Skip to content

Add etherscan-contract-review skill - #6

Merged
homeyong merged 2 commits into
mainfrom
add-eth-contract-review
Aug 18, 2026
Merged

Add etherscan-contract-review skill#6
homeyong merged 2 commits into
mainfrom
add-eth-contract-review

Conversation

@wwwMalcolm

Copy link
Copy Markdown
Collaborator

Summary

Adds etherscan-contract-review, a developer-oriented skill for explaining verified deployed EVM contracts from a contract address and chain. It covers architecture, user and admin flows, proxy relationships, asset movement, privileged controls, and evidence-backed uncertainty without presenting the result as a security audit.

What's included

  • SKILL.md — retrieval and analysis workflow, safety boundaries, evidence rules, and failure handling
  • references/ — CLI setup and authentication, source analysis, contract patterns, and report guidance
  • agents/openai.yaml — skill UI metadata and default prompt
  • README discovery and installation entries

Validation

  • python scripts/validate_skills.py — pass
  • python -B -m unittest discover -s tests -p "test_*.py" — 19 tests passed
  • Skills CLI discovery (Node 22 / skills@1.5.22) — found 1 skill

@wwwMalcolm
wwwMalcolm requested a review from homeyong August 17, 2026 10:20
@wwwMalcolm wwwMalcolm self-assigned this Aug 17, 2026
@@ -0,0 +1,77 @@
---
name: etherscan-contract-review
description: Review and explain verified deployed EVM smart contracts from a contract address and chain. Use when Codex is asked to break down what a Solidity contract does, map its architecture and source files, identify user/admin flows, proxy or implementation roles, asset movement, privileged controls, events, state variables, or unresolved uncertainty for developer onboarding, integration triage, or preliminary technical review. This is a developer-oriented contract review, not a security audit or safety certification.

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@wwwMalcolm The description hard-codes "Use when Codex is asked to…", but every sibling skill (etherscan, etherscan-flow, etherscan-transaction-debugger) phrases the trigger agent-neutrally ("Use when a user provides/asks…").

This description field is the text an agent matches against to decide whether to activate the skill. Binding it to "Codex" specifically looks like a copy-paste artifact — under Claude Code (a primary consumer per the README) and any other non-Codex agent, the phrasing reads wrong and degrades triggering fidelity.

Could you update it to "Use when a user is asked to…" (or similar agent-neutral wording) to match the other skills? 🙏

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi @homeyong , I have pushed the changes, please review again.

@homeyong
homeyong merged commit ac0206c into main Aug 18, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants