Save, organize, synchronize, and retrieve documents, conversations, and project information across local files, memory tools, knowledge repositories, and databases. Check for duplicates before storing information and choose a suitable home for each type of knowledge.
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
knowledge-ops classifies documents, conversations, and project information, then stores, organizes, synchronizes, and searches them in suitable locations. It works across Claude Code memory, MCP Memory Server, Git repositories for knowledge bases, and external databases. Before saving, it searches existing information and updates matching entries rather than creating duplicates. It also maintains indexes and summaries.
Use it when conversation records and reference materials are scattered across several places and are difficult to find later. It also helps you choose storage based on the information's purpose: ongoing plans can go in GitHub or Linear, while research worth keeping can go in a knowledge base.
Depending on the destination, access to MCP memory tools, Git repositories, GitHub, Linear, Supabase, or other storage is required. API keys and passwords are removed before information is recorded in Git. Knowledge bases and archive folders must not replace the working location used for actual code changes.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 19, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Manage a multi-layered knowledge system for ingesting, organizing, syncing, and retrieving knowledge across multiple stores.
Prefer the live workspace model:
~/.claude/projects/*/memory/When new knowledge needs to be captured:
What type of knowledge is it?
Check if this knowledge already exists:
Write to appropriate layer(s):
Update any relevant indexes or summary files.
Periodically sync conversation history into the knowledge base:
Mirror important workspace configuration and scripts to the knowledge base:
When the information affects active execution:
Pull knowledge from multiple sources into one place:
# Short-term: current session context
Use TodoWrite for in-session task tracking
# Medium-term: project memory files
Write to ~/.claude/projects/*/memory/ for cross-session recall
# Long-term: GitHub / Linear / KB
Put active execution truth in GitHub + Linear
Put durable synthesized context in the knowledge base repo
# Semantic layer: MCP knowledge graph
Use mcp__memory__create_entities for permanent structured data
Use mcp__memory__create_relations for relationship mapping
Use mcp__memory__add_observations for new facts about known entities
Use mcp__memory__search_nodes to find existing knowledge
Before completing any knowledge operation:
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design and audit interfaces for Web, iOS, and Android using WCAG 2.2 accessibility guidance. Check screen-reader labels, keyboard navigation, contrast, and control sizes to identify barriers and guide implementation for people using assistive technology.
Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.
Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.
Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.
Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.
Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.