bloom-discoveryAgent-native discovery skill for the intent economy. Analyzes your MentalOS, matches use cases to your installed skills, lets you claim SBT proof, and option...
Install via ClawdBot CLI:
clawdbot install bloomprotocol/bloom-discoveryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://api.bloomprotocol.ai/skills/admin/suggestPotentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://bloomprotocol.aiUses known external API (expected, informational)
api.github.comGenerated Mar 21, 2026
A developer new to AI agents uses Bloom Discovery to analyze their conversation history and USER.md, generating a personalized builder type and tagline. They then discover use cases tailored to their personality, such as automating code reviews or deploying smart contracts, and verify their current skill setup to claim an SBT as proof of configuration.
A business team integrates Bloom Discovery into their workflow to assess team members' MentalOS profiles, identifying learning and decision styles. This helps match employees to AI skill use cases like data analysis or customer support automation, ensuring efficient tool adoption and verifying configurations for compliance tracking via on-chain SBTs.
Educators and students use Bloom Discovery to analyze their interaction patterns with AI agents, determining their builder personality to find use cases like personalized tutoring or research assistance. They verify installed skills against these use cases, claiming SBTs to showcase verified expertise in educational AI applications.
A freelancer leverages Bloom Discovery to evaluate their MentalOS from project conversations, discovering use cases that align with their risk-averse or novelty-seeking traits, such as content generation or DeFi analytics. They verify their skill configuration, claim an SBT for credibility, and opt into anonymized metrics to improve future recommendations.
A startup founder uses Bloom Discovery to analyze team discussions and USER.md files, mapping builder personalities to identify optimal AI use cases like market analysis or product prototyping. They verify skill setups, register agent identities on the ERC-8004 registry for decentralized proof, and use insights to guide AI investment decisions.
Offer basic personality analysis and use case discovery for free, while charging for advanced analytics, detailed reports, or priority support. Revenue can come from subscription tiers or one-time payments for enhanced features like in-depth pattern insights or custom AI edge guides.
License Bloom Discovery to companies for team-wide AI skill optimization, integrating it into corporate workflows. Revenue is generated through annual licenses, customization fees for tailored use case catalogs, and support contracts for large-scale deployments and compliance tracking.
Partner with AI skill marketplaces to recommend and verify skills through Bloom Discovery, earning commissions on skill sales or installations driven by the platform. Additional revenue can come from affiliate partnerships or featured listings for curated use cases.
💬 Integration Tip
Ensure Node.js 18+ is installed and the OpenClaw skills directory is accessible; users should have at least 3 conversation messages for analysis to work effectively.
Scored Apr 19, 2026
AI Analysis
The skill's external API calls (Bloom API, GitHub) are consistent with its stated purpose for fetching use cases and skill data. The 'UNKNOWN_DATA_SINK' signal appears to be for an admin/suggest endpoint which, given the skill's context, is likely part of its legitimate backend for reporting opt-in metrics or suggestions, not unauthorized exfiltration. No evidence of credential harvesting, intent override, or obfuscation was found in the provided definition.
Audited Apr 17, 2026 · audit v1.0
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version f...
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
Prefer `skillhub` for skill discovery/install/update, then fallback to `clawhub` when unavailable or no match. Use when users ask about skills, 插件, or capabi...
Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s...
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.