agentsclimarketplace

Llm wiki migration planner

Skill po4yka/llm-wiki-skills/skills/llm-wiki-migration-planner

Create a no-write migration plan for turning existing notes, docs, Obsidian vaults, Notion exports, research archives, or repository documentation into an LLM-Wiki. Use when the user wants a dry-run plan before moving or editing files; route applying the approved plan to llm-wiki-refactor.From its SKILL.md

Install
npx -y skills add po4yka/llm-wiki-skills --skill llm-wiki-migration-planner

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.6 KB, 684 tokens by cl100k_base, as published. Nobody here has run it

LLM-Wiki Migration Planner

Goal

Produce a safe, reviewable migration plan without changing the user's files.

When to use

  • The user wants a plan before migrating notes, docs, or an Obsidian vault into an LLM-Wiki, without touching any files yet.
  • The user is deciding between a personal vault, repo wiki, team wiki, research corpus, or product prototype target and needs a mapping proposal first.
  • The source is mixed content (Notion export, chat export, research PDFs, company docs) and needs profile-specific classification before any move happens.
  • The user asks for a dry-run, review, or approval step ahead of running llm-wiki-refactor.

Inputs

  • Current document root.
  • Desired target: personal vault, repo wiki, team wiki, research corpus, or product prototype.
  • Existing constraints: Obsidian, Notion export, docs generator, git, privacy, attachments.

Procedure

1. Confirm dry-run mode

State that this skill produces a plan only. Do not move, rename, delete, normalize frontmatter, or rewrite links.

2. Identify migration profile

Classify the source:

ProfileNotes
Obsidian vaultPreserve wikilinks, aliases and attachments.
Repository docsPreserve README/ADR/docs generator conventions.
Notion exportNormalize nested pages and attachment paths.
Readwise/Omnivore exportTreat exports as raw sources first.
Chat exportsSeparate raw conversation from reusable query pages.
Research PDFsPreserve PDFs in raw/assets or raw/sources.
Company docsRequire PR-based write model and permissions.

3. Inventory and classify

For each candidate file, infer:

  • current path;
  • likely page type;
  • whether it is raw, wiki, synthesis, query, asset, or mixed;
  • confidence;
  • migration risk;
  • proposed target path.

4. Build mapping table

Use this table:

| Current path | Proposed path | Type | Confidence | Risk | Notes |
|---|---|---|---:|---|---|

Use confidence values conservatively. Low-confidence rows should require human review. Re-verify each row's proposed path and confidence against the actual current file contents, not just filenames, before finalizing the table.

5. Design phases

Split the migration into batches:

  1. create scaffold;
  2. preserve raw sources and assets;
  3. move source summaries;
  4. create or update index/log;
  5. normalize frontmatter;
  6. repair links;
  7. run lint and trust audit.

6. Produce apply instructions

Give exact next steps for llm-wiki-refactor, but do not execute them.

Output

## Migration thesis

## Source profile

## Target structure

## Migration table

## High-risk files

## Phased plan

## Required approvals

## Next skill

Safety gates

  • No file writes.
  • No deletion recommendations without a separate archive/backup option.
  • Do not convert Obsidian wikilinks to Markdown links unless explicitly requested.
  • Do not collapse raw sources into summaries.
  • Do not propose cloud ingestion for sensitive material without explicit approval.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,736. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.