Bloom Discovery Skill

---

name: bloom-discovery

version: 4.0.1

description: >

Agent-native discovery skill for the intent economy.

Analyzes your MentalOS, matches use cases to your installed skills,

lets you claim SBT proof, and optionally reports usage metrics —

all privacy-first with local analysis.

homepage: https://bloomprotocol.ai

category: agent-tools

os: [macos, linux]

network: base-mainnet

metadata:

{

"openclaw": {

"emoji": "🌸",

"requires": { "bins": ["node", "npx"] }

}

}

---

# Bloom Discovery Skill

Don't browse 13,000 skills. Browse use cases.

Bloom Discovery is an agent-native skill that analyzes how you work, matches you to curated use cases, verifies your configuration, and lets you claim on-chain proof — so your agent works for you, not the other way around.

Capabilities

1. Personality Analysis (MentalOS)

Reads your USER.md and conversation history (~120 messages) to map your builder personality across 4 dimensions:

Outputs: Personality type (Visionary / Explorer / Cultivator / Optimizer / Innovator), custom tagline, hidden pattern insight, AI edge guide. Includes `displayLabels` with en/zh translations for all sections.

2. Use Case Discovery

Intent-driven skill browsing. Instead of searching 13,000 skills, you describe what you want to accomplish and Bloom matches you to curated use cases — each a tested combination of skills.

3. Verify Configuration & Claim SBT

Scans your installed skills (`~/.openclaw/skills/`) and verifies whether you have the right setup for a given use case.

4. ERC-8004 Identity Registration

Register your agent identity on the ERC-8004 Agent Identity Registry (Base mainnet).

5. Usage Metrics (Opt-in)

Anonymized usage reporting to improve recommendations for everyone.

Security & Privacy

✅ **Local analysis** — Conversation text analyzed on your machine, never uploaded

✅ **Local Differential Privacy (ε=1.0)** — Spectrum scores noised via Laplace mechanism before transmission

✅ **SHA-256 fingerprint** — Conversation hashed locally; only irreversible hash stored for dedup

✅ **Minimal transmission** — Server receives personality type + approximate scores only

✅ **Minimal writes** — Writes only `~/.bloom/agent-id.json` (returning user token, 0600 permissions) and `bloom-discoveries.md` (local sync log). Never modifies session files or USER.md

✅ **Atomic file writes** — Uses tmp+rename pattern to prevent corruption

✅ **User-initiated** — Only runs when you explicitly invoke the skill

✅ **Opt-in metrics** — Usage data never sent without consent

✅ **Open source** — Full source at [github.com/bloomprotocol/bloom-discovery-skill](https://github.com/bloomprotocol/bloom-discovery-skill)

❌ Raw conversation text is **never** sent to any server

❌ Wallet private keys are **never** transmitted

❌ Personal identifiable information is **never** collected

❌ No background data collection — only runs on explicit invocation

Triggers

Data Sources

Primary: USER.md + Conversation History

Secondary: Installed Skills

Output

Technical Details

Requirements

- `BLOOM_API_URL` — API URL (default: https://api.bloomprotocol.ai)

- `DASHBOARD_URL` — Dashboard URL (default: https://bloomprotocol.ai)

Installation

git clone https://github.com/bloomprotocol/bloom-discovery-skill.git
cd bloom-identity-skill
npm install

---

Built by [Bloom Protocol](https://bloomprotocol.ai)