Borrowing it
Nothing to install: this file belongs to u9401066/nsforge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/u9401066/nsforge-mcp/master/.claude/skills/nsforge-usolver-collab/SKILL.mdgit clone --depth 1 https://github.com/u9401066/nsforge-mcpWrote 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.
[](https://agentmods.dev/skills/u9401066/nsforge-mcp/nsforge-usolver-collab)<a href="https://agentmods.dev/skills/u9401066/nsforge-mcp/nsforge-usolver-collab"><img src="https://agentmods.dev/badge/skills/u9401066/nsforge-mcp/nsforge-usolver-collab.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.02435 |
| Opus 5 | $0.00000 | $0.01218 |
| Sonnet 5 | $0.00000 | $0.00487 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade A, and why
nsforge-usolver-collab 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NSForge-USolver 協作 Skill
ID: nsforge-usolver-collab
Version: 1.0.0
Trigger: 優化, optimize, 最佳解, optimal, 約束求解, constraint solving, USolver
🎯 Skill 定位
領域知識推導 × 數學優化 = 完整解決方案
此 Skill 協調 NSForge 和 USolver 兩個 MCP Server 協同工作:
- NSForge: 推導領域專業的修正公式(考慮藥物交互作用、體質差異等)
- USolver: 在修正後的公式中找最優解(滿足約束的最佳參數值)
⚙️ 工作流程
用戶問題
↓
1️⃣ NSForge 推導修正公式
derivation_start()
derivation_load_formula()
derivation_substitute() / derivation_add_note()
derivation_complete()
↓
2️⃣ 準備優化輸入
derivation_prepare_for_optimization()
↓
3️⃣ USolver 求最優解
usolver.solve(...)
↓
4️⃣ 呈現結果
整合推導步驟 + 最優解 + 解釋
📋 使用時機
適用場景
-
藥物劑量優化
- 用戶:「65歲、體脂30%、併用midazolam,最佳Fentanyl劑量?」
- NSForge:推導修正後的 PK 公式
- USolver:找滿足治療窗的最優劑量
-
電路參數優化
- 用戶:「考慮寄生電容和溫度漂移,濾波器最佳 R, C 值?」
- NSForge:推導修正後的轉移函數
- USolver:找符合規格的標準元件值
-
資源配置優化
- 用戶:「考慮加班費和技能津貼,最低成本排班?」
- NSForge:推導成本計算公式
- USolver:找最優排班方案
不適用場景
- 純數學計算(直接用 SymPy-MCP)
- 不需優化的問題(直接用 NSForge)
- 沒有領域修正的優化(直接用 USolver)
🔧 工具鏈
Phase 1: NSForge 推導
# 1. 開始推導會話
derivation_start(
name="temp_corrected_pk",
description="Temperature-corrected pharmacokinetics"
)
# 2. 載入基礎公式
derivation_load_formula(
source_type="library",
identifier="pharmacokinetics/three_compartment"
)
# 3. 應用修正
derivation_substitute(
"CL",
"CL_base * temp_factor * age_factor * interaction_factor",
notes="溫度 × 年齡 × 藥物交互作用修正"
)
# 4. 完成推導
derivation_complete()
Phase 2: 準備優化
# 取得優化器格式
result = derivation_prepare_for_optimization()
# 返回:
# {
# "function_str": "dose/V1 * exp(-CL*t/V1)",
# "variables": ["dose", "t"],
# "parameters": {"CL": 0.476, "V1": 15.875},
# "suggested_constraints": [
# "dose >= 0.01",
# "dose <= 0.10"
# ],
# "usolver_template": "..."
# }
Phase 3: USolver 優化
# 複製 USolver 模板到 USolver MCP
usolver.solve(
problem_type="convex_optimization",
objective="minimize (target - C(t, dose))**2",
constraints=[
"C(t=5, dose) >= 2.0", # 治療下限
"C(t=5, dose) <= 4.0", # 毒性上限
"dose >= 0.01",
"dose <= 0.10"
],
formula="dose/15.875 * exp(-0.476*5/15.875)"
)
# 返回:
# {
# "optimal_dose": 0.035,
# "objective_value": 0.04,
# "C_at_t5": 2.8
# }
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 · 294 lines · 0 tokens per session scan A 27552e7ad27f
nsforge-usolver-collab is a skill published in the GitHub repository u9401066/nsforge-mcp (4 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,435 tokens. 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 2026-08-31.
Other skills, from other repositories
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
batch-processing-clinical-text
Run large-scale batch NER, PII extraction, or de-identification over many clinical notes on-device with OpenMed, with sharding, checkpointing, resumability, and append-only JSONL output. Use when the user needs to process a corpus or folder of notes, de-identify a dataset, run NER over thousands of documents, build a…
coding-hcc-risk-adjustment
Maps chronic conditions extracted by OpenMed to CMS-HCC V28 risk-adjustment categories and estimates a RAF (Risk Adjustment Factor) score as decision support. Use when the user wants to surface risk-adjustable diagnoses from notes, map ICD-10-CM codes to HCC categories, estimate or reconcile a patient/panel RAF, find…
detecting-pv-signals
Computes disproportionality signals — PRR, ROR, EBGM, and IC (BCPNN) — over FAERS / OpenFDA drug-event data to flag potential safety signals. Use when the user wants to mine spontaneous-report data for drug-reaction associations, build a 2x2 contingency table, compute a Proportional Reporting Ratio or Reporting Odds…
paper-revision-author
Revise independently drafted paper sections into one coherent LaTeX body before the abstract is written.