Productivity
update-claude - Claude MCP Skill
Update CLAUDE Files with Relevant Knowledge from This Session
SEO Guide: Enhance your AI agent with the update-claude tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to update claude files with relevant knowledge from this session... Download and configure this skill to unlock new capabilities for your AI workflow.
Documentation
SKILL.md# Update CLAUDE Files with Relevant Knowledge from This Session FYI: You, Claude Code, manage persistent memory using two main file types: `CLAUDE.md` for shared or global project context, and `CLAUDE.local.md` for private, developer-specific notes. The system recursively searches upward from the current working directory to load all relevant `CLAUDE.md` and `CLAUDE.local.md` files, ensuring both project-level and personal context are available. Subdirectory `CLAUDE.md` files are only loaded when working within those subfolders, keeping the active context focused and efficient. Additionally, placing a `CLAUDE.md` in your home directory (e.g., `~/.claude/CLAUDE.md`) provides a global, cross-project memory that is merged into every session under your home directory. **Summary of Memory File Behavior:** - **Shared Project Memory (`CLAUDE.md`):** - Located in the repository root or any working directory - Checked into version control for team-wide context sharing - Loaded recursively from the current directory up to the root - **Local, Non-Shared Memory (`CLAUDE.local.md`):** - Placed alongside or above working files, excluded from version control - Stores private, developer-specific notes and settings - Loaded recursively like `CLAUDE.md` - **On-Demand Subdirectory Loading:** - `CLAUDE.md` files in child folders are loaded only when editing files in those subfolders - Prevents unnecessary context bloat - **Global User Memory (`~/.claude/CLAUDE.md`):** - Acts as a personal, cross-project memory - Automatically merged into sessions under your home directory --- **Instructions:** If during your session: - You learned something new about the project - I corrected you on a specific implementation detail - I corrected source code you generated - You struggled to find specific information and had to infer details about the project - You lost track of the project structure and had to look up information in the source code ...that is relevant, was not known initially, and should be persisted, add it to the appropriate `CLAUDE.md` (for shared context) or `CLAUDE.local.md` (for private notes) file. If the information is relevant for a subdirectory only, place or update it in the `CLAUDE.md` file within that subdirectory. When specific information belongs to a particular subcomponent, ensure you place it in the CLAUDE file for that component. For example: - Information A belongs exclusively to the `web` component → put it in `web/CLAUDE.md` - Information B belongs exclusively to the `api` component → put it in `api/CLAUDE.md` This ensures important knowledge is retained and available in future sessions.
Signals
Information
- Repository
- kamui-fin/readspace
- Author
- kamui-fin
- Last Sync
- 6/7/2026
- Repo Updated
- 5/1/2026
- Created
- 1/16/2026
Reviews (0)
No reviews yet. Be the first to review this skill!
Related Skills
cursorrules
CrewAI Development Rules
firecrawl-build-onboarding
Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.
firecrawl-build-search
Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.
firecrawl-build
Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.
Related Guides
Bear Notes Claude Skill: Your AI-Powered Note-Taking Assistant
Learn how to use the bear-notes Claude skill. Complete guide with installation instructions and examples.
OpenAI Whisper API Claude Skill: Complete Guide to AI-Powered Audio Transcription
Learn how to use the openai-whisper-api Claude skill. Complete guide with installation instructions and examples.
Mastering the Oracle CLI: A Complete Guide to the Claude Skill for Database Professionals
Learn how to use the oracle Claude skill. Complete guide with installation instructions and examples.