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.
89
Quality
86%
Does it follow best practices?
Impact
93%
2.32xAverage score across 3 eval scenarios
Evaluation results
96%
52%AI Agent Memory Attestation Automation
CLI invocation and configuration
uv run invocation
0%
100%
Script path pattern
100%
100%
ERCDATA_KEY env var
0%
80%
ERCDATA_CONTRACT env var
100%
75%
Private storage flag
0%
100%
AI_AGENT_MEMORY data type
0%
100%
Hash stored not raw content
100%
100%
Metadata included
0%
100%
Configuration comment block
100%
100%
JSON output
100%
100%
Without context: $0.2280 · 1m 13s · 18 turns · 53 in / 3,854 out tokens
With context: $0.3725 · 1m 16s · 19 turns · 23 in / 4,389 out tokens
100%
66%On-Chain AI Output Integrity Auditor
Data verification and integrity checking
verify eip712 method
0%
100%
verify hash method
0%
100%
info command usage
0%
100%
VERIFIER_ROLE noted
60%
100%
uv run invocation
0%
100%
ERCDATA_KEY used
0%
100%
ERCDATA_CONTRACT used
0%
100%
Structured JSON report
100%
100%
Iterates all provided IDs
100%
100%
CLI path from env var
100%
100%
Without context: $0.5816 · 2m 40s · 42 turns · 625 in / 8,092 out tokens
With context: $0.3955 · 1m 26s · 21 turns · 1,224 in / 4,769 out tokens
84%
40%Multi-Agent Confidential Configuration Sharing
Private data access control and snapshots
Private storage used
16%
100%
Encryption before storing
92%
100%
grant-access command
20%
100%
Multiple addresses granted
100%
100%
snapshot command
50%
100%
uv run invocation
0%
100%
ERCDATA_KEY env var
0%
0%
ERCDATA_CONTRACT env var
0%
0%
Privacy model comment
70%
100%
CLI path from env var
75%
100%
Without context: $0.6510 · 2m 52s · 31 turns · 36 in / 9,423 out tokens
With context: $0.6620 · 3m 4s · 20 turns · 1,191 in / 10,732 out tokens
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
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.