llm-wiki

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

86%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 well-architected skill body: highly actionable with executable commands and tool tables, excellent progressive disclosure to verified one-level-deep bundles, and a clear ingest/query/lint workflow with validation via lint and approval gates. Only mild conciseness drift from the duplicated RAG-versus-wiki framing.

Suggestions

Collapse the 'Core principle' and 'Why this works (vs plain RAG)' sections into one, since both restate the RAG-vs-compounding argument.

Surface a one-line validate→fix→retry loop inline in the ingest quick-start (e.g. 'run /wiki-lint after ingest; fix flagged contradictions before next ingest') rather than deferring entirely to references/lint-workflow.md.

Trim the 'When to use' bullet list or move niche examples (trip planning, course notes) to a reference to tighten the overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (architecture, slash-command and script tables earn their place), but the 'Core principle' and 'Why this works (vs plain RAG)' sections restate the same RAG-vs-compounding argument, and the body runs ~167 lines that could be trimmed slightly.	4 / 5
Actionability	Copy-paste-ready quick-start commands, a slash-command table, a scripts table with per-tool purposes and `python scripts/<tool>.py --help` invocation, plus concrete Obsidian setup specifics (hotkey, attachment path) cover the common cases.	5 / 5
Workflow Clarity	The three core operations and numbered quick-start give a clear sequence, and the lint operation plus sub-agent 'applies after your approval' and the iron-rule guardrail provide validation checkpoints; minor gaps remain because detailed validate→fix→retry loops live in the referenced files rather than the body.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with a dedicated 'Reference docs' section and tables pointing one level deep to real, verified bundles in references/, scripts/, and assets/ (page-templates/ and example-vault/ confirmed present), making navigation easy.	5 / 5
	Total	18 / 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.

A strong, third-person description that pairs concrete capability statements with an explicit trigger clause and a rich set of natural keyword synonyms. It clearly delineates its niche against plain RAG, leaving little conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (build/maintain a persistent knowledge base, ingest, update pages, cross-reference, synthesize) and when via an explicit 'Use when...' clause with concrete trigger phrases; voice is third person.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases including synonyms: 'second brain', 'Obsidian wiki', 'personal knowledge management', 'ingest this paper/article/book', 'build a research wiki', 'compound knowledge', 'Memex'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Obsidian second-brain / Memex) with distinct triggers and a concrete anti-trigger ('instead of being re-derived by RAG on every query'), minimizing conflict risk.	5 / 5
	Total	20 / 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

Repository: alirezarezvani/claude-skills
Path: engineering/llm-wiki/skills/llm-wiki/SKILL.md
Commit: 19392f7

Reviewed: ~5 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.