ar9av/obsidian-wiki

memory-bridge

Browse or compare wiki knowledge by originating AI tool.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/ar9av/obsidian-wiki --skill memory-bridge

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Memory Bridge — Cross-Tool Knowledge Browser

You are helping the user browse and compare their Obsidian wiki knowledge filtered by which AI tool originally produced it. The wiki tracks source provenance in .manifest.json and page sources: frontmatter — this skill surfaces that metadata as a navigable view.

Before You Start

  1. Resolve config — follow the Config Resolution Protocol in llm-wiki/SKILL.md (inline @name override → walk up CWD for .env → global config → prompt setup). This gives OBSIDIAN_VAULT_PATH.
  2. Read $OBSIDIAN_VAULT_PATH/.manifest.json — this is the source-of-truth for what tool produced what.
  3. Read $OBSIDIAN_VAULT_PATH/index.md for page titles and one-line descriptions.

Commands

Parse the user's invocation to determine mode:

InvocationMode
/memory-bridge <tool>Browse — list all wiki pages sourced from <tool>
/memory-bridge <tool> "<topic>"Search — pages from <tool> that mention <topic>
/memory-bridge diffDiff — pages unique to each tool; overlap; blind spots
/memory-bridge diff <tool-a> <tool-b>Diff — compare two specific tools
/memory-bridge mapMap — full origin matrix: every page × every tool that touched it

Recognized tool names: claude, codex, hermes, openclaw, copilot, pi, manual (hand-written), ingest (wiki-ingest documents).

Step 1: Build the Source Map

Read .manifest.json. For each source entry, extract:

  • source_type — maps to tool name:
  • claude_conversation, claude_memory, claude_audit_log, claude_desktop_session → claude
  • codex_rollout, codex_index, codex_history → codex
  • hermes_memory, hermes_session → hermes
  • openclaw_memory, openclaw_daily_note, openclaw_session, openclaw_dreams → openclaw
  • copilot_session, copilot_checkpoint, copilot_transcript, copilot_memory_artifact → copilot
  • pi_session → pi
  • document → ingest
  • anything else → manual
  • pages_created and pages_updated — the wiki pages that came out of this source

Build a map:

tool_pages = {
  "claude": set(pages created/updated by claude sources),
  "codex":  set(pages created/updated by codex sources),
  ...
}

A page can appear in multiple tools' sets if multiple tools contributed to it.

Step 2: Execute the Mode

Browse Mode

Filter tool_pages[<tool>] and present as a grouped list:

## Knowledge from <tool> (<N> pages)

### By category
- concepts/ — N pages
- entities/ — N pages
- skills/   — N pages
...

### Pages
| Page | Category | Tags | Last updated |
|------|----------|------|--------------|
| [[page-name]] | concept | tag1, tag2 | 2026-04-10 |
...

Read frontmatter for the listed pages (grep for ^(title|category|tags|updated):) — do not read full page bodies unless the user asks.

Search Mode

Within the filtered page set, run:

rg -l "<topic>" <pages in tool set>

Then grep section headers (^##) around matches to give context without full reads. Present results as a ranked list with the matching excerpt.

Diff Mode

Compute:

  • only_in_a = tool_pages[a] − tool_pages[b]
  • only_in_b = tool_pages[b] − tool_pages[a]
  • shared = tool_pages[a] ∩ tool_pages[b]

If no specific tools are given, compare all tools pairwise (limit to pairs with >0 overlap or unique pages to keep output concise).

Present:

## Memory Bridge Diff — <tool-a> vs <tool-b>

### Only in <tool-a> (<N> pages)
These concepts exist in your wiki from <tool-a> sessions but <tool-b> has never touched them.
<list with one-line descriptions from index.md>

### Only in <tool-b> (<N> pages)
<list>

### Shared (<N> pages)
Both tools have contributed to these pages.
<list — only show if ≤15; otherwise just the count>

### Notable gaps
<highlight the most interesting asymmetries — e.g. "codex has 12 pages on build tooling that claude has never seen">

Map Mode

Build a matrix showing every page and which tools have touched it. Cap at 50 rows; sort by number of contributing tools descending (most cross-tool pages first — these are the richest nodes).

| Page | claude | codex | hermes | copilot | pi |
|------|--------|-------|--------|---------|----|
| [[react-patterns]] | ✓ | ✓ | — | ✓ | — |
| [[rust-ownership]] | — | ✓ | — | — | ✓ |

Step 3: Spawn impl-validator (if available)

After generating output, if the impl-validator skill is available in the current environment, spawn it as a subagent:

impl-validator check:
  goal: "Browse/diff wiki knowledge by source tool and surface cross-tool blind spots"
  artifacts: [the output you just generated]
  checks:
    - Did you correctly parse source_type from .manifest.json?
    - Are page counts plausible (not 0 unless vault is empty)?
    - Is the diff symmetric (a−b and b−a are disjoint)?
    - Did you avoid reading full page bodies when not needed?

Apply any issues it surfaces before presenting output to the user.

Step 4: Log

Append to $OBSIDIAN_VAULT_PATH/log.md:

- [TIMESTAMP] MEMORY-BRIDGE mode=<browse|search|diff|map> tool=<tool> pages_shown=N

Output Conventions

  • Always show page counts so the user can calibrate how much knowledge is in each tool's silo.
  • Use [[wikilinks]] for page references (or standard Markdown links if OBSIDIAN_LINK_FORMAT=markdown is set).
  • In diff mode, call out the most surprising asymmetry explicitly — that's the insight the user came for.
  • If .manifest.json is empty or missing, say so clearly and suggest running /wiki-history-ingest first.
同じリポジトリから

関連する Skills

すべての Skills
ar9av
コミュニティ

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

1時間の導入数
1
GitHub Stars
3793
更新日
11月21日
ar9av
コミュニティ

copilot-history-ingest

Ingest GitHub Copilot CLI/session history into Obsidian as distilled knowledge. Use for importing or mining Copilot history; not for general Copilot help, simple session search, or backup.

1時間の導入数
1
GitHub Stars
3793
更新日
11月20日
ar9av
コミュニティ

hermes-history-ingest

Ingest Hermes agent history into Obsidian as distilled knowledge. Use for importing or mining ~/.hermes sessions, memories, or logs; use wiki-agent for targeted topic-only cross-agent recall.

1時間の導入数
1
GitHub Stars
3793
更新日
11月20日
ar9av
コミュニティ

vault-skill-factory

Create a reviewable Agent Skill package from mature curated wiki pages, or from one recorded walkthrough of a job (a narrated screen recording, a call, a voice note: "turn this recording into a skill", "I did it once out loud, make it a skill"). Use when turning verified vault knowledge or a recorded workflow into a reusable skill. Reads the vault and writes only to a review directory; it does not install skills.

1時間の導入数
1
GitHub Stars
3793
更新日
11月20日