pol-probe

Define a Proof of Life probe to test a risky hypothesis cheaply. Use when you need harsh truth before building real product.

Quality

60%

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/SKILL.md

Quality

Content

63%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 content is a well-structured, actionable methodology skill with a copy-paste template and a validation checklist, but it carries some conceptual padding and references two bundle files (template.md, examples/sample.md) that are not actually present.

Suggestions

Create the referenced template.md and examples/sample.md bundle files (or remove the references and keep the inlined template) so progressive_disclosure references resolve to real files.

Trim inferable exposition — the origin paragraph, the "What is a PoL Probe?" prose that repeats the frontmatter, and repeated "prototype theater" mentions — to tighten conciseness.

Add a short numbered workflow (define hypothesis → pick prototype flavor → fill template → run Quality Checklist → revise) to make the sequence explicit rather than implicit.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with substantive tables, a template, and a checklist, but includes unnecessary exposition Claude could infer (the origin paragraph, repeated "prototype theater" framing, and a "What is a PoL Probe?" prose block that rehashes the frontmatter), fitting anchor 3.	3 / 5
Actionability	The fill-in PoL Probe Template is copy-paste ready and the Quality Checklist gives concrete verification criteria; per the instruction-skill note the absence of code is not penalized, but the referenced full example (examples/sample.md) is missing, leaving a minor gap at anchor 4.	4 / 5
Workflow Clarity	The skill is single-purpose (document a probe) with an unambiguous action and an explicit validation gate ("If any answer is 'no,' revise your probe"), giving a clear sequence with most checkpoints present at anchor 4, though no numbered step sequence is spelled out.	4 / 5
Progressive Disclosure	Section headers are well organized, but the body references template.md (line 114) and examples/sample.md (line 195) that do not exist in any bundle directory, and the template is inlined while also being pointed to as a separate file, fitting anchor 3 (references present but not cleanly signaled, content that should be separate is inline).	3 / 5
	Total	14 / 20 Passed

Description

57%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 clearly answers what the skill does and when to use it with a recognizable niche framing, but loses points for second-person voice and for trigger phrasing that leans on metaphor ("harsh truth") rather than concrete user-said synonyms.

Suggestions

Rewrite in third person to avoid the second-person penalty: e.g. "Defines a Proof of Life probe to test a risky hypothesis cheaply. Use when harsh truth is needed before building a real product."

Broaden trigger terms with natural synonyms users actually say (validate, experiment, prototype, de-risk) to improve trigger_term_quality.

Make the "when" clause more concrete by naming triggering situations (e.g. "before committing engineering time to a new feature") rather than relying on "harsh truth."

Dimension	Reasoning	Score
Specificity	"Define a Proof of Life probe to test a risky hypothesis cheaply" names the domain plus 1-2 concrete actions (define, test), fitting anchor 3, but the description uses second person ("Use when you need harsh truth...") so specificity is reduced by 1 per the voice guideline.	2 / 5
Completeness	Both what ("Define a Proof of Life probe to test a risky hypothesis cheaply") and when ("Use when you need harsh truth before building real product") are present, but the when clause is somewhat abstract/metaphorical rather than listing concrete triggering situations, fitting anchor 4.	4 / 5
Trigger Term Quality	Natural phrases like "test a risky hypothesis" and "harsh truth" are present, but common synonyms users would say (validate, experiment, prototype, MVP) are missing, matching anchor 3 rather than the broader coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	The "Proof of Life probe" framing carves a clear niche distinct from general build skills, with only minor overlap risk against closely related validation/experimentation skills, matching anchor 4.	4 / 5
	Total	13 / 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: 4 missing, 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/pol-probe/SKILL.md
Commit: a03af68

Reviewed: 20 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.