pol-probe-advisor

Select the right Proof of Life (PoL) probe based on hypothesis, risk, and resources. Use this to match the validation method to the real learning goal, not tooling comfort.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/pol-probe-advisor/SKILL.md

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 content is highly actionable with a clear, well-sequenced workflow and concrete examples, but it is verbose with duplicated probe definitions and inlines material that would benefit from being split into separate reference files.

Suggestions

De-duplicate the 5 probe definitions: keep the quick-reference table in SKILL.md and move the full per-probe methods/tools/success-criteria blocks into one reference file (e.g. references/probe-flavors.md) linked from Step 2.

Remove the verbatim repeat of the frontmatter intent in the Purpose section, keeping only the additional framing that adds new information.

Verify or mark the cross-skill links (../workshop-facilitation, ../pol-probe, etc.) as external dependencies so the bundle's progressive-disclosure structure is honest about what is and isn't included.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the 5 probe flavors are fully restated after the quick-reference table, the frontmatter intent is repeated verbatim in Purpose, and Step 2's per-option blocks repeat methods/timelines already tabulated, so it could be tightened.	2 / 3
Actionability	Provides concrete, specific guidance throughout: named tools per probe (Optimal Workshop, UsabilityHub, Synthea, Replit), quantitative success criteria (e.g. "80%+ users complete task in <2 minutes"), timelines, disposal plans, and worked examples with reasoning — copy-ready actionable instruction.	3 / 3
Workflow Clarity	Clear numbered sequence (Step 0 gather context → Step 1 core question → Step 2 recommend → Step 3 apply → Step 4 refine/iterate) with an explicit refine-or-iterate feedback loop and clarifying questions for ambiguous hypotheses.	3 / 3
Progressive Disclosure	Sections are well-organized and cross-skill references are clearly signaled, but the five full probe specifications (methods, tools, success criteria, disposal plans) are inlined in one ~485-line file rather than split into per-probe reference files, and the referenced bundle paths (../pol-probe/SKILL.md, ../workshop-facilitation/SKILL.md) do not exist in this bundle.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 clear and occupies a distinct niche, but its triggering guidance is abstract rather than situation-based and it relies on framework-specific jargon, so it lands in the middle band on completeness and trigger quality.

Suggestions

Rewrite the trigger as concrete situations, e.g. "Use when a user asks which validation method or prototype to run for a hypothesis, or needs to pick the cheapest way to test a risky idea before building."

Add the natural-language phrasings users actually say ("which validation method", "prototype", "test this idea cheaply") alongside "PoL probe" so it surfaces for users unfamiliar with the term.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Select the right Proof of Life (PoL) probe") plus the inputs (hypothesis, risk, resources), but it is a single selection action rather than a list of multiple specific actions, so it stops short of the top anchor.	2 / 3
Completeness	It states what the skill does and has an explicit "Use this to..." clause, but the trigger reads as a purpose statement ("match the validation method to the real learning goal, not tooling comfort") rather than concrete triggering situations, leaving the "when" abstract rather than fully explicit.	2 / 3
Trigger Term Quality	Includes relevant terms ("Proof of Life (PoL) probe", "hypothesis", "validation method") but leans on the coined "PoL probe" jargon and omits common phrasings a user would naturally say (e.g., "which validation method", "prototype"), missing common variations.	2 / 3
Distinctiveness Conflict Risk	The Proof of Life probe-selection niche across 5 specific flavors is clearly distinct and unlikely to trigger for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (505 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 6 suspicious	Warning

	Total	13 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/pol-probe-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.