Name: personwise/personwise-customer-education
Rating: 66.4 (1 reviews)
Author: personwise

personwise/personwise-customer-education

Customers keep asking the same questions, and every repeat answer costs support time. Turn your help content and product knowledge into an interactive digital-human customer education course that answers learner questions on its own — a customer academy asset for your help center, portal, or CSM follow-ups. Account-specific diagnosis always routes back to your support team.

Quality

83%

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

Quality

Content

77%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 CLI orchestration skill with strong validation and recovery loops. Its main weaknesses are repetitive restatements of the same rules and a monolithic structure that could offload detail into reference files.

Suggestions

Consolidate the awaiting_sources no-op guidance and the "never create a replacement run" rule into a single authoritative statement instead of restating them across three sections.

Move the lengthy CLI/Skill freshness-update procedure and the source-upload lifecycle into separate reference files (e.g. UPDATE.md, SOURCES.md) referenced one level deep from SKILL.md.

Trim the repeated re-derivation of the same conflict/awaiting_sources handling in the "Finish, recover, and report" section since it duplicates earlier guidance.

Dimension	Reasoning	Score
Conciseness	The body is operational rather than concept-explaining, but several rules are restated multiple times (the awaiting_sources no-op behavior at three points, "never create a replacement run" at three points), which could be tightened.	3 / 5
Actionability	It provides fully executable, copy-paste-ready commands with exact flags (e.g. "personwise --account <alias> course readiness --json", "course create --input <blueprint.json> --json") covering the common cases.	5 / 5
Workflow Clarity	The course-creation process is clearly sequenced (version → bootstrap → auth → update check → classify → readiness → blueprint → upload → wait → review → finish) with explicit validation checkpoints and bounded feedback loops for source failures and conflicts.	5 / 5
Progressive Disclosure	Section headers organize the content well and the referenced assets/bootstrap.sh and bootstrap.ps1 are real bundle files, but the bulk of procedural detail (freshness updates, source lifecycle) is inlined rather than split into one-level-deep reference files.	3 / 5
	Total	16 / 20 Passed

Description

83%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 strong description that clearly states both capability and trigger conditions with concrete, third-person phrasing and explicit trigger language. It could be slightly tightened on synonym coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("Produce a grounded interactive digital-human course learners can interrupt with voice questions", "install or update the official PersonWise CLI", "uses browser OAuth"), with minor gaps such as assessments and source upload left to the body.	4 / 5
Completeness	It explicitly answers both what ("Produce a grounded interactive digital-human course...") and when ("Use when the user asks for Customer Education..." plus explicit trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	"Trigger language: customer education; customer training; customer academy; support deflection" gives good natural-term coverage, though a few common synonyms are absent and "support deflection" leans toward internal jargon.	4 / 5
Distinctiveness Conflict Risk	The PersonWise digital-human course niche is mostly distinct with clear triggers, but "customer training"/"support deflection" carry minor overlap risk with general training or support skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Reviewed

21 days ago

Table of Contents

Discovery Implementation Validation