What makes Obsidian Vault Curator notable?

1.1K downloads. Trust evidence available

How should Obsidian Vault Curator be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Obsidian Vault Curator

Cautious curation, classification, review, and migration planning for Obsidian or Markdown vaults. Use when the user wants to organize a messy vault, classif...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.1.0release · observed May 19, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s174xf840fv9gsykcep648d75d83qqy6:obsidian-vault-curator

Install using `clawhub skill install s174xf840fv9gsykcep648d75d83qqy6:obsidian-vault-curator` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/thenerdforge/obsidian-vault-curator before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-thenerdforge-obsidian-vault-curator/snapshot"

Documentation

CLAWHUB

130,490 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: obsidian-vault-curator
description: Cautious curation, classification, review, and migration planning for Obsidian or Markdown vaults. Use when the user wants to organize a messy vault, classify notes, define canonical reference pages, separate current vs historical vs future-state material, design review dashboards or Bases views, or plan safe cleanup and migration without losing historical context. This skill requires installed Python 3 on PATH.
metadata:
openclaw:
emoji: "🗂️"
requires:
bins: ["python3"]
install:
- id: brew-python
kind: brew
formula: python
bins: ["python3"]
label: "Install Python 3 (brew)"
os: ["darwin"]
---

# Obsidian Vault Curator

Bring structure to a messy Obsidian vault without flattening its history. Start with inventory. Then run separate read-only analysis passes. Then propose one small, reviewable write slice.

For multi-note work, use read-only subagents by default. Keep the main agent as the only writer. Use one bounded slice per subagent and separate passes for inventory, comparison, classification, verification, and sensitive-content review.

## Runtime requirement

This skill declares `python3` on `PATH` as a host requirement.

- The requirement is surfaced in metadata as `requires.bins: ["python3"]`.
- On macOS, the metadata includes a Homebrew install hint.
- On Linux, install Python 3 with your distro package manager, for example `sudo apt install python3`, then verify `python3 --version`.
- On Windows, install Python from the official Python Install Manager or with `winget install Python.Python.3.14`, then open a new terminal and verify that `python3 --version` works. If only `python` works, add a `python3` alias or shim on `PATH` before using this skill.
- The bundled helper scripts in `scripts/` use only the Python standard library.
- No extra Python packages are required.
- No exact minor version is currently pinned. The helpers were validated with Python 3.11+ and tested locally on macOS against Python `3.14.4`.
- Windows support is documented, but the full workflow has not yet been live-validated on Windows.

## Core rules

- Default to read-only.
- Use subagents by default for multi-note or heterogeneous work.
- Keep inventory first, then read-only review, then writes.
- Never delete notes unless the user explicitly asks.
- Never rewrite more than one write slice at a time. A write slice must stay within 3-10 related notes. Multiple-slice content rewrites in one pass count as mass-rewrite and require explicit user approval.
- Never run parallel write agents.
- Treat findings of sensitive content (see `references/subagents.md` glossary) as hypotheses until the main agent verifies the exact note content.
- Never rely on a global forced subagent model. Reuse the main-agent model when it fits; change model only when a specific role clearly benefits.
- Prefer `superseded_by` over overwrite.
- Preserve historical context.
- Treat `d

_meta.json

{
  "ownerId": "kn7dzka1n2vjb8wgzt8v4xrych82ph5f",
  "slug": "obsidian-vault-curator",
  "version": "1.1.0",
  "publishedAt": 1779221366671
}

references/bases-views.md

# Bases and review views

Use Bases or equivalent review lists as the control plane for curation.

Views that group by `topic` depend on consistent topic slugs. Use the `topic` rule in `references/status-schema.md` before creating or changing topic-based views.

## Recommended views

### Vault Inbox
Show notes missing `status` or `doc_kind`.

### Needs Review
Show notes where:

- `status = needs-review`, or
- `review_state = conflict`

### Canonical Pages
Show notes where:

- `canonical = true`

group by `topic`.

### Historical but linked
Show notes where:

- `status = historical`
- and the note still has meaningful inbound links

### Concept / future state
Show notes where:

- `status = concept`

### Reactivatable
Show notes where:

- `status = reactivatable`

### Supersession gaps
Show notes where:

- `status = historical`
- and `superseded_by` is empty

### Stale current docs
Show notes where:

- `status = current`
- and `last_verified` is older than 90 days or missing

### Research not integrated
Show notes where:

- `doc_kind = research`
- and no canonical page links to them

## Practical guidance

- Keep the first dashboard small and obvious.
- Start with visibility, not automation.
- Prefer a handful of high-signal views over a huge taxonomy.
- If Bases is not available, propose manual indexes or search-driven lists as equivalent queues.

references/classification-rubric.md

# Classification rubric

Classify one note at a time. Prefer explicit uncertainty over confident mislabeling.

Subagents that use this rubric return candidates only; the main agent verifies and applies.
See `references/status-schema.md` for the `confidence` rule when emitting per-note recommendations.

## Step 1: Determine `doc_kind`

Ask what the note is trying to be:

- `reference` — source of truth, stable facts, config, paths, commands
- `howto` — procedure to achieve a task
- `explanation` — why something works, tradeoffs, reasoning
- `tutorial` — guided learning sequence
- `research` — collected findings, comparisons, external material
- `adr` — a decision with context and consequences
- `log` — diary, changelog, working notes, progress trail
- `index` — hub page or navigation page
- `concept` — target design or future plan

## Step 2: Determine `status`

### `current`
Use when the note is still valid and should be trusted now.
Signals:
- verified paths, commands, hostnames, versions, or architecture
- referenced by 2 or more inbound wikilinks from notes that are already `status: current`
- clearly reflects the live environment

### `historical`
Use when the note is not current but still valuable.
Signals:
- documents a previous setup, migration path, or decision history
- useful for recovery, comparison, or context
- replaced by a newer page

### `concept`
Use when the note describes a desired future state.
Signals:
- signal words in the title or opening section, in German or English, such as Zielbild, Soll, Plan, Proposal, Vision, target state, draft, or future state
- contains intended rather than verified state

### `needs-review`
Use when status is unclear.
Signals:
- mixed old and new facts
- no verification date, or `last_verified` older than 90 days for a note claiming `status: current`
- conflicts with better evidence
- unclear whether the note is still active

### `reactivatable`
Use when the note is dormant but likely reusable.
Signals:
- currently inactive workflow or system
- likely to return later
- should stay discoverable without being treated as live

## Canonical page test

A note is a good canonical candidate when most of these are true:

- it has the clearest scope for a topic
- it is easier to update than the alternatives
- it already attracts links or should attract them
- it can safely point outward to detail pages
- it is not mostly historical baggage

If no note qualifies, propose creating a small new index or reference page instead of forcing a bad canonical page.

## Supersession rules

- Do not erase old context when a new page replaces it.
- Mark older pages with `superseded_by`.
- Mark the new leading page with `supersedes`.
- Prefer short transition notes over giant merge rewrites.

## Conflict handling

When two notes disagree:

1. trust live evidence over prose
2. trust the note with recent verification over the undated one
3. downgrade uncertain notes to `needs-review`
4. do not silently merge contradiction

references/output-format.md

# Output and merge format

Use one compact format so subagent findings are mergeable.
This file is the single source of truth for output shapes.

## Context router

| Context | Use this shape |
|---|---|
| Subagent reply | `Required five-section shape` |
| Single-pass main-agent reply with no subagents | `Required five-section shape` |
| Main-agent merged reply from two or more subagent slices | `Final main-agent summary shape` |

## Required five-section shape

Return these sections in this order:

1. `Current state`
2. `Classification recommendations`
3. `Risks and contradictions`
4. `Next write slice`
5. `Verification`

Keep each section short and concrete.
If a section has nothing material, write `none`.

## Preferred note-level fields

When naming important notes, prefer this shape:

- `Path or note name`
- `doc_kind`
- `status`
- `canonical` yes/no when relevant
- short reason
- optional `confidence: low|medium|high`

If the bounded slice does not support a recommendation, write `insufficient evidence` and prefer `needs-review` over guessing.

## Sensitive findings

If a subagent suspects sensitive content (see `references/subagents.md` glossary):

- treat it as a hypothesis, not a confirmed finding
- reference only the note path, field or section, pattern type, and redacted shape
- do not quote the sensitive value
- do not recommend edits as if the finding were confirmed
- place the finding under `Risks and contradictions`
- require main-agent verification against exact note text before escalation or editing

## Merge rules for the main agent

When merging child-slice results:

1. prefer compact summaries over repeating every detail, but keep disagreements visible
2. surface disagreements explicitly
3. downgrade contested notes to `needs-review`
4. separate confirmed facts from hypotheses
5. separate structural actions from content rewrite actions
6. keep unsupported claims out of the merged summary; use `insufficient evidence` where needed

## Human-review gates

Escalate to explicit human review before:

- deleting notes
- moves or renames affecting more than 10 notes or more than 1 vault top-level directory
- editing notes after only inferred classification
- acting on sensitive-content hypotheses
- collapsing multiple competing pages into one canonical page without clear evidence
- changing a canonical page with 3 or more affected backlinks

## Final main-agent summary shape

When reporting merged results back after a multi-slice pass, use the required five-section shape.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.