What is obsidian-to-clew-import?

A converter for moving an Obsidian vault—a folder of linked Markdown notes—into a validated Clew learning graph package.

It is for inspecting a vault, previewing an import, choosing relevant settings, preserving relations, and producing either a validated package or a reshape recommendation.

It checks whether the notes can be imported cleanly, preserves explicit links, and stops when the source structure is ambiguous instead of silently inventing meaning.

How miuuyy/Clew configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to miuuyy/Clew. 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/miuuyy/Clew/main/.agents/skills/obsidian-to-clew-import/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/miuuyy/Clew

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/miuuyy/clew/obsidian-to-clew-import/github.svg)](https://agentmods.dev/skills/miuuyy/clew/obsidian-to-clew-import)

Your own site

<a href="https://agentmods.dev/skills/miuuyy/clew/obsidian-to-clew-import"><img src="https://agentmods.dev/badge/skills/miuuyy/clew/obsidian-to-clew-import/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/miuuyy/clew/obsidian-to-clew-import"><img src="https://agentmods.dev/badge/skills/miuuyy/clew/obsidian-to-clew-import.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,812 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00072	$0.02812
Opus 5.5	$0.00029	$0.01125
Sonnet 5.5	$0.00014	$0.00562
Haiku 4.5	$0.00007	$0.00281

Measured 2mo ago against content hash 6686c839c72b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

obsidian-to-clew-import 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.

.agents/skills/obsidian-to-clew-import/SKILL.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obsidian To Clew Import

Use this skill when a user wants to move an Obsidian vault, a folder of markdown notes, or a wiki-linked markdown graph into Clew.

This skill has one job:

inspect the source vault
map it into the Clew import contract
preserve explicit structure
ask only the minimum important questions
produce either a validated package preview or a clear reshape recommendation

Do not turn this into a generic Obsidian copilot or a fuzzy consultation flow.

Product truth

Clew is already opinionated:

it is a graph-first workspace for structured learning
the graph is the center of truth
AI must not silently invent semantics
imports must be reviewable and fail closed

So do not ask the user whether the product is “really” a roadmap graph, a knowledge graph, or a study graph.

The target shape is already known:

topics
relations
optional zones
optional descriptions
optional artifacts

The only question is whether the source vault can be mapped into that shape cleanly, and which import settings best preserve meaning.

Core stance

The converter must:

preserve trust
surface ambiguity
preserve explicit relation markers
avoid hidden semantic upgrades
preview the result before import

Never silently “improve” meaning.

Scope lock

Stay inside the currently-open vault. Its root is the complete universe of this skill invocation.

Rules:

Only read, analyze, and reason about files under the active vault root.
Do not look at ~, other Desktop/ folders, sibling vaults, parent directories, other repositories, OS-level paths, or anything outside the vault root — even when the vault is empty or sparse.
If the vault is empty, stay empty-aware and follow the "Missing source data" state in the structural audit. Do not scan other locations to compensate.
If the user references a path that resolves outside the vault root, stop and surface that explicitly. Do not silently resolve it.
"The vault" in this skill means the directory the agent is currently rooted in (for Claudian: the Obsidian vault that became cwd; for Claude Code: the session working directory).

Read the full file on GitHub · 390 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 · 390 lines · 72 tokens per session scan A 6686c839c72b

Subscribe to this mod's changes

obsidian-to-clew-import is a skill published in the GitHub repository miuuyy/Clew (212 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 2,812 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 2026-08-30.

Learning and teaching ai-agents chatgpt learning mcp obsidian study

obsidian-to-clew-import next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
obsidian-to-clew-importmiuuyy/Clew	Skill	212	8d ago	MIT	A	72	Claude Code, Codex
ankibytesagain/ai-skills	Skill	16	6mo ago	none	A	53	Claude Code, Codex
Learning Journaltheagentledger/agent-skills	Skill	6	7mo ago	none	A	84	Claude Code, Codex
baoyu-comicNousResearch/hermes-agent	Skill	261k	today	MIT	A	17	Claude Code, Codex
canvasNousResearch/hermes-agent	Skill	261k	today	MIT	A	12	Claude Code, Codex
antigravity-guideasgeirtj/system_prompts_leaks	Skill	71k	today	CC0-1.0	A	112	Claude Code, Codex
annotate-paper54yyyu/zotero-mcp	Skill	5.8k	today	MIT	A	82	Claude Code, Codex

Clew: Skill for Claude Code