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests. Use when a stakeholder request needs problem framing before you decide what to build.

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

Quality

Content

77%

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 strong, highly actionable interactive playbook with a clear phased workflow, but it is padded with a duplicated purpose statement and OST concept explanation, and it dangles references to template/example files that are not bundled while keeping that material inline.

Suggestions

Delete the duplicated Purpose paragraph (line 12, near-identical to the frontmatter intent) and trim the 'What is an OST' explanation + ASCII tree, which restates a framework Claude already knows.

Create the referenced `template.md` and `examples/sample.md` bundle files and move the full output template and worked example walkthroughs into them, so the inline body slims to an overview — or remove the dangling references if the inline versions are intended to be canonical.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but padded: the Purpose paragraph (line 12) duplicates the frontmatter intent nearly verbatim, and the 'What is an OST' section plus ASCII tree explain a framework Claude already knows. It is not level 3 because of this redundant/conceptual padding, and not level 1 because the bulk (prompts, table, template, pitfalls) earns its place.	2 / 3
Actionability	Highly concrete: exact agent prompts, enumerated response options with worked examples, a fully populated scoring table with real 1-5 values and rationale, scoring criteria definitions, and a copy-paste-ready markdown output template.	3 / 3
Workflow Clarity	Clear two-phase sequence (Step 0 gather context → Phase 1 Q1-3 generate tree → Phase 2 Q4-5 select POC → output) with user-confirmation checkpoints after each question. The destructive/batch feedback-loop cap does not apply to this interactive discovery dialog, so the confirm-and-proceed pattern meets the clear-sequence bar.	3 / 3
Progressive Disclosure	References are signaled (`template.md` at line 93, `examples/sample.md` at line 352, `../workshop-facilitation/SKILL.md` at line 79) but none of these files exist — no references/, scripts/, or assets/ directories are present. Meanwhile the large output template and full worked examples remain inline, i.e. content that should be separate is inline while the referenced separate files are absent. Not level 1 because section headings give real organization; not level 3 because the references are dangling.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 concise, third-person, and cleanly answers both what the skill does and when to invoke it. It names concrete actions and uses natural trigger language with minimal risk of conflicting with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests' names the four distinct artifacts the skill produces, matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Build an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests') and when ('Use when a stakeholder request needs problem framing...'), with a clear 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Natural PM-facing triggers — 'stakeholder request needs problem framing before you decide what to build' — use terms a user would actually say (stakeholder request, problem framing, deciding what to build).	3 / 3
Distinctiveness Conflict Risk	'Opportunity Solution Tree' is a distinct named framework with a specific trigger (problem framing before deciding what to build), giving it a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/opportunity-solution-tree/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.