Wiki Fold logo

Wiki Fold

CommunityPopular
AgriciDaniel
wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit the fold.

Overview

PublisherAgriciDaniel
Repositoryclaude-obsidian
Skill namewiki-fold
Stars
15K
Forks
1.5K
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by AgriciDaniel on GitHub. Read the source before you install it.

Installation

Install the Wiki Fold AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AgriciDaniel/claude-obsidian.git /tmp/claude-obsidian
mkdir -p .claude/skills
cp -r /tmp/claude-obsidian/skills/wiki-fold .claude/skills/wiki-fold
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wiki Fold in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wiki Fold on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wiki Fold is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Extractive log fold

Create an additive rollup of raw wiki/log.md entries. Never modify, move, or delete child entries or their pages. Do not perform fold-of-folds or trigger a fold automatically.

Resolve the portable core from this skill's installation. Resolve the user vault by explicit --vault, CLAUDE_OBSIDIAN_VAULT, workspace config, then current-directory discovery. Never treat the plugin/product root as a vault.

bash
PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
CORE="$PRODUCT_ROOT/scripts/claude-obsidian.py"
test -f "$CORE"

Every ../wiki/references/ link in this file resolves the same way, relative to this skill's own directory under $PRODUCT_ROOT, never relative to the selected vault's wiki/ directory.

This skill needs no network egress. Do not call external services.

Select a bounded range

Use batch exponent k with size 2^k; default to k=4. An explicit entry range may override it. If fewer entries exist than requested, report the shortfall and stop rather than folding a partial batch.

Read the selected log entries completely. Read referenced child pages only when the log lacks enough context: target 0-10 reads, hard ceiling 15. Missing pages remain explicit page_missing records.

Derive the structural ID only from inputs:

text
fold-k{K}-from-{EARLIEST-DATE}-to-{LATEST-DATE}-n{COUNT}

If wiki/folds/{FOLD_ID}.md already exists, return a no-op. Replacing it requires an explicit force request and a separately reviewed replace proposal.

Draft extractively

Follow fold-template.md. Every child log entry must have one deterministic child_key in frontmatter and exactly one matching row in the Child Entries table. Do not deduplicate children by page, although the final Child Pages link list may be deduplicated.

Every outcome must name its source entry. Every number must be verifiable in the selected entry. A cross-entry theme must name at least two contributing entries. Prefer ambiguous in source or source missing to invention. When a child page and log entry disagree, preserve both and identify the mismatch; the log entry is the fold's primary source.

Run these checks before proposing any write:

  • deterministic ID and exact entry count;
  • frontmatter/table bijection;
  • numeric traceability;
  • source citation for every outcome and theme;
  • no change to a child, source, source ledger, or claim ledger.

A fold adds no new factual evidence, so it does not upgrade claim assessments or create source records. Report discovered contradictions for later review instead of editing canonical claims.

Preview by default

Return the complete fold draft, ID, child range, read budget, and proposed changed paths without modifying the vault. Parallel agents may check child entries and return extracts, but only the orchestrator assembles the fold; workers never write.

When the user explicitly says to apply or commit the fold, build one claude-obsidian.transaction.v1 bundle with operation_type: fold. Read the transaction contract. Couple:

  • wiki/folds/{FOLD_ID}.md in create mode by default;
  • the fold catalog entry in wiki/index.md;
  • one new top-of-file fold entry in wiki/log.md.

Do not update wiki/hot.md. Record SHA-256 preconditions for all three targets. Do not use host Write/Edit, Obsidian transport writes, deprecated locks, automatic commits, or one apply per file.

Inspect before the single apply:

bash
python3 "$CORE" transaction inspect /path/to/fold-bundle.json --vault /path/to/vault
# Set APPROVAL_SHA256 to the inspect result's approval_sha256 after review.
python3 "$CORE" transaction apply /path/to/fold-bundle.json --vault /path/to/vault \
  --approved-plan-sha256 "$APPROVAL_SHA256"

Report the operation ID and exact changed paths. The identical bundle and ID are idempotent. On exit 75, re-read and rebuild; after interruption, use transaction recover.

Git history is a separate optional action:

bash
python3 "$CORE" checkpoint OPERATION_ID --vault /path/to/vault

Observe all selected entries, verify traceability and counts, then grow the rollup only from what its children actually say.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wiki Fold AI skill do?

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit the fold.

Why use Wiki Fold on TypingMind?

Because you install it once and use it with any model. Wiki Fold is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wiki Fold in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AgriciDaniel/claude-obsidian/tree/main/skills/wiki-fold. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wiki Fold?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wiki Fold?

As many as you like. As long as a model supports skills, you can use Wiki Fold with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wiki Fold AI skill free?

Yes. It is published on GitHub by AgriciDaniel under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇