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

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/derisk-measurement-advisor/SKILL.md

Quality

Content

81%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 highly actionable, well-sequenced interactive skill with verbatim prompts, per-risk triage checkpoints, and a pitfalls checklist. Its main weakness is conciseness — redundant conceptual restatements and illustrative padding inflate an already long single-file body that leans on sibling-skill references rather than its own bundle files.

Suggestions

Collapse the redundant Product/Business Outcome Metrics explanations (Two Lenses section vs. DUFV section) into one and trim the PESTEL Example Risk column and 'Key insight from the classroom' line to tighten conciseness.

Move the full worked example and/or Common Pitfalls into a reference bundle file (e.g. references/example.md) and link to it from the body, improving progressive disclosure and reducing inline length.

Consider extracting the per-dimension test option lists into a reference file so the main body can stay a lean overview while retaining the verbatim prompts.

Dimension	Reasoning	Score
Conciseness	The verbatim facilitation script is necessary for an interactive skill, but the ~460-line body carries redundant explanation — the Purpose restates the description, the Two Lenses and DUFV sections both explain Product/Business Outcome Metrics, and lines like 'Key insight from the classroom' and the PESTEL Example Risk column are padding that could be trimmed.	3 / 5
Actionability	Provides verbatim copy-paste-ready agent prompts (in quotes), numbered response options per dimension, concrete PESTEL starter prompts, a filled risk-register table template, and a complete worked example — fully executable guidance for an instruction skill.	5 / 5
Workflow Clarity	A clearly sequenced flow (Session Start → Step 0 context Q1-4 → Steps 1-3 risk scan Q1-10 → Step 4 synthesis) with progress labels, an explicit context-summary checkpoint after Q4, per-risk act/watch triage validation, and a Common Pitfalls checklist with a 40/60 corrective feedback loop.	5 / 5
Progressive Disclosure	Good section structure and clearly signaled sibling-skill references (workshop-facilitation as interaction protocol, pestel-analysis for deep dives), but the skill is a single 460-line monolithic file with the worked example, pitfalls, and detailed starters inlined rather than split into bundle files.	4 / 5
	Total	17 / 20 Passed

Description

75%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 concise, well-constructed description that clearly states both capability and trigger, using third person with concrete verbs. It is strong across the board but stops short of the top anchor on every dimension due to limited synonym coverage and a single trigger phrase.

Suggestions

Add 1-2 more natural trigger phrases to the 'Use when' clause (e.g., 'before putting an idea on the roadmap' or 'when deciding what to test first') to lift completeness and trigger_term_quality toward 5.

Mention the output artifact (a prioritized risk register with act-now vs. watch triage) to broaden specificity and distinctiveness beyond the measurement verbs.

Include a common synonym such as 'validation' or 'what could go wrong' so users who don't say 'stress-testing' still land on this skill.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions — "measure, test, or track" plus "de-risk" and "stress-testing" — placing it above the 1-2-action anchor (3) but short of comprehensive coverage (5) since triage/register outputs are not enumerated.	4 / 5
Completeness	Explicitly answers both what ("Identify what to measure, test, or track to de-risk...") and when ("Use when stress-testing an idea across internal (DUFV) and external (PESTEL) dimensions"), but the when clause offers one main trigger rather than the multiple concrete trigger phrases of the 5 anchor.	4 / 5
Trigger Term Quality	Includes natural phrases a PM would say ("stress-testing an idea", "de-risk", "product or AI idea") plus framework terms (DUFV, PESTEL), but lacks several common synonyms like "risk register", "validation", or "what could go wrong" that would merit a 5.	4 / 5
Distinctiveness Conflict Risk	The DUFV+PESTEL de-risking framing carves a clear niche with distinct triggers, but the explicit PESTEL mention creates minor overlap risk with a dedicated pestel-analysis sibling skill, keeping it just below 5.	4 / 5
	Total	16 / 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: 6 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/derisk-measurement-advisor/SKILL.md
Commit: 1b5a524

Reviewed: 4 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.