What is vault-skill-factory?

A packaging tool that turns a well-developed group of wiki notes into a portable set of instructions for an AI agent.

Use it to create a reusable expert skill from connected notes about a technical topic, project, or working method.

It lets an agent reuse established knowledge without repeatedly searching the original notes. It also avoids packaging topics that are too small, unfinished, or frequently changing.

How ystreibel/logseq-wiki configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to ystreibel/logseq-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ystreibel/logseq-wiki/main/.skills/vault-skill-factory/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ystreibel/logseq-wiki

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ystreibel/logseq-wiki/vault-skill-factory/github.svg)](https://agentmods.dev/skills/ystreibel/logseq-wiki/vault-skill-factory)

Your own site

<a href="https://agentmods.dev/skills/ystreibel/logseq-wiki/vault-skill-factory"><img src="https://agentmods.dev/badge/skills/ystreibel/logseq-wiki/vault-skill-factory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ystreibel/logseq-wiki/vault-skill-factory"><img src="https://agentmods.dev/badge/skills/ystreibel/logseq-wiki/vault-skill-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 905 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.00905
Opus 5.5	$0.00034	$0.00362
Sonnet 5.5	$0.00017	$0.00181
Haiku 4.5	$0.00008	$0.00090

Measured 2mo ago against content hash 2b9f3d5be8b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vault-skill-factory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.skills/vault-skill-factory/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vault Skill Factory — Notes → Portable Skill

REQUIRED: Invoke llm-wiki first for Logseq syntax; this skill also builds on skill-creator.

Compile a dense cluster of wiki pages into a distributable skill: the accumulated knowledge becomes an "expert" other agents can load, instead of re-querying the vault each time (the "compile once, keep current" principle applied to expertise).

Before You Start

Read ~/.logseq-wiki/config (preferred) or .env to get LOGSEQ_VAULT_PATH
Read wiki/_master-index.md to see themes and page density
Identify the target cluster: a theme, or a hub page + its neighbors (use wiki-status hubs or ask the user)

Step 1: Assess Maturity

A cluster is skill-ready only if it is substantial and stable:

≥ 4–5 interconnected pages on the topic (check density with the graph, excluding _index)
Pages carry real distilled knowledge (facts, decisions, patterns), not mostly TODO/stubs
Content is stable (not actively churning). If the cluster is thin or volatile, say so and stop — suggest more ingestion first rather than packaging premature knowledge.

Step 2: Extract the Expertise

From the cluster, distill into skill material:

Scope — what the expert knows and when it applies
Core facts & patterns — the reusable knowledge (not vault-specific navigation)
Decision rules / heuristics the pages encode
Pointers back to the source pages [[wiki/theme/page]] for provenance
Preserve ^[inferred]/^[ambiguous] — an expert states its confidence

Strip anything vault-private that should not travel (personal notes, internal identifiers) unless the user wants an internal-only skill.

Step 3: Generate the Skill

Invoke the skill-creator skill to produce the new skill (it owns the authoring workflow, evals and validation — do not hand-roll the SKILL.md structure). Pass it:

name: a clear, hyphenated expert name (e.g. gcp-architecture-expert)
description: third-person "Use when…" triggering conditions only (no workflow summary)
Body: the distilled expertise, with a "Sources" section linking the originating wiki pages
Keep under ~500 lines; move heavy reference to supporting files

Read the full file on GitHub · 72 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 72 lines · 84 tokens per session scan A 2b9f3d5be8b9

Subscribe to this mod's changes

vault-skill-factory is a skill published in the GitHub repository ystreibel/logseq-wiki (5 stars, last pushed 11d ago), licensed MIT. It adds 84 tokens to every session and 905 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

vault-skill-factory next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vault-skill-factoryystreibel/logseq-wiki	Skill	5	11d ago	MIT	A	84	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

logseq-wiki: Skill for Claude Code