aiedwardyi

SecondLook — Development skill for Claude Code

Development community

BCC detector with Claude as a Grad-CAM trust layer - attention check for the doctor's final call.

How to install SecondLook

This entry records only its repository, not the path inside it, so there is no exact command to give. Open aiedwardyi/SecondLook and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What SecondLook does

BCC detector with Claude as a Grad-CAM trust layer - attention check for the doctor's final call.

Alternatives in Development

Internet Court Skill — The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 4.9k ★
CORS — Scan an endpoint for CORS misconfiguration — arbitrary-origin reflection, null-origin trust, credential exposu 4.5k ★
Octo Doctor — Environment diagnostics — check providers, auth, config, hooks, scheduler, and more 2.8k ★

README

SecondLook: a trust layer for a skin-cancer detector

[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE) ![Python 3.12](https://img.shields.io/badge/python-3.12-blue.svg) ![EfficientNet-B4](https://img.shields.io/badge/model-EfficientNet--B4-blue.svg)

Research and teaching demonstration only. Not a medical device. Not for diagnosis or clinical use.

*Detection approach presented at AAD Innovation Academy 2026. [See related research](#related-research).*

SecondLook is for a **dermatopathologist, Mohs surgeon, or dermatologist** reviewing tissue tiles for basal cell carcinoma. They upload images. The app scores each tile with EfficientNet-B4, shows Grad-CAM attention, and maps the score to a three-tier call (positive / uncertain / negative). On a confident positive, Claude runs a constrained attention check - a spellcheck on whether that finding should be trusted, not a diagnosis of the patient. The detector class never changes. The doctor owns the final call.

The detector finds cancer. Claude decides whether to trust that finding.

![Before and after Grad-CAM for one BCC tile](docs/figure_before_after.png)

Left: a basal cell carcinoma tile.
Center: baseline attention concentrates on the top-right padding corner, not the tissue.
Right: after correction, attention sits on tissue.

Try this first

Open the live app: demo
Open Compare on a positive tile.
Note before: corner heat, Claude FLAGGED. Note after: tissue heat, Claude VERIFIED. Same detector confidence class; different trust.

Video: [YouTube](https://youtu.be/v3zw5bIx1yw)

Website: [secondlookderm.com](https://secondlookderm.com)

Hackathon entry: [Built with Claude: Life Sciences](https://cerebralvalley.ai/e/built-with-claude-life-sciences/hackathon/gallery?project=90)