Skip to main content
skill CX Codex

wiki-history-ingest — Claude Code skill: route agent history

A thin router that picks the right history-ingest skill from an agent name or a session path, then hands the job over.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Ar9av/obsidian-wiki --skill wiki-history-ingest -a claude-code
Open on GitHub

What wiki-history-ingest does

The skill does not parse history itself. It reads the request and decides which specialized skill to call: claude-history-ingest, copilot-history-ingest, codex-history-ingest, hermes-history-ingest, openclaw-history-ingest or pi-history-ingest. The destination skill's workflow then runs as written, and the router keeps no copy of that logic.

You can name the route directly with a subcommand: claude, copilot, codex, hermes, openclaw or pi. Give a path instead and the router inspects the source. ~/.claude and Claude session JSONL artifacts go to claude-history-ingest; ~/.copilot, session-store.db and VS Code copilot-chat transcripts go to copilot-history-ingest; ~/.codex goes to codex-history-ingest; ~/.hermes goes to hermes-history-ingest; ~/.openclaw goes to openclaw-history-ingest; ~/.pi/agent/sessions goes to pi-history-ingest. If the source is ambiguous, it asks one short clarifying question instead of guessing.

This router covers agent history only. Documents and other content sources belong to wiki-ingest in the same set, and the router is not a replacement for it. Manifest, index and log updates stay with the destination skill, so what you get depends on whether that skill is installed.

What it helps with

  • pick the right history-ingest skill from an agent name
  • identify the agent from a session directory path
  • get one clarifying question instead of a wrong guess
  • keep agent-history imports separate from document imports
  • hand off to a specialized skill without duplicated logic

Example prompts for the agent

  • /wiki-history-ingest claude
  • /wiki-history-ingest copilot
  • $wiki-history-ingest Claude

How to install wiki-history-ingest

1Skills CLI (Vercel)

npx skills add Ar9av/obsidian-wiki --skill wiki-history-ingest -a claude-code

2Manually: put the files in place

~/.claude/skills/wiki-history-ingest/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/wiki-history-ingest/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about wiki-history-ingest

How do I install wiki-history-ingest in Claude?

Run npx skills add Ar9av/obsidian-wiki --skill wiki-history-ingest -a claude-code. The skill lands at ~/.claude/skills/wiki-history-ingest/SKILL.md.

What does wiki-history-ingest do?

It routes generic AI-agent history ingestion requests to the matching specialized skill. It does not parse history itself; it runs the destination skill's workflow.

How is it different from wiki-ingest?

wiki-ingest handles documents and content sources, while wiki-history-ingest handles agent history sources only. The router does not replace wiki-ingest.

Source text

SKILL.md · MIT
---
name: wiki-history-ingest
description: >
  Route generic agent-history ingestion requests to the appropriate specialized history-ingest skill. Use when the user asks to ingest AI-agent history without directly selecting the underlying agent-specific skill.
---

# Unified History Ingest Router

This is a thin router for **history sources only**. It does not replace `wiki-ingest` for documents.

## Subcommands

If the user invokes `/wiki-history-ingest <target>` (or equivalent text command), dispatch directly:

| Subcommand | Route To |
|---|---|
| `claude` | `claude-history-ingest` |
| `copilot` | `copilot-history-ingest` |
| `codex` | `codex-history-ingest` |
| `hermes` | `hermes-history-ingest` |
| `openclaw` | `openclaw-history-ingest` |
| `pi` | `pi-history-ingest` |
| `auto` | infer from context using rules below |

## Routing Rules

1. If the user explicitly says `claude`, `copilot`, `codex`, `hermes`, `openclaw`, or `pi`, route directly.
2. If the user provides a path/source:
   - `~/.claude` or Claude memory/session JSONL artifacts -> `claude-history-ingest`
   - `~/.copilot`, `session-store.db`, VS Code copilot-chat transcripts -> `copilot-history-ingest`
   - `~/.codex` or rollout/session index artifacts -> `codex-history-ingest`
   - `~/.hermes` or Hermes memories/session artifacts -> `hermes-history-ingest`
   - `~/.openclaw` or OpenClaw MEMORY.md/session JSONL artifacts -> `openclaw-history-ingest`
   - `~/.pi/agent/sessions` or Pi session JSONL artifacts -> `pi-history-ingest`
3. If ambiguous, ask one short clarification:
   - "Should I ingest `claude`, `copilot`, `codex`, `hermes`, `openclaw`, or `pi` history?"

## Execution Contract

- After routing, execute the destination skill's workflow exactly.
- Do not duplicate destination logic in this file.
- Leave manifest/index/log update semantics to the destination skill.

## UX Convention

- Use `wiki-ingest` for **documents/content sources**
- Use `wiki-history-ingest` for **agent history sources**

Examples:

- `/wiki-history-ingest claude`
- `/wiki-history-ingest copilot`
- `/wiki-history-ingest codex`
- `/wiki-history-ingest hermes`
- `/wiki-history-ingest openclaw`
- `/wiki-history-ingest pi`
- `$wiki-history-ingest claude` (agents that use `$skill` invocation)
- `$wiki-history-ingest copilot`

© Ar9av · MIT · Ar9av/obsidian-wiki

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set38

wiki-update Distills architecture decisions and project context from your current repository into an Obsidian vault. Useful when you need durable notes without manual copy-pasting. CX Codex +1 3,400installs wiki-status Reports what an Obsidian wiki has ingested, what changed since the last run, and which pages went stale. Run it before deciding whether to append or rebuild the vault. CX Codex +1 3,400installs cross-linker Finds wiki pages that ought to reference each other but don't, then inserts the missing [[wikilinks]]. Useful right after a bulk import of notes. CX Codex +1 3,300installs tag-taxonomy This skill audits and normalizes tags across an Obsidian vault using a controlled vocabulary. It spots aliases, cleans up excess tags, and suggests canonical labels for new notes. CX Codex +1 3,200installs wiki-export Turns the wikilink graph of an Obsidian vault into JSON, GraphML, Cypher, SQL, HTML or OKF. Handy when the notes have to land in Gephi, Neo4j or a script of your own. CX Codex +1 3,200installs wiki-rebuild Creates full snapshots of an Obsidian wiki, restores earlier archives, and wipes the vault to let you reprocess all raw sources from scratch. CX Codex +1 3,200installs claude-history-ingest Distills past Claude Code sessions into structured Obsidian wiki notes. Useful for preserving project context and mining technical takeaways from chat logs. CX Codex +1 3,000installs graph-colorize Color-codes Obsidian graph nodes by tag, folder, or visibility in .obsidian/graph.json. Useful when you need a clear visual structure across your vault. CX Codex +1 2,800installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor