llm-wiki

Create or update an Obsidian-friendly local markdown knowledge base. Use when the user wants LLM-maintained notes, wikilinks/backlinks, frontmatter, citations, local attachments, vault cleanup, or reusable research synthesis.

Quality

100%

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

Quality

Content

100%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 content is a dense, well-structured overview that combines concrete output shapes, executable commands, and explicit validation gates, with advanced detail appropriately deferred to a real, well-organized references/ bundle. It respects Claude's intelligence while adding only skill-specific policy.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense — sections like 'Philosophy: Cited local files beat remembered answers' and tight workflow sentences assume Claude's competence and add only non-obvious skill-specific policy, with every token earning its place.	5 / 5
Actionability	Concrete output shapes, a complete copy-paste ingest example with frontmatter/citations/wikilinks/index/log, and exact commands (`rg -n "\[\[[^]]+\]\]" wiki/`, `find raw/assets -type f`) give fully executable, copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	Ingest, Query, and Lint workflows are clearly sequenced, and the 'Update Gates' section provides explicit fail-fast validation checkpoints with a feedback loop ('stop at the first failed gate; do not proceed'), matching the 5-anchor pattern for destructive/batch operations.	5 / 5
Progressive Disclosure	The body is a compact overview with a 'Progressive Disclosure' section that names exactly when to consult references/, and the verified references/ bundle (contract.yaml, discovery-interview.md, evals.yaml, lint-report-v1.md, obsidian-vault-contract.md, operating-contract.md, task-profile.json) are all real one-level-deep files clearly signaled by topic, giving easy navigation.	5 / 5
	Total	20 / 20 Passed

Description

100%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 a strong, concise statement that covers both capability and explicit trigger conditions with concrete, natural-language terms. It is distinct from generic note/document skills and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities — 'Create or update', 'wikilinks/backlinks', 'frontmatter', 'citations', 'local attachments', 'vault cleanup', 'reusable research synthesis' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ('Create or update an Obsidian-friendly local markdown knowledge base') and when ('Use when the user wants...') with concrete trigger phrases, matching the 5-anchor example closely.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms users actually say — 'LLM-maintained notes', 'wikilinks/backlinks', 'frontmatter', 'citations', 'vault cleanup', 'reusable research synthesis' — with the domain term 'Obsidian' included.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (LLM-maintained Obsidian markdown wiki) with distinct, specific triggers that would not fire for generic note or document skills, giving minimal conflict risk.	5 / 5
	Total	20 / 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: jscraik/Agent-Skills
Path: Skills/content-publishing/llm-wiki/SKILL.md
Commit: 0c01b2e

Reviewed: 3 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.