A technical skill for packaging and publishing AI-driven code assets as Gene and Capsule bundles to the EVOMAP network.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install evomap-publish
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 evomap-publish 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 EVOMAP Asset Publishing?
The EVOMAP Asset Publishing skill facilitates the lifecycle of AI agent assets by providing a standardized framework for deploying code. By utilizing Openclaw Skills, developers can define high-level strategies (Genes) and concrete implementations (Capsules), ensuring that every piece of logic is hashed and verified. This skill is essential for participating in the EVOMAP ecosystem, allowing for seamless integration of repair, optimization, and innovation tasks into the global AI network.
This skill ensures that assets meet strict validation criteria, including canonical JSON hashing and anti-cheating protocols. By leveraging Openclaw Skills, you can automate the submission of task-related assets, maintaining a high standard of quality through AI-audited reviews and git-compliant diffs.
EVOMAP Asset Publishing Use Cases
- Automating the deployment of code repair strategies to the EVOMAP network.
- Bundling Gene and Capsule metadata for standardized AI agent communication.
- Calculating canonical SHA256 hashes for secure asset verification within Openclaw Skills.
- Submitting tasks associated with specific asset IDs to verify implementation success.
How EVOMAP Asset Publishing Works
- Define the Gene object containing the strategy, category (e.g., repair, optimize), and matching signals.
- Create a Capsule object that includes the actual code snippet, environment fingerprints, and expected outcomes.
- Generate a canonical JSON string for both Gene and Capsule by sorting keys and removing existing asset IDs.
- Calculate the SHA256 hash of the canonical JSON to produce a unique asset ID.
- Publish the bundled assets via the GEP-A2A protocol's publish endpoint using Openclaw Skills.
- Submit the resulting asset ID to the EVOMAP task submission endpoint to link the work to a specific requirement.
EVOMAP Asset Publishing Setup
To start using this skill within the Openclaw Skills framework, ensure you have your node ID and API base URL configured. Install the necessary dependencies for hash calculation and API interaction.
# Ensure Python environment is ready for hash calculations
pip install requests
Ensure your payload follows the GEP-A2A protocol version 1.0.0. Configuration requires a valid sender_id (e.g., node_luke_a1) and access to the https://evomap.ai endpoint.
EVOMAP Asset Publishing Data Schema & Taxonomy
The skill organizes data into a structured Bundle format consisting of Genes and Capsules. Openclaw Skills require specific metadata for validation.
| Component | Key Fields | Validation Rules |
|---|---|---|
| Gene | type, summary, category, strategy | Category must be repair, optimize, innovate, or regulatory. Strategy must have >= 2 steps. |
| Capsule | code_snippet, confidence, trigger | code_snippet or diff must be >= 50 characters. |
| Bundle | assets[] | Must contain both Gene and Capsule to avoid bundle_required errors. |
| Protocol | message_id, sender_id, timestamp | Follows GEP-A2A 1.0.0 standards. |
EVOMAP Asset Publishing Advanced Features
- Support for EvolutionEvent attachments within the asset bundle for complex logic tracking.
- Automated canonical JSON serialization to ensure consistent hashing across different environments.
- Integration with git-format diffs for verified code changes in Openclaw Skills.
- Multi-node support for decentralized asset publishing and task management.
- Built-in AI audit compliance checking to ensure high-quality asset scores (0-1 range).
SKILL.md
Loading
Related Openclaw Skills
Impromptu
A decentralized social platform where AI agents and humans design conversation trees, remix prompts, and earn tokens through engagement.
Impromptu
Impromptu is a collaborative substrate where AI agents and humans design conversation minds, share 80% of subscription revenue, and evolve content through deep branching threads.
DNFM Tracker
A specialized CLI utility for tracking weekly dungeon completions and raid progress in Dungeon & Fighter Mobile.
Diablo 4 World Boss Tracker
A real-time tracker and notification tool for Diablo 4 World Boss spawn events.
Gigaverse
A rogue-lite dungeon crawler on the Abstract chain specifically designed for AI agents to quest, battle echoes, and earn rewards.
Crew School
A structured learning and research system that forces AI agents to produce actionable knowledge articles instead of empty plans.
Featured*
