skills.rest
pjherron
pjherronCOMMUNITY
Explore all skills by this author →
GitHub

knowledge-ops

Organizes, syncs, and retrieves knowledge across memory files, MCP memory, Git repos, and external data stores.

Updated Jul 16, 2026
Search Tags:#git#knowledge management#mcp#memory#ingestion#sync#deduplication
One-click install
npx skills add https://github.com/pjherron/hypoc --skill knowledge-ops-pjherron
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: knowledge-ops
Source: https://github.com/pjherron/hypoc/tree/main/hypoc/skills/knowledge-ops
Command: npx skills add https://github.com/pjherron/hypoc --skill knowledge-ops-pjherron

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Knowledge about decisions, preferences, and project state gets scattered across chat sessions, local notes, GitHub, Linear, and databases, making it hard to find, deduplicate, and keep in sync. This Skill provides a structured workflow for classifying, storing, syncing, and retrieving knowledge across multiple storage layers. ## Core Features & Use Cases - Multi-layer storage routing: Classifies incoming knowledge and routes it to the right layer, from quick-access memory files to MCP memory graphs, GitHub/Linear, knowledge base repos, and external databases like Supabase or PostgreSQL. - Deduplication and indexing: Searches existing memory files and MCP memory before writing, updates entries instead of duplicating them, and maintains indexes and summaries. - Sync operations: Syncs conversation sessions, workspace state, and cross-source exports (Claude, ChatGPT, bookmarks, GitHub activity) into a durable knowledge base repo with sensitive data redaction. - Use Case: After a long planning session, ask to save the key decisions. The Skill checks for existing entries, writes a concise memory file, creates entities and relations in MCP memory, updates the relevant GitHub issue, and commits a session summary to the knowledge base repo. ## Quick Start Save the decisions from this session to my knowledge base and sync them with GitHub and MCP memory.

Frequently Asked Questions about knowledge-ops

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

FAQPage Schema
How do I save information to a persistent knowledge base across sessions?▼

Classify the information by type first, then store it in the matching layer: quick-access memory files for preferences and context, MCP memory for searchable structured facts, and a Git-tracked knowledge base repo for durable long-form notes. Always search for existing entries before creating new ones.

How do I sync conversation history into a knowledge base?▼

Export sessions from Claude, Codex, or other agent tools into a knowledge base repo, generate a session index for browsing, then commit and push. Redact API keys and other sensitive values before committing anything to Git.

What is MCP memory and when should I use it?▼

MCP memory is a structured knowledge graph accessed through tools like create_entities, create_relations, add_observations, and search_nodes. Use it for semantic search and relationship mapping across sessions rather than for quick-access context, which belongs in memory files.

Should project status go in local notes or GitHub and Linear?▼

Active execution truth such as roadmaps, releases, and implementation state belongs in GitHub issues, PRs, and Linear first. Local notes should only mirror that information when they add value, avoiding parallel copies of the same plan.

How do I avoid duplicate knowledge entries?▼

Search memory files and query MCP memory with relevant terms before writing anything new, and check GitHub or Linear for existing records. Update the existing entry instead of creating a duplicate.

When should I use an external database instead of memory files?▼

Use an external store like Supabase or PostgreSQL for documents too large for memory files or data that needs SQL queries and full-text search. Keep a short summary in memory so the content remains discoverable.

Related Skills

Explore More Software Engineering Skills→
haomingzhaomingz
12

meeting-recap

Organize meeting materials into structured minutes with action items.

Community
Advanced
papercomputecopapercomputeco
264

tapes-search

Index and semantically search stored LLM sessions in the tapes telemetry system.

Official
Intermediate
LucasMatuszewskiLucasMatuszewski
2

audit-agents

Audit and repair agent configuration files for duplicates, stale facts, and naming conflicts.

Community
Advanced
AniTrendAniTrend
51

code-review-graph-explore

Explore repository architecture via code-review-graph knowledge graph queries.

Official
Intermediate