obsidian-project-kb-core

Use this as the main Claude Scholar skill for a vault-first, project-scoped Obsidian research knowledge base rooted at Research/{project-slug}/. It owns bootstrap, routing, daily logging, hub/plan/index maintenance, registry updates, lifecycle actions, and lint orchestration.

Quality

71%

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 ./skills/obsidian-project-kb-core/SKILL.md

Quality

Content

68%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.

An exemplary token-efficient router skill with verified one-level-deep references and no padding. Its weaknesses are execution-level vagueness (scripts named by category, never invoked) and the absence of validation/feedback checkpoints around destructive lifecycle actions like purge.

Suggestions

In 'Deterministic helpers', name the actual scripts and their invocations (e.g. 'python scripts/kb_scaffold.py' for scaffold, 'python scripts/kb_lint.py' for lint aggregation) instead of listing them only by category.

Add an explicit validation loop for destructive lifecycle actions: after create/rename/archive/purge, run the lint or link-check script and only report success when it passes.

Annotate each 'Read next' entry with a one-line scope (e.g. 'references/REGISTRY.md — registry sections, ID defaults, and rules') so the correct reference can be selected without opening all seven.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview: a directory tree, terse core rules, and a plain responsibilities list with zero over-explanation of concepts Claude already knows. Every line carries non-obvious project-specific information.	5 / 5
Actionability	Concrete artifacts are named (the full directory tree, 00-Hub.md, _system/registry.md, routing destinations), but scripts are referenced only by category ("Use the scripts under `scripts/` for: scaffold, registry consistency, link checks...") with no filenames or invocations, leaving the specific steps to execute unstated.	3 / 5
Workflow Clarity	The responsibilities imply a sequence (detect/bind, bootstrap, route, update, health checks) and lint serves as a check, but destructive lifecycle actions like "purge" have no explicit validation checkpoints or fix-and-retry feedback loop, which caps this at 3.	3 / 5
Progressive Disclosure	The body is a clean overview with a one-level-deep "Read next" list whose seven references all exist as real files, and the scripts directory contains matching helpers. Minor gap: references are bare paths with no hint of when to read which.	4 / 5
	Total	15 / 20 Passed

Description

75%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 with an explicit capability inventory and a distinct niche. Its main weaknesses are a scope-defining rather than behavior-triggering 'when' clause and missing natural synonym terms (notes, daily notes, zettelkasten).

Dimension	Reasoning	Score
Specificity	Lists seven named actions ("bootstrap, routing, daily logging, hub/plan/index maintenance, registry updates, lifecycle actions, and lint orchestration") with a concrete root path, but "lifecycle actions" and "routing" remain umbrella terms, so coverage is several specific actions with minor gaps rather than fully comprehensive.	4 / 5
Completeness	The 'what' is explicit (the enumerated owned responsibilities) and a 'Use this as...' clause provides equivalent trigger guidance, but the 'when' is scope-defining rather than behavior-triggering, so it could be more specific.	4 / 5
Trigger Term Quality	Natural terms users would say are present ("Obsidian", "research knowledge base", "vault", "project"), but common variations like "notes", "daily notes", or "wikilinks" are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The project-scoped Obsidian research KB niche is clearly distinct, but it could still overlap with generic Obsidian or note-management skills since triggers don't fully separate it.	4 / 5
	Total	16 / 20 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: Galaxy-Dawn/claude-scholar
Path: skills/obsidian-project-kb-core/SKILL.md
Commit: 9037873

Reviewed: 2 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.