llm-wiki

The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).

Quality

75%

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/llm-wiki/SKILL.md

Quality

Content

63%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 thorough, well-structured foundational reference with highly actionable templates, formulas, and shell functions, weakened mainly by its length and a progressive-disclosure gap: heavy operational detail is inlined and the existing reference bundle is not navigated to. Workflow sequencing and validation are solid for a theory skill.

Suggestions

Link references/karpathy-pattern.md from the body (e.g., in an opening or 'Reference' section) so the provided bundle is discoverable rather than orphaned.

Move the dense operational policy that sibling skills own (confidence-score buckets, lifecycle state machine, config-resolution shell functions) into reference files and keep SKILL.md as a concise overview pointing one level deep.

Tighten the longest sections — consolidate the env-var list and tier/lifecycle tables to the essentials, trimming detail that 'wiki-lint' and 'wiki-ingest' already cover.

Dimension	Reasoning	Score
Conciseness	The ~630-line body is mostly skill-specific policy that earns its place (no padding with general concepts Claude already knows), but the sheer volume of inline operational detail — full bash functions, confidence-score buckets, lifecycle state machine, env-var list — could be tightened or moved to references, matching 'mostly efficient but could be tightened.'	3 / 5
Actionability	Provides concrete, copy-paste-ready material — full page and paper-deep-dive templates, provenance marker syntax, a numeric confidence formula with source-quality buckets, retrieval-primitive commands, and config-resolution shell functions — with only minor gaps because operational execution is partly deferred to sibling skills.	4 / 5
Workflow Clarity	Embedded mini-workflows are clearly sequenced (config resolution order 0–3 with explicit fallback, append/rebuild/restore modes, lifecycle transitions) and validation mechanisms are named (manifest delta, staleness detection, wiki-lint recomputing provenance and flagging drift), with only minor checkpoint gaps since destructive operations are delegated to wiki-rebuild.	4 / 5
Progressive Disclosure	Section headers organize the content well, but the body is a large near-monolithic block with operational policy that could be split into reference files, and the one provided bundle file (references/karpathy-pattern.md) is never linked or signaled from the body.	3 / 5
	Total	14 / 20 Passed

Description

87%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 that clearly states what the skill does and when to use it, with concrete trigger phrases and explicit disambiguation from sibling operational skills. It is slightly conceptual rather than operationally concrete, keeping specificity and trigger-term quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'building and maintaining,' 'set up a new knowledge base,' 'understand the wiki pattern,' 'guidance on the three-layer architecture' — but the verbs lean conceptual (a 'theory' skill) rather than fully operational, leaving minor gaps versus the most comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what ('foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki') and when ('Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base... Also use when discussing knowledge management strategy...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('wiki pattern,' 'knowledge base,' 'knowledge management strategy,' 'wiki structure,' 'Obsidian wiki') with explicit trigger phrases, but missing some synonyms and variations that would reach comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Carves out a clear niche and explicitly disambiguates from siblings — 'This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting)' — minimizing the chance of triggering the wrong skill.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (643 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 3 missing, 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: Ar9av/obsidian-wiki
Path: .skills/llm-wiki/SKILL.md
Commit: 52c9f2b

Reviewed: 1 day 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.