A conversation-intelligent skill that generates a personalized builder identity and recommends AI tools based on your actual work habits.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-wrapper
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 openclaw-wrapper 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 Bloom Discovery?
Bloom Discovery is a specialized utility designed for the modern developer working with Openclaw Skills. It functions by analyzing your local conversation history and configuration files to build a comprehensive profile of how you learn, decide, and build in the AI era. Instead of relying on generic surveys, it leverages your real-world interactions to define your builder taste and professional archetype.
This skill bridges the gap between raw data and actionable self-insight, providing users with a Bloom Identity Card that includes personality types like the Visionary or the Optimizer. By integrating directly into your workflow, it ensures that your discovery of new tools and frameworks is always personalized to your specific technical interests and risk tolerance.
Bloom Discovery Use Cases
- Discovering your unique builder archetype through automated analysis of your chat history.
- Generating a shareable, portable identity dashboard to showcase your builder profile to the community.
- Receiving highly relevant recommendations for other Openclaw Skills that match your specific tech stack and interests.
- Identifying hidden patterns in your decision-making and learning style to optimize your daily workflow.
How Bloom Discovery Works
- The skill is triggered via the
/bloomcommand or natural language prompts within the agent interface. - It locally accesses the last 120 messages of your conversation history and your local USER.md profile to gather context.
- A local analysis engine maps your data against four core taste spectrums: Learning (Try vs. Study), Decision (Gut vs. Analytical), Novelty (Early vs. Proven), and Risk (All-in vs. Measured).
- The processed analysis is sent to the Bloom Protocol API to generate a unique identity card and dashboard URL.
- The agent presents a structured summary of your identity, builder tagline, and a list of recommended tools with high-percentage match scores.
Bloom Discovery Setup
To install this as one of your active Openclaw Skills, use the quick install command:
clawhub install bloom-taste-finder
For manual installation and development setup:
# Navigate to your workspace and clone the repository
cd ~/.openclaw/workspace
git clone https://github.com/Bloom-Protocol/bloom-discovery-skill.git
cd bloom-discovery-skill
# Install the necessary Node.js dependencies
npm install
# Deploy the skill wrapper to your local skills directory
cp -r openclaw-wrapper ~/.openclaw/skills/bloom
Bloom Discovery Data Schema & Taxonomy
The skill manages data across local files and remote endpoints to balance privacy with functionality:
| Component | Source | Storage Type | Purpose |
|---|---|---|---|
| Conversation Context | ~/.openclaw/agents/ | Local (JSONL) | Analyzes the last 120 messages for identity mapping. |
| User Preferences | USER.md | Local (Markdown) | Reads declared role, tech stack, and interests. |
| Discovery Log | bloom-discoveries.md | Local (Markdown) | Syncs and saves tools you have discovered via the skill. |
| Identity Metadata | Bloom API | Remote (JSON) | Stores your personality type and taste spectrums for dashboard hosting. |
Bloom Discovery Advanced Features
- Intelligent Feedback Loop: The system learns from your engagement, boosting categories you interact with and filtering out dismissed recommendations.
- USER.md Primary Signaling: Automatically detects your manually defined developer role and stack to ensure profiling accuracy.
- Piped Context Support: Power users can run analysis from piped CLI input or specific session files using the provided TypeScript scripts.
- TTL-Based Refresh: Recommendations are automatically refreshed every 7 days to incorporate new Openclaw Skills and updated user habits.
SKILL.md
Loading
Related Openclaw Skills
Bloom Taste Finder
Analyze your conversation history to discover your unique builder archetype and receive tailored AI tool recommendations.
Bloom Identity Card Generator
An advanced identity generator that transforms conversation history and social data into a personalized AI agent profile and crypto wallet.
Valyu Search
An advanced search and intelligence skill that enables AI agents to perform deep research, web scraping, and cited answering via Valyu.ai.
Qlik Cloud Integration for AI Agents
A comprehensive integration suite of 37 tools for managing Qlik Cloud analytics, reloads, and AI-powered insights through Openclaw Skills.
Context Guard
An automated context management protocol that prevents AI memory loss and token waste through intelligent watermarking, partitioning, and checkpoint archiving.
UniOne Email API
A professional-grade email delivery skill for sending transactional and marketing messages at scale with 99.88% deliverability.
Featured*
