onboard

Interactive vault setup and context loading. On first run, personalizes your vault. On subsequent runs, loads full context. Use at start of session or when Claude needs full vault context.

Quality

62%

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 ./vault-template/.claude/skills/onboard/SKILL.md

Quality

Content

50%

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

The skill delivers a concrete, well-sequenced first-run setup but pads the body with generic best-practice material and leaves the context-loading workflow descriptive and checkpoint-free, with no progressive file-based disclosure.

Suggestions

Trim the Best Practices, Privacy & Security, and Integration sections to a few essential rules, or move them into a separate reference file linked from SKILL.md.

Add validation checkpoints to the first-run flow (confirm vault-config.json written and CLAUDE.md edits applied before running `rm FIRST_RUN`) and give the subsequent-run context loading a concrete sequenced procedure with exact glob patterns and depth limits.

Replace the descriptive 'What This Skill Does' bullets with executable commands or specific file-discovery patterns so the context-loading half is as actionable as the setup half.

Dimension	Reasoning	Score
Conciseness	The first-run setup section is efficiently concrete, but later sections (Best Practices, Privacy & Security, Context Variables, Integration) restate generic guidance Claude already knows and pad the ~270-line body, so it is mostly efficient with unnecessary explanation that could be trimmed.	2 / 3
Actionability	The setup steps give copy-paste-ready questions, options, and an exact config JSON, but the context-loading half only describes actions ("Discovers Context Files", "Traverses project directories", "Respects depth limits") without concrete commands or specifics like the actual depth limit, leaving guidance incomplete.	2 / 3
Workflow Clarity	The first-run flow is a clear 6-step sequence, but it lacks validation checkpoints (e.g., verifying vault-config.json was written, confirming CLAUDE.md edits) before the destructive `rm FIRST_RUN` step, and the subsequent-run context loading is only a descriptive bullet list with no sequenced checkpoints.	2 / 3
Progressive Disclosure	No bundle files exist in references/scripts/assets and the body references no separate files, so everything is inline; sections are well-organized but content that could be split (CLAUDE.md templates, best practices) is monolithic with no one-level-deep reference navigation, and the over-50-line simple-skill exemption does not apply.	2 / 3
	Total	8 / 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.

The description clearly covers both what the skill does and when to use it with a distinct vault-setup niche, but its action list is only partially specific and its trigger terms rely on domain jargon with limited natural-language coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and some actions ("vault setup", "context loading", "personalizes your vault", "loads full context") but the actions are not comprehensive and "personalizes your vault" is somewhat abstract, so it sits at the names-domain-and-some-actions anchor rather than listing multiple concrete actions.	2 / 3
Completeness	It explicitly states what it does (setup on first run, context loading on subsequent runs) and includes an explicit when clause ("Use at start of session or when Claude needs full vault context"), answering both what and when.	3 / 3
Trigger Term Quality	Relevant terms like "vault setup", "context loading", "start of session", and "full vault context" appear, but coverage of natural user phrasings is partial and leans on domain-internal jargon ("vault", "onboard"), missing common variations a user might say.	2 / 3
Distinctiveness Conflict Risk	The vault-personalization and full-context-loading niche is distinct, and the "first run" vs "subsequent runs" framing plus "start of session" trigger make it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: ballred/obsidian-claude-pkm
Path: vault-template/.claude/skills/onboard/SKILL.md
Commit: ef1e4da

Reviewed: about 2 hours 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.