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

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

67%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-structured, actionable interactive skill with concrete tools, scripted prompts, success-criteria templates, and a clear sequenced workflow with a feedback loop. Its weaknesses are notable redundancy across the three presentations of the five probe types and inline content that could be offloaded to a reference file.

Suggestions

Collapse the three renderings of the 5 probe flavors into one authoritative table plus one detailed section, removing the duplicated Step 1 options list.

Move the per-probe detail blocks (methods, tools, success criteria, disposal) into a references/probe-flavors.md file and keep SKILL.md as a quick-reference + decision flow.

Drop the verbatim duplication of the intent paragraph in the Purpose section and trim chatty asides ('you should') to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body carries valuable domain specifics Claude would not know, but the 5 probe flavors are described three times (quick-reference table, Step 1 options, Step 2 detailed options), the Purpose section duplicates the frontmatter intent verbatim, and chatty lines like 'you should' add padding that could be tightened.	3 / 5
Actionability	Concrete facilitation scripts, named tools (UsabilityHub, Loom, Replit, Synthea), method lists, and templated success criteria (e.g. '80%+ users complete task in <2 minutes') give mostly executable guidance, with the minor gap that artifact generation delegates to an external pol-probe template not shown here.	4 / 5
Workflow Clarity	Steps 0-4 are clearly sequenced with user-selection checkpoints at each decision point and a refine/iterate feedback loop in Step 4, plus prototype-theater detection in Example 4; the main flow lacks one explicit 'confirm before recommending' checkpoint, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Good section structure with clear headers, and it appropriately delegates the facilitation protocol to workshop-facilitation and artifact generation to pol-probe (one-level-deep references); however all five probe-by-probe details are inlined in a ~500-line file rather than split into a reference file, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

70%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 specific and distinguishable, with good natural trigger terms and both a what and a when present. Its main weakness is that the 'when' is phrased as purpose rather than as an explicit trigger condition, and it lists a single action rather than comprehensive capabilities.

Suggestions

Rewrite the second sentence as an explicit trigger, e.g. 'Use when choosing how to validate a hypothesis or deciding which prototype/proof-of-concept to run.'

Add 1-2 more concrete actions or synonyms (e.g. 'prototype', 'experiment', 'test an idea') to broaden natural trigger coverage.

State the scope boundary in the description (e.g. 'for pre-MVP validation, not MVP delivery') to further reduce overlap with build-oriented skills.

Dimension	Reasoning	Score
Specificity	It names the domain ('Proof of Life (PoL) probe') and one concrete action ('Select the right probe') plus the decision criteria (hypothesis, risk, resources), but does not enumerate multiple distinct actions, so it is not comprehensive.	3 / 5
Completeness	A clear 'what' (select the right PoL probe) is paired with a stated 'Use this to...' clause indicating the triggering situation, but the 'when' is purpose-framed rather than a crisp 'Use when...' trigger phrase and could be more explicit.	4 / 5
Trigger Term Quality	Natural terms like 'hypothesis', 'risk', 'resources', and 'validation method' appear and would be said by a PM, though synonyms such as 'prototype', 'experiment', or 'test the idea' are missing.	4 / 5
Distinctiveness Conflict Risk	The PoL-probe-selection niche is distinct with its own trigger vocabulary, with only minor overlap risk against closely related validation/discovery skills.	4 / 5
	Total	15 / 20 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 (507 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: a03af68

Reviewed: 11 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.