second brain
A local-first RAG system for indexing Markdown vaults and generating project documents via local LLMs.
$30
Works with the AI Agents you already use
second brain
Example session with this skill installed
I need a project brief for the 'Helios' migration. Index the vault first to make sure you have the latest notes on the database schema, then run the brief command.
- Read your context and instructions
- Compiled the second brain
I have indexed the vault and generated the project brief for the Helios migration based on your latest notes.
Project Brief: Helios Migration
Context: Migration of legacy user data from the v1 PostgreSQL instance to the new distributed schema.
Objectives:
- Move 4.2 million records with zero downtime.
- Implement the new partitioned schema for the 'orders' table.
- Validate data integrity using the new hashing service.
Retrieved Findings:
Notes indicate that the 'orders' table in v1 lacks a consistent created_at index, which may slow down the initial batch extraction. The user_metadata blob must be flattened into the profile_attributes table as per the tech lead's note from 2023-11-12.
Technical Risks:
- Data Latency: Potential replication lag between the old and new nodes during the cutover phase.
Schema Mismatch: The v1 json fields may contain malformed entries that do not validate against the new Pydantic models.
Timeline Risks:
- The batch processing scripts are currently unoptimized; initial tests suggest a 14-hour window, which exceeds the maintenance target.
Assumptions:
- The staging environment accurately reflects the production load.
- The v1 database will remain in read-only mode during the final sync.
Next steps
- Review the Technical Risks section with the DevOps team to finalize the cutover strategy.
- Run
make research INPUT="Helios batch script optimization"to find existing performance benchmarks.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop feeding your entire knowledge base into context windows or cloud-hosted notebooks. This skill implements a local-first retrieval system that processes your private Markdown vault using local LLMs. It solves the privacy problem by ensuring sensitive project notes and technical documentation stay on your disk, only sending specific, retrieved context packs to a local model for synthesis.
What it does
- Vault Indexing generates a local vector store from your Markdown notes for efficient retrieval.
- Privacy Enforcement ensures note content stays local, preventing large-scale data leakage to cloud providers.
- Synthesis Engine transforms raw notes into structured project briefs, research summaries, and technical proposals.
- Decision Tracking records architecture decisions directly back to your vault as formatted Markdown files.
- Risk Assessment automatically appends technical and timeline risks to every generated document based on vault hooks.
How it works
- Index the vault using
make indexwhenever your local Markdown files are updated. - Query the system using specific commands like
make researchormake briefwith a targeted subject string. - Verify the output, which combines retrieved context with mandatory risk and assumption sections.
- Persist decisions by running
make decision, which saves a timestamped record to the vault.
Frameworks & tools
Built with Python 3.10+, GNU Make, and Ollama. It requires the llama3 model and utilizes Chroma for local vector storage of Markdown files.
Why this beats prompting it yourself
Manual prompting requires copy-pasting notes, which is slow and risks leaking data to the model provider. This skill automates the RAG pipeline locally, ensuring consistent formatting and mandatory risk analysis that single prompts often skip.
Use cases
- Draft project briefs using scattered meeting notes and technical specs.
- Generate technical proposals from private internal documentation.
- Synthesize research findings across dozens of disparate Markdown files.
- Log architectural decisions with automated risk and assumption tagging.
Known limitations
Requires a local Ollama instance running llama3. The vault must contain Markdown files to function. It does not support non-markdown file formats or remote vector databases.
Requires local Python 3.10+, GNU Make, and Ollama with llama3. Only supports Markdown files in the vault. Output depends on local model performance and existing vault content.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires
Permissions
No special permissions declared or detected