One-click install
npx skills add https://github.com/EliasOulkadi/shokunin --skill shokunin-update
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shokunin-update
Source: https://github.com/EliasOulkadi/shokunin/tree/main/.pack/skills/shokunin-update
Command: npx skills add https://github.com/EliasOulkadi/shokunin --skill shokunin-update

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

It prevents Shokunin’s locally installed ecosystem from silently drifting away from its declarative manifest, which can break tools and agents until things are manually repaired.

Core Features & Use Cases

  • Drift detection via manifest: Compares ~/.shokunin/shokunin.json (single source of truth) against actual filesystem state using shokunin-update.ps1 status for accurate MISSING/OK/protected reporting.
  • Safe change planning and guided apply: Produces a plan summary before applying changes, then applies only after the user confirms the update.
  • Backups, rollback, and health verification: Backs up prior state, supports rollback by timestamp, saves an update event to ChromaDB, and runs memory-healthcheck.ps1 to verify integrity.

Quick Start

Ask the AI to run an ecosystem update by saying: “Check drift and update the Shokunin ecosystem safely, using plan and confirmation.”

Frequently Asked Questions about shokunin-update

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect infrastructure as code drift between a declarative manifest and the filesystem?

You can detect configuration drift by comparing the source of truth in `~/.shokunin/shokunin.json` against the actual filesystem state, reporting MISSING, OK, and protected-path violations to identify inconsistencies.

What is the safest way to apply an ecosystem update without breaking agents or tools?

The safest ecosystem update method uses plan-before-apply logic, generating a summary of changes and prompting for user confirmation before modifying files to prevent silent breakage of tools and agents.

How do I rollback a failed configuration management sync to a previous state?

You can rollback a failed sync using timestamped backups created prior to applying changes, restoring the previous filesystem state to revert failed updates and maintain ecosystem consistency.

Can I verify post-update health and save events to ChromaDB using PowerShell automation?

Yes, PowerShell automation verifies post-update health by running `memory-healthcheck.ps1` to confirm system integrity, then saves the update event to ChromaDB to maintain a persistent record of the reconciliation.

Do I need a specific declarative manifest file to prevent silent ecosystem drift?

Yes, you need the `~/.shokunin/shokunin.json` manifest file acting as the single source of truth to prevent silent ecosystem drift, which compares against the filesystem to keep components and hashes consistent.

Why does a protected-path violation stop a manifest reconciliation update?

A protected-path violation stops manifest reconciliation to prevent unauthorized modifications to critical files, ensuring the update process safely reports violations before applying any changes to the filesystem.