Skip to content
SkillModel-led553 tokens in use

wiki-history-ingest

A router for agent-history ingestion: it picks the Claude, Copilot, Codex, Hermes, OpenClaw or Pi ingest skill from a subcommand or a history path.

3,792 stars on the repository MIT LicenseAr9av/obsidian-wiki · skills/wiki-history-ingest
pip install obsidian-wiki
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing wiki-history-ingest costs

39tokens idle
553tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure16/25
  • Examples6/15
  • Output5/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

wiki-history-ingest is the single entry point for turning past AI agent sessions into wiki pages. It holds no ingestion logic of its own. It decides which specialized history-ingest skill should handle the request and hands over to it.

Routing works from an explicit subcommand such as claude or codex, or from the source path the user gives, such as a Copilot session store or a Hermes folder. When neither is clear it asks one short question.

What You Get

  • One command, wiki-history-ingest, for six kinds of agent history
  • Routing by subcommand, by path or by a one-question clarification
  • The destination skill’s workflow run unchanged, including its manifest, index and log updates
  • A clear split between document ingestion and history ingestion

Common Use Cases

  • Mining past Claude Code sessions into a wiki without remembering the skill name
  • Pointing at a Codex or Copilot history folder and letting the router choose
  • Giving a team one documented command for all agent history imports

What Makes It Unique

It keeps history ingestion behind one name while the work stays in six specialized skills, so the router never duplicates their logic. It leaves manifest, index and log handling to the destination, and it draws a line with wiki-ingest, which stays the choice for documents and other content sources.

Under The Hood

The skill is instructions for the agent and runs nothing itself. It matches the request or source path against a short routing table and then follows the destination skill. Any shell commands, file reads or file writes come from that destination skill, not from this one. It does not fetch web pages or call remote APIs.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers