ercdata
Store, verify, and manage AI data on the Ethereum blockchain (Base network) using the ERCData standard. Use when an agent needs to store data fingerprints on-chain, verify data integrity, create audit trails, manage access control for private data, or interact with the ERCData smart contract. Supports public and private storage, EIP-712 verification, snapshots, and batch operations.
94
93%
Does it follow best practices?
Impact
93%
2.32xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific capabilities, provides explicit 'Use when' triggers, and occupies a highly distinctive niche. It uses proper third-person voice throughout and balances conciseness with comprehensive detail about both the domain (blockchain/Ethereum/Base) and the specific operations supported.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: store data fingerprints on-chain, verify data integrity, create audit trails, manage access control, interact with ERCData smart contract, plus mentions public/private storage, EIP-712 verification, snapshots, and batch operations. | 3 / 3 |
Completeness | Clearly answers both 'what' (store, verify, manage AI data on Ethereum/Base using ERCData standard) and 'when' (explicit 'Use when' clause listing specific trigger scenarios like storing data fingerprints, verifying integrity, creating audit trails, managing access control). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Ethereum', 'blockchain', 'Base network', 'ERCData', 'on-chain', 'data fingerprints', 'verify data integrity', 'audit trails', 'access control', 'smart contract', 'EIP-712'. Good coverage of domain-specific terms a user working in this space would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very clear niche: Ethereum blockchain (Base network), ERCData standard, EIP-712 verification. These are extremely specific triggers unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that efficiently communicates how to use the ERCData CLI for blockchain data storage. Its strengths are excellent conciseness, fully executable examples, and good progressive disclosure. The main weakness is the lack of explicit validation workflows for multi-step or irreversible blockchain operations (e.g., confirming transaction success before proceeding).
Suggestions
Add an explicit workflow sequence for common multi-step operations (e.g., store → confirm tx receipt → verify → read back) with validation checkpoints, especially since blockchain transactions are irreversible.
Include a brief error handling note: what to do if a transaction fails or reverts (e.g., insufficient gas, missing PROVIDER_ROLE), since these are common failure modes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Ethereum, Base, or EIP-712 are—it assumes Claude knows. Every section serves a purpose: quick start commands, config, command reference table, privacy model notes, and use cases are all tightly written without padding. | 3 / 3 |
Actionability | The quick start section provides fully copy-paste ready CLI commands for all core operations (store, read, verify, grant-access). Configuration is clearly specified with env vars and flags. The commands table gives a complete overview of available operations. | 3 / 3 |
Workflow Clarity | While individual commands are clear, there's no explicit validation workflow for multi-step processes. For example, after storing data, there's no 'verify the store succeeded' step. The store-then-verify flow is implied but not sequenced with checkpoints. Since this involves blockchain transactions (potentially destructive/irreversible), missing validation steps cap this at 2. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-organized sections and a single, clearly signaled reference to the full API documentation in references/api.md. Content is appropriately split between the overview and the detailed reference file. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
45f9fac
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.