understand-onboard

Use when you need to generate an onboarding guide for new team members joining a project

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./understand-anything-plugin/skills/understand-onboard/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable, and well-validated workflow with concrete executable commands. The main weaknesses are an inline reference taxonomy that could be externalized and trimmed, affecting both conciseness and progressive disclosure.

Suggestions

Move the full Graph Structure Reference (node/edge type taxonomy) into a separate file such as references/graph-structure.md and keep only the essential summary inline, improving both conciseness and progressive disclosure.

Trim the exhaustive edge-type and node-type lists to only the types the onboarding workflow uses (file-level types, layers, tour), cutting tokens that do not earn their place for this specific task.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids generic-concept padding, but the exhaustive node-type and edge-type taxonomy in 'Graph Structure Reference' is more reference material than the onboarding workflow actually consumes.	2 / 3
Actionability	Steps include fully executable, copy-paste-ready bash (the UA_DIR resolution and git diff block) and specific Grep targets like '"layers"' and '"tour"'.	3 / 3
Workflow Clarity	Eleven sequenced steps with an explicit validation checkpoint (graph-freshness check in step 2) and a feedback loop ('Run /understand to refresh the graph') for error recovery.	3 / 3
Progressive Disclosure	Sections are well-organized and there are no bundle files, but the sizable Graph Structure Reference block is reference-style content kept inline in a skill over 50 lines rather than split into a separate file.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 clear, well-targeted description with an explicit 'Use when...' trigger, but it names only one action and a narrow set of trigger terms. Broadening the action list and trigger variations would raise specificity and trigger-term quality.

Suggestions

List multiple specific concrete actions to raise specificity, e.g. 'Generate onboarding guides, architecture overviews, file maps, and complexity hotspot reports for new team members.'

Broaden trigger term coverage with natural variations users would actually say, e.g. 'Use when onboarding new developers, ramping up new team members, or creating a welcome/onboarding guide for a project.'

Dimension	Reasoning	Score
Specificity	It names the domain ('onboarding guide for new team members joining a project') and one concrete action ('generate'), but lists only a single action rather than multiple specific concrete actions.	2 / 3
Completeness	An explicit 'Use when...' clause provides the trigger and the 'what' (generate an onboarding guide) is clearly stated, answering both what and when.	3 / 3
Trigger Term Quality	Terms like 'onboarding guide' and 'new team members' are natural, but coverage is a single framing and misses common variations users might say ('ramp up', 'developer onboarding', 'welcome guide').	2 / 3
Distinctiveness Conflict Risk	The onboarding-guide-generation niche has distinct triggers and is unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Egonex-AI/Understand-Anything
Path: understand-anything-plugin/skills/understand-onboard/SKILL.md
Commit: 6ae7187

Reviewed: 4 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.