derisk-measurement-advisor

Identify what to measure, test, or track to de-risk a product or AI idea. Use when stress-testing an idea across internal (DUFV) and external (PESTEL) dimensions.

Quality

81%

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.

A thorough, highly actionable facilitation skill with a clearly sequenced multi-step workflow and concrete prompts. It loses points for verbosity (re-explaining known frameworks, a long inline example) and for keeping all content in one large file rather than progressively disclosing detail into reference files.

Suggestions

Move the full worked example (and optionally the per-dimension starter prompts) into a reference file the body links to, keeping SKILL.md as a lean overview of the workflow.

Tighten or remove the framework-explanation tables (DUFV quadrants, PESTEL category definitions) that restate concepts Claude already knows, retaining only the skill-specific framing.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but ~485 lines with re-explanation of frameworks Claude already knows (Marty Cagan's four risks, PESTEL via tables), restating of the frontmatter framing in the Purpose section, and a lengthy full worked example that could be trimmed.	2 / 3
Actionability	Highly concrete guidance: exact agent opening prompts, numbered quick-select options, specific test/metric lists per dimension, and a ready-to-fill risk-register table with concrete 'Recommended First Step' examples.	3 / 3
Workflow Clarity	Clear sequenced workflow (Step 0 context Q1-4, Steps 1-3 risk scans Q1-10, Step 4 synthesize) with progress labels, a summarize-after-Q4 checkpoint, an act/watch triage checkpoint at each risk, and a Common Pitfalls section for error recovery.	3 / 3
Progressive Disclosure	Well-organized into labeled sections with clearly signaled one-level-deep related-skill references, but it is a single monolithic ~485-line file with the full facilitation script and worked example inline rather than split into bundle reference files.	2 / 3
	Total	10 / 12 Passed

Description

85%

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, complete description that states concrete actions and an explicit 'Use when' trigger, with a clear distinct niche. Its main weakness is the 'when' clause's reliance on DUFV/PESTEL jargon over natural user phrasing and a lack of common trigger variations.

Suggestions

Replace or supplement the DUFV/PESTEL acronyms in the trigger clause with natural phrases a PM would say, e.g. 'Use when deciding what could go wrong with a product or AI idea and what to test or track first.'

Add common trigger variations such as 'risks', 'what could go wrong', or 'what should we test before committing' to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Identify what to measure, test, or track to de-risk' — naming specific verbs rather than vague capability language.	3 / 3
Completeness	Explicitly answers both 'what' (identify what to measure, test, or track to de-risk an idea) and 'when' (an explicit 'Use when stress-testing an idea...' trigger clause).	3 / 3
Trigger Term Quality	Has natural terms ('de-risk', 'stress-testing', 'measure, test, or track', 'product or AI idea') but the 'when' clause leans on jargon acronyms (DUFV, PESTEL) a user would not naturally say, and common variations like 'what could go wrong' or 'risks' are absent.	2 / 3
Distinctiveness Conflict Risk	Carves a clear niche (de-risking product/AI ideas across internal and external dimensions) with distinct triggers unlikely to fire for unrelated skills.	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: 6 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/derisk-measurement-advisor/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.