Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

GenLayer ERC-7710 Connector · internet-court | DecimalAI

codingby internet-court

GenLayer ERC-7710 Connector

internet-court/genlayer-erc7710-connector

Source internet-court/internet-court-skill ↗License NOASSERTION

Connect GenLayer Intelligent Contract decisions to ERC-7710-style delegated authority.

SkillScore86Maintained

Automatic

Coding pack

Last verified 8/12/2026

What it changes

Passed 17 of 20 test cases with the skill, and 5 of 20 without it.

Without skill27%

With skill86%

Checks it passed that the model alone missed

Specifies GenLayer source chain ID as 61998
Selects the Manual Demo Relay connector mode
Specifies a one-minute review cadence for demos

and 23 more in the full report

14 fixed5 passed either way2 still failing1 broke

Pass-rate lift: +59 pp
Tokens: +47%
Agent turns: 0%
Response time: -25%

Model gemini-3.6-flashMeasured 8/12/2026v119 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/internet-court-genlayer-erc7710-connector/SKILL.md https://app.decimal.ai/s/internet-court-genlayer-erc7710-connector/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add internet-court-genlayer-erc7710-connector, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/internet-court-genlayer-erc7710-connector/ and pins it in .decimal/skills.lock

decimalai skills add internet-court-genlayer-erc7710-connector

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/internet-court-genlayer-erc7710-connector/SKILL.md https://app.decimal.ai/s/internet-court-genlayer-erc7710-connector/SKILL.md

Raw file: /s/internet-court-genlayer-erc7710-connector/SKILL.md ↗ · machine-readable summary at /s/internet-court-genlayer-erc7710-connector.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

We are connecting Base Sepolia to GenLayer using the standard Studio bridge boilerplate. What chain IDs and LayerZero endpoint IDs should be configured by default?

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies Base Sepolia chain ID as 84532	Passed	Passed
Specifies Base Sepolia LayerZero endpoint ID as 40245	Passed	Passed
Specifies GenLayer source chain ID as 61998	Missed	Passed

case-13 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md197 lines2 files

GenLayer ERC-7710 Connector

Use this skill after the mandate, ERC-7710 policy, and GenLayer Intelligent Contract review flow exist. This skill does not teach GenLayer contract deployment. For GenLayer build, deploy, test, and CLI operations, use the official GenLayer skills at https://skills.genlayer.com/ or the GenLayer documentation.

This skill specifies the connector:

GenLayer Intelligent Contract decision
  -> decision proof / receipt / finalized result
  -> relayer or bridge
  -> EVM RevocationController
  -> ERC-7710 Delegation Manager rejects or constrains future redemptions

Design Rule

Never say "GenLayer cancels ERC-7710" without defining the effect path. GenLayer produces a decision. An EVM-side controller, account module, caveat enforcer, or delegation manager integration must consume that decision.

Workflow

Identify the permission:
- mandateId, permissionHash, delegator, delegate, delegation manager, target EVM chain, and current policy.
Identify the GenLayer decision source:
- supervisor contract address, method that stores/returns the decision, review window, decision enum, score, issued timestamp, and finalized transaction id.
Choose the connector mode:
- Manual demo relay, trusted relayer, GenLayer Studio bridge relay, optimistic relay with challenge window, light-client/bridge verification, or direct EVM call if supported by the target GenLayer/EVM integration.
Define the message:
- Include enough data for the EVM controller to revoke or constrain exactly one mandate/permission.
Define the EVM effect:
- Revoke, constrain, pause, require human approval, or mark pending appeal.
Define safety:
- Finality assumptions, replay protection, nonce, deadline, idempotency, emergency owner revoke, and absolute permission expiry.
Define tests:
- Continue does nothing, revoke blocks future redemption, constrain tightens policy, stale decisions fail, duplicate messages are idempotent, forged decisions fail.

Connector Modes

Use the simplest mode that honestly matches the demo.

Manual Demo Relay

Track record

Benchmark

17 / 20

test cases passed, vs 5 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

internet-court / internet-court-skill

integrations/genlayer-erc7710-connector/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

GenLayer ERC-7710 Connector

Design Rule

Workflow

Connector Modes

Manual Demo Relay

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills