knowledge-sync

Collect ADO work items and IcM incidents into an incremental knowledge log.

298|70|Updated Nov 4, 2020
One-click install
npx skills add https://github.com/microsoft/powerplatform-build-tools --skill knowledge-sync-microsoft
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: knowledge-sync
Source: https://github.com/microsoft/powerplatform-build-tools/tree/main/.claude/skills/knowledge-sync
Command: npx skills add https://github.com/microsoft/powerplatform-build-tools --skill knowledge-sync-microsoft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reads ADO work items and ICM incidents for the PPBT area, extracts patterns and fixes, and appends them to a persistent knowledge log. Each run only fetches items newer than the last sync — knowledge accumulates over time rather than being overwritten.

Core Features & Use Cases

  • Incremental knowledge capture: reads ADO work items and ICM incidents, extracts patterns, and appends them to the knowledge log.
  • Automatic knowledge maintenance: the knowledge base is updated incrementally with new findings; nothing is overwritten.
  • Triggered and inline execution: invoked with /knowledge-sync and also run inline by /review, /workitem, and /pac-cli-update when the knowledge base ages.
  • Memory architecture: stores raw entries in memory/ado-knowledge.md and the live distilled summary in memory/MEMORY.md.
  • The sync keeps progress via the ## Last sync header and bootstraps from the past 90 days if no log exists.

Quick Start

Invoke /knowledge-sync to start the incremental synchronization.

Frequently Asked Questions about knowledge-sync

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

FAQPage Schema
How do I automatically sync ADO work items to a knowledge log?

The knowledge sync process extracts patterns and fixes from ADO work items and IcM incidents, appending them to a persistent log to preserve organizational learnings. It uses two memory files to store raw entries and a distilled summary.

Does the knowledge sync overwrite existing memory logs?

No, the sync updates incrementally without overwriting existing data. It fetches only items newer than the last sync, ensuring knowledge accumulates over time rather than replacing previous findings.

What happens when I run knowledge-sync for the first time?

When no log exists, it bootstraps the sync by fetching ADO work items and ICM incidents from the past 90 days to establish an initial baseline of organizational knowledge.

Can I trigger ADO work item syncing inline during a code review?

Yes, the sync is triggered inline by the /review, /workitem, and /pac-cli-update commands when the knowledge base ages, automatically applying new patterns alongside the primary /knowledge-sync command.

How does the tool track progress during an incremental ADO sync?

The tool tracks progress using the ## Last sync header in its memory files, ensuring each run only processes work items and incidents created after the previous synchronization.