A skin-health screening workflow that takes a photo, analyzes it with local image models, and can optionally send it for remote expert review. It also stores results and compares changes over time.

Use it to analyze a new or existing photo, mark possible lesions, review severity scores, consult a remote expert, and compare past checks.

It provides a way to organize image-based skin checks, records, and trend comparisons in one workflow.

skin-check — Skill for Claude Code by lisihao

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add lisihao/Solar --skill skin-check

Clone the repo

git clone --depth 1 https://github.com/lisihao/Solar

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lisihao/solar/skin-check/github.svg)](https://agentmods.dev/skills/lisihao/solar/skin-check)

Your own site

<a href="https://agentmods.dev/skills/lisihao/solar/skin-check"><img src="https://agentmods.dev/badge/skills/lisihao/solar/skin-check/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lisihao/solar/skin-check"><img src="https://agentmods.dev/badge/skills/lisihao/solar/skin-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,187 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.01187
Opus 5	$0.00009	$0.00593
Sonnet 5	$0.00003	$0.00237
Haiku 4.5	$0.00002	$0.00119

Measured 7d ago against content hash d2afb956297a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skin-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/skin-check/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

皮肤检测 v2.0

AI 驱动的皮肤健康检测系统，支持本地分析和远程专家评审。

Phase 2: 本地模型实现

✅ 已实现

Phase 2.1: 本地分类器 (~/.claude/skills/skin-check/phase2/)
- CoreML 框架 + MobileNetV3-Large
- 推理速度: ~30ms (100x faster than API)
- 成本: $0 (vs $0.002/次 Phase 1)
- 支持离线使用
Phase 2.2: YOLOv8 病灶检测
- 实时病灶位置标注
- 严重程度评估 (0-100 分)
- 边界框可视化
Phase 2.3: 历史记录与趋势分析
- SQLite 数据库存储
- 30 天趋势分析
- 改善/恶化/稳定状态检测

⏸️ 挂起

Phase 2.4: 专用模型训练
- 等待部署到 Mac mini Pro 48G
- 数据集: DermNet (23K) / ISIC (50K)
- 预估时间: 1-2.5 小时
- 目标准确度: 85-90%
- Backlog: task-e84fb0b2b11dfe95

使用方式

完整流程 (拍照 + 本地分析)

bun ~/.claude/skills/skin-check/phase2/skin-check-v2.ts

测试模式 (使用已有图片)

bun ~/.claude/skills/skin-check/phase2/skin-check-v2.ts --test=~/Desktop/selfie_xxx.jpg

混合模式 (本地 + 远程专家)

bun ~/.claude/skills/skin-check/phase2/skin-check-v2.ts --remote

历史记录管理

# 查看最近 10 次记录
bun ~/.claude/skills/skin-check/phase2/history-tracker.ts list 10

# 趋势分析
bun ~/.claude/skills/skin-check/phase2/history-tracker.ts trend 30d

# 对比两次检测
bun ~/.claude/skills/skin-check/phase2/history-tracker.ts compare 1 2

性能对比

指标	Phase 1 (纯API)	Phase 2.1 (本地)
延迟	3-5s	~30ms (100x faster)
成本	$0.002/次	$0
离线	❌	✅
准确度	80-90% (专家)	60-70% (简化规则)

技术栈

运行时: Bun (TypeScript)
本地模型: CoreML (MobileNetV3-Large)
推理: Vision framework (Swift)
病灶检测: YOLOv8 (CoreML)
历史存储: SQLite

架构

用户拍照
    │
    ▼
┌──────────────────────┐
│ Phase 2.1: 本地分类  │ ← CoreML + Swift
│ • 皮肤类型识别       │   Vision framework
│ • 置信度评分         │   ~30ms
└──────┬───────────────┘
       │
       ▼
┌──────────────────────┐
│ Phase 2.2: 病灶检测  │ ← YOLOv8 + CoreML
│ • 位置标注           │   边界框检测
│ • 严重程度评估       │   0-100 分
└──────┬───────────────┘
       │
       ▼
┌──────────────────────┐
│ Phase 2.3: 历史记录  │ ← SQLite
│ • 保存检测结果       │   趋势分析
│ • 趋势分析           │   改善/恶化/稳定
└──────────────────────┘

Read the full file on GitHub · 134 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 134 lines · 17 tokens per session scan A d2afb956297a

Subscribe to this mod's changes

skin-check is a skill published in the GitHub repository lisihao/Solar (2 stars, last pushed 28d ago), licensed MIT. It adds 17 tokens to every session and 1,187 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Scientific

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens