A specialized tool that extracts first-principles knowledge from AI dialogues and generates structured, Obsidian-compatible Markdown notes.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install distill-conversation
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install distill-conversation using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Distill Conversation (Alembic)?
The Distill Conversation skill is a powerful cognitive tool within the Openclaw Skills ecosystem designed to act as a knowledge alembic. Instead of merely summarizing a chat, it analyzes raw AI dialogues to filter out noise, redundant pleasantries, and corrected errors, leaving behind high-value insights. It is specifically built for developers and researchers who use LLMs for deep thinking and want to preserve those insights in a structured format.
By leveraging first-principles thinking, this skill reorganizes information into logical layers—definition, purpose, mechanism, and implementation. It integrates seamlessly with personal knowledge management workflows by generating notes that include full YAML frontmatter, Wiki-links, and conflict detection for existing vault content.
Distill Conversation (Alembic) Use Cases
- Automatically converting ChatGPT share links into permanent technical documentation for a knowledge base.
- Distilling long, rambling brainstorming sessions into clear, actionable first-principles notes.
- Populating an Obsidian inbox with structured insights without manual copy-pasting.
- Managing complex research by extracting up to three core independent knowledge units from a single session.
How Distill Conversation (Alembic) Works
- The user provides a ChatGPT share URL or pastes raw conversation text directly into the agent.
- For URLs, the skill uses a Python-based parser to locally fetch and extract structured data from the React Server Component format.
- The agent identifies core keywords—focusing on cognitive gain rather than word frequency—to determine the note's primary subjects.
- The skill performs a search in the local vault to check for naming conflicts, ensuring existing knowledge is not overwritten.
- Content is distilled through a filter that discards redundant dialogue and emphasizes the correct logical conclusions and the user's specific learning path.
- A structured Markdown file is generated with optimized headers, tags, and metadata, then saved to the designated inbox directory.
Distill Conversation (Alembic) Setup
The skill requires Python 3.6+ and utilizes only standard libraries to ensure security. To optimize your experience with Openclaw Skills, set your Obsidian vault path in your environment variables:
export OBSIDIAN_VAULT_PATH="/path/to/your/obsidian/vault"
To initiate distillation from a shared link, use the following command structure:
/distill-conversation https://chatgpt.com/share/your-uuid-here
Distill Conversation (Alembic) Data Schema & Taxonomy
The skill organizes knowledge using a strict Markdown taxonomy to ensure long-term readability and vault compatibility:
| Component | Description |
|---|---|
| YAML Frontmatter | Contains auto-generated tags (e.g., #AI, #Tools), source URL, and creation date. |
| Core Question | Every note starts with a central question the distillation aims to answer. |
| Essence Definition | A first-principles explanation of what the concept is and why it exists. |
| Mechanism | A detailed breakdown of how the concept or solution works. |
| Learning Path | A unique section capturing the user's specific logic and follow-up questions from the original chat. |
| Wiki-links | Internal links to related concepts already present in your vault. |
Distill Conversation (Alembic) Advanced Features
- Conflict Warning System: Automatically detects similar filenames in your vault and adds a warning callout to help you merge new insights with existing notes.
- Local-First Security: All processing occurs locally; share URLs are parsed using standard Python libraries without external API calls or subprocess execution.
- Smart Keyword Extraction: Limits output to 1-3 high-impact files to prevent vault clutter, focusing on the most significant cognitive increments.
- Flexible Output Priority: Supports specific --output-dir overrides while defaulting to an organized 00.Inbox folder within the Openclaw Skills framework.
SKILL.md
Loading
Related Openclaw Skills
DeerFlow
A high-performance deep research integration that connects AI agents to the LangGraph-powered DeerFlow engine for complex, multi-step information gathering.
Writing Credibility Auditor
A sophisticated AI auditor that scans text for logical fallacies, unsupported claims, weasel words, and misleading statistics to generate a structured credibility report.
Lead Guardian
Lead Guardian is an AI-driven automation skill designed to instantly qualify real estate leads and alert agents to high-intent opportunities.
Compliance Guardian — FinCEN Real Estate Reporting
A specialized compliance tool for real estate professionals to navigate FinCEN reporting requirements for non-financed property transfers.
Polymarket Micro Coin Lag Trader
A specialized trading skill that exploits price discovery delays between Bitcoin and altcoins in Polymarket 5-minute interval markets.
Micro Pulse Revert Trader
A specialized trading skill that detects extreme retail sentiment pulses on Polymarket's 5-minute crypto markets to execute automated mean-reversion trades.
Featured*
