Name: llm-wiki
Rating: 60 (1 reviews)
Author: alirezarezvani

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

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 ./.gemini/skills/llm-wiki/SKILL.md

The canonical home for this skill is llm-wiki in alirezarezvani/claude-skills

Quality

Content

42%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 body is a well-organized overview that delegates detail to referenced files, but it is verbose and the referenced bundle files are missing, weakening both actionability and progressive disclosure. The ingest workflow also lacks validation checkpoints appropriate to a batch/mutating operation.

Suggestions

Trim the "Why this works (vs plain RAG)" comparison table and inspirational framing — Claude already knows what RAG is; keep only what guides action.

Add an explicit validation step to the ingest workflow (e.g., re-run /wiki-lint or verify inbound links resolve before appending to log.md) so the batch update has a feedback loop.

Either ship the referenced bundle files (references/*.md, scripts/*.py, assets/*.template) or inline the minimum executable detail (page frontmatter schema, ingest step list) so the body is actionable on its own.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose — the "Why this works (vs plain RAG)" table, the "When to use" enumeration, the Karpathy framing and "Obsidian is the IDE" quote restate concepts Claude already knows or that belong in bundle files.	2 / 5
Actionability	Concrete commands exist (init_vault.py invocation, /wiki-ingest, /wiki-query) but the executable detail — page frontmatter, exact ingest procedure, lint heuristics — is deferred to reference files that are not present, leaving the body with high-level hints like "updates 10-15 relevant pages".	3 / 5
Workflow Clarity	Ingest/Query/Lint are sequenced and the quick start gives a 5-step flow, but ingest is a batch/mutating operation (updates many pages, appends to a persistent log) with no validate→fix→retry checkpoint, capping this dimension at 3 per the destructive/batch rule.	3 / 5
Progressive Disclosure	Sections and a one-level-deep reference list are clearly signaled, but the actual bundle directories (references/, scripts/, assets/) are absent, so every referenced path fails to resolve — structure is present but not verifiably navigable.	3 / 5
	Total	11 / 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 excellent: concrete capabilities, abundant natural trigger phrases, and explicit what/when guidance in third person. It is one of the strongest activation descriptions in the reference set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "ingests sources", "updates entity/concept pages", "maintains cross-references", and "keeps a synthesis current" — giving comprehensive coverage rather than a few with gaps.	5 / 5
Completeness	Explicitly answers both what (ingest, update pages, maintain cross-refs, keep synthesis current) and when ("Use when building or maintaining...", "Triggers include...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Packs in natural, varied triggers users would actually say — "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex" — including synonyms and phrasings.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — an Obsidian-backed, LLM-maintained compounding wiki framed as a RAG alternative/Memex — with distinctive triggers and minimal overlap with generic note skills.	5 / 5
	Total	20 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 15 missing	Warning

	Total	14 / 16 Passed

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

Reviewed: ~10 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.