Name: personwise/personwise-end-user-software-training
Rating: 68 (1 reviews)
Author: personwise

personwise/personwise-end-user-software-training

End users learn systems from whoever sits nearby — and their mistakes become your support queue. Turn your training guides into an interactive digital-human end-user software training course that walks users through the real workflows from your documentation. Screens, permissions, and click paths come only from your guides; the course never invents UI.

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.

A highly actionable, well-sequenced procedural skill with strong validation and error-recovery feedback loops. Its main weaknesses are repeated restatement of the same source-pending semantics and a monolithic structure that inlines detail a separate reference file could carry.

Suggestions

Consolidate the awaiting-sources / run-advance no-op explanation into one section and reference it from the other two locations instead of restating it three times.

Move the detailed CLI command catalog and update-freshness rules into a references/ file (e.g. CLI_REFERENCE.md) and link to it from SKILL.md to improve progressive disclosure.

Tighten the update-freshness section by merging the repeated 'never substitute another command/flag/origin' admonitions into a single stated rule.

Dimension	Reasoning	Score
Conciseness	The body is densely operational and avoids explaining concepts Claude already knows, but the awaiting-sources / run-advance no-op semantics are restated three times across sections and several passages could be tightened without losing clarity.	3 / 5
Actionability	Fully executable guidance throughout — concrete copy-paste-ready commands with flags and --json outputs (e.g. 'personwise --account <alias> course readiness --json', 'personwise auth begin --service personwise.ai --json') covering the common cases.	5 / 5
Workflow Clarity	Clear end-to-end sequence (version → bootstrap → auth → freshness → classify → readiness → blueprint → sources → wait → review → patch → publish) with explicit validation checkpoints, fresh-read-before-mutate rules, --expected-revision, and feedback loops for source retry and conflict resolution.	5 / 5
Progressive Disclosure	Section headers organize the content and bundled asset paths (assets/bootstrap.sh, assets/bootstrap.ps1) are referenced correctly, but the dense CLI procedural detail is all inlined in SKILL.md with no references/ split, so content that could live one level deeper remains inline.	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.

A strong, well-scoped description that clearly states both capability and trigger conditions with concrete, natural trigger language and explicit boundaries against adjacent skills. Minor room to broaden trigger synonyms and tighten the action inventory.

Dimension	Reasoning	Score
Specificity	Lists 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 only minor gaps in coverage of the full course-creation action set.	4 / 5
Completeness	Explicitly answers both 'what' (produce a grounded interactive digital-human course) and 'when' ('Use when the user asks for End-User Software Training... Trigger language: ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides good natural keyword coverage ('end-user training; software user training; CRM training; ERP user training') that users would plausibly say, though a few common synonyms or phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct end-user-qualified triggers, explicit routing to the Internal Change Adoption Skill for broader rollouts, and explicit exclusion of admin/developer documentation, minimizing conflict risk.	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