skills.rest
yes506
yes506COMMUNITY
Explore all skills by this author →
GitHub

knowledge-harvest

Distill developer knowledge from completed work cycles into a structured Obsidian vault.

Updated May 9, 2026
Search Tags:#automation#documentation#knowledge management#obsidian#developer productivity#idempotency
One-click install
npx skills add https://github.com/yes506/ai-driven-items --skill knowledge-harvest-yes506
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: knowledge-harvest
Source: https://github.com/yes506/ai-driven-items/tree/main/skills/knowledge-harvest
Command: npx skills add https://github.com/yes506/ai-driven-items --skill knowledge-harvest-yes506

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, tomli, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of losing valuable developer insights by automating the distillation of completed work cycles into a structured, deduplicated Obsidian knowledge base.

Core Features & Use Cases

  • Deterministic Distillation: Uses a 2-stage architecture where Python scripts handle state and atomic writes, while the LLM focuses solely on reasoning and judgment.
  • Security-First Design: Implements pre-LLM redaction and write-time fail-closed gates to ensure secrets never reach your vault.
  • Use Case: After finishing a complex debugging session or feature implementation, use this Skill to capture the patterns, pitfalls, and decisions you encountered, ensuring they are indexed and searchable for future projects.

Quick Start

Run the knowledge-harvest skill to distill the current work cycle into your global Obsidian knowledge vault.

Frequently Asked Questions about knowledge-harvest

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

FAQPage Schema
How do I automate developer knowledge extraction into an Obsidian vault?▼

Automating knowledge extraction into an Obsidian vault uses a 2-stage architecture where Python scripts handle state and atomic writes, while the LLM focuses on reasoning to capture reusable developer insights.

Can I safely distill debugging sessions without exposing secrets to the LLM?▼

Yes, distilling debugging sessions safely requires pre-LLM redaction and write-time fail-closed gates, ensuring secrets never reach your Obsidian vault during the knowledge capture process.

What is the best way to deduplicate developer insights when capturing work cycles?▼

Deduplicating developer insights is handled by fuzzy-matching new evidence against an existing index, ensuring your structured knowledge base remains clean and reusable across future projects.

How do atomic CAS-protected file operations work when updating a knowledge base?▼

Atomic CAS-protected file operations work by bundling evidence and applying updates through deterministic Python scripts, preventing race conditions and ensuring idempotent writes to your Obsidian vault.

Do I need PyYAML and tomli to automate documentation into Obsidian?▼

Yes, automating documentation into Obsidian requires PyYAML and tomli dependencies, which support the Python scripts responsible for managing state and executing atomic file operations.

Related Skills

Explore More Software Engineering Skills→
Fudan-SMI-labFudan-SMI-lab
39

torch-npu-pyyaml-preinstall

Preinstall PyYAML before torch-npu to prevent transitive dependency failures.

Official
Intermediate
timkrasetimkrase

qmd

Search an Obsidian vault with BM25, vector, and reranked hybrid queries.

Community
Intermediate
quangkmhdquangkmhd

obsidian-cli

Manage Obsidian vault notes, tasks, and properties from the command line.

Community
Advanced
krzemienskikrzemienski
2

skill-discovery

Scan project and user directories for SKILL.md files and generate a structured skill catalog.

Community
Intermediate