Name: personwise/personwise-customer-onboarding
Rating: 68 (1 reviews)
Author: personwise

personwise/personwise-customer-onboarding

Every new customer asks the same first-week questions, and your team answers them one call at a time. Turn your confirmed onboarding materials into an interactive digital-human course that walks new customers from signup to first value and answers their questions along the way. Built only on confirmed scope, timelines, and support channels — never invented promises.

Quality

85%

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.

The body is a highly actionable, well-sequenced CLI workflow with strong validation and error-recovery loops, scoring top marks on actionability and workflow clarity. Its weaknesses are token efficiency (repeated caveats and dense inline enumerations) and progressive disclosure (operational detail that could move to reference docs).

Suggestions

Consolidate the repeated awaiting_sources / 200-no-op explanation into one canonical paragraph and cross-reference it to lift conciseness.

Move the detailed update-handling and source-lifecycle protocols into a references/ doc (e.g., UPDATE-PROTOCOL.md, SOURCE-LIFECYCLE.md) and link from the body to improve progressive_disclosure.

Trim 'Never X, Y, Z' enumeration lists to the highest-risk items and group the rest under a single 'do not substitute origins, credentials, or paths' rule.

Dimension	Reasoning	Score
Conciseness	The guidance is domain-specific and mostly earns its tokens, but the awaiting_sources / 200-no-op caveat is restated three times (lines 207-212, 218-220, 294-298) and several 'Never X, Y, Z' enumerations could be consolidated, fitting 'mostly efficient but could be tightened' rather than the lean 4.	3 / 5
Actionability	Provides fully executable commands with exact flags and arguments (e.g., 'personwise --account <alias> course readiness --json'), precise JSON fields, and named error codes like 'CLI_VERSION_BELOW_MINIMUM' and 'page_quota_exceeded', matching the copy-paste-ready top anchor.	5 / 5
Workflow Clarity	A clear sequenced workflow (version check → bootstrap → auth → update check → readiness → blueprint → sources → run wait → review → publish) with explicit validation checkpoints and feedback loops (conflict → read_current_state → retry; source fail → retry/detach → replace), matching the explicit-checkpoints anchor.	5 / 5
Progressive Disclosure	Clear section headers and real, one-level-deep asset references (assets/bootstrap.sh, assets/bootstrap.ps1) that exist on disk, but the bulk of the detailed operational protocol (update handling, source lifecycle) is inlined rather than split into reference files, fitting 'some structure but could be better organized' over the well-split 4.	3 / 5
	Total	16 / 20 Passed

Description

87%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 strong: it answers both what and when explicitly, uses third person, and supplies concrete trigger language with synonyms. Minor room to expand trigger synonyms and enumerate a few more concrete actions to lift specificity and trigger coverage to the top anchor.

Suggestions

Add a few more natural trigger variants (e.g., 'customer training course', 'client implementation kickoff') to broaden trigger_term_quality.

Name one or two additional concrete course-production actions (e.g., 'compose teaching arc', 'attach source documents') to push specificity toward the comprehensive anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Produce a grounded interactive digital-human course learners can interrupt with voice questions' and 'install or update the official PersonWise CLI and uses browser OAuth' — with only minor coverage gaps, fitting the 'lists several specific actions' anchor rather than the comprehensive 5 or the minimal 3.	4 / 5
Completeness	Explicitly answers both 'what' ('Produce a grounded interactive digital-human course...') and 'when' ('Use when the user asks for Customer Onboarding Course... Trigger language: ...'), matching the anchor for clearly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	'Trigger language: customer onboarding; client onboarding; onboarding training; implementation start' gives good natural-term coverage with synonyms, but a few common variants are absent, placing it just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (customer onboarding courses) with distinct triggers and explicit exclusions ('Do not use it for employee or new-hire onboarding'), minimizing conflict risk per the 'clear niche' anchor.	5 / 5
	Total	18 / 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