Automated summary
Scores a research proposal's clinical value across four domains — patient outcomes, clinical decision impact, healthcare system impact, and evidence quality — and combines them into a weighted 0–5 score with an interpretation tier.
Strengths
- Four-domain rubric with 20 sub-criteria, each scored 1–5 alongside a written rationale.
- Explicit weighting formula (0.35 / 0.30 / 0.20 / 0.15) and five tiers from Transformative to Minimal, making scores transparent and comparable.
- Grounds ratings in current guideline recommendations and literature using WebSearch and the PubMed search tool.
- Enforces a fixed Markdown report template, so assessments are consistent across proposals.
Limitations
- Scores are model judgment rather than a validated instrument such as GRADE or an HTA framework.
- Requires the user to supply drug, indication, target population, and clinical question up front.
- Examples and the guideline table are heavily oncology-specific (multiple myeloma), and the fourth section of the output template is truncated.
Use it to triage and prioritize clinical research proposals before committing resources to them.
Not suitable for regulatory dossiers, formal HTA submissions, or quantitative benefit-risk analyses that demand validated instruments.
Security analysis
SafeThe skill only uses read-only tools (Read, Grep, Glob, WebSearch, PubMed search) and provides a structured evaluation framework. It does not instruct destructive, exfiltrating, or obfuscated actions, and has no execution risk.
No concerns found
How this analysis is madeExamples
ダラツムマブ皮下注の新規診断多発性骨髄腫（NDMM、TIE基準の高齢者）に対する DRd vs VRd 比較研究案について、臨床価値スコアを算出し、患者アウトカム・臨床意思決定・医療システム・エビデンス質の4領域で評価レポートを作成してください。現在の標準治療は VRd（または入手可能性に応じて DRd）です。切除不能膵癌に対する FOLFIRINOX とゲムシタビン＋ナブパクリタキセルを比較する研究案の臨床的価値を評価してください。臨床的問いは「高齢者・PS低下例ではどちらが優れるか」、対象集団は70歳以上です。NCCN・ESMO・日本膵臓学会の推奨も踏まえて各項目を1〜5で採点し、総合スコアと臨床価値レベルを出してください。以下の3つの研究案（A: DRd vs VRd、B: 高齢者での用量調整、C: PRO評価研究）それぞれに clinical-value スキルを適用し、総合臨床価値スコアとレベルを並べて優先順位を提案してください。name: clinical-value description: | 研究案の臨床的価値を評価する。患者アウトカム改善への貢献度、臨床意思決定への影響、 ガイドライン・治療戦略変更の可能性を多角的に評価。 allowed-tools:
- Read
- Grep
- Glob
- WebSearch
- mcp__plugin_pubmed_PubMed__search_articles context: normal
Clinical Value Skill
目的
研究案の臨床的価値を体系的に評価し、患者・臨床医・医療システムへの貢献度を定量化する。
入力パラメータ
| パラメータ | 必須 | 説明 | 例 | |-----------|------|------|-----| | RESEARCH_PROPOSAL | Yes | 研究案の概要 | DRd vs VRd比較効果研究 | | DRUG | Yes | 対象薬剤 | daratumumab | | INDICATION | Yes | 対象疾患 | NDMM | | TARGET_POPULATION | Yes | 対象患者集団 | TIE elderly patients | | CLINICAL_QUESTION | Yes | 臨床的問い | Which regimen is superior for frail patients? | | CURRENT_PRACTICE | No | 現在の標準治療 | VRd or DRd based on availability |
臨床的価値評価フレームワーク
1. 患者アウトカムへの影響（Patient Outcomes Impact）
| 評価項目 | 評価基準 | スコア (1-5) | |----------|----------|-------------| | 生存改善可能性 | 死亡率・OS改善への寄与 | | | QOL改善可能性 | 症状・機能・PRO改善への寄与 | | | 有害事象回避 | 毒性・副作用軽減への寄与 | | | 治療負担軽減 | 通院・入院・費用負担軽減 | | | 個別化治療への貢献 | 患者特性に応じた治療選択支援 | |
2. 臨床意思決定への影響（Clinical Decision Impact）
| 評価項目 | 評価基準 | スコア (1-5) | |----------|----------|-------------| | エビデンスギャップ充足 | 現在の不確実性解消への貢献 | | | 治療選択への影響 | 実臨床での処方行動変化 | | | 患者説明への活用 | IC・shared decision making支援 | | | リスク層別化への貢献 | 予後予測・リスク評価改善 | | | 適正使用への貢献 | 過少/過剰使用是正 | |
3. 医療システムへの影響（Healthcare System Impact）
| 評価項目 | 評価基準 | スコア (1-5) | |----------|----------|-------------| | ガイドライン改訂可能性 | 推奨変更への寄与 | | | 保険収載・償還への影響 | 薬価・適応拡大への寄与 | | | 医療資源適正化 | コスト・資源配分最適化 | | | 医療格差是正 | アクセス・公平性改善 | | | 医療安全向上 | 安全性監視・リスク管理改善 | |
4. エビデンスの質と適用性（Evidence Quality & Applicability）
| 評価項目 | 評価基準 | スコア (1-5) | |----------|----------|-------------| | 内的妥当性 | バイアス最小化、方法論的質 | | | 外的妥当性 | 日本実臨床への適用可能性 | | | 効果の大きさ | 臨床的に意味のある差か | | | 精度 | 十分なサンプルサイズ・信頼区間 | | | 一貫性 | 先行研究との整合性 | |
臨床価値スコアリング
総合臨床価値スコア算出
Clinical Value Score =
(Patient Outcomes × 0.35) +
(Clinical Decision × 0.30) +
(Healthcare System × 0.20) +
(Evidence Quality × 0.15)
スコア解釈
| スコア範囲 | 臨床価値レベル | 解釈 | |-----------|---------------|------| | 4.5-5.0 | Transformative | 診療を根本的に変える可能性 | | 3.5-4.4 | High | 重要な臨床的貢献が期待 | | 2.5-3.4 | Moderate | 一定の臨床的意義あり | | 1.5-2.4 | Limited | 限定的な臨床的意義 | | 1.0-1.4 | Minimal | 臨床的意義乏しい |
出力フォーマット
# Clinical Value Assessment: {RESEARCH_PROPOSAL}
## 1. 臨床的文脈
### 現在の臨床課題
- 対象疾患: {INDICATION}
- 対象薬剤: {DRUG}
- 対象患者: {TARGET_POPULATION}
- 臨床的問い: {CLINICAL_QUESTION}
- 現在の標準治療: {CURRENT_PRACTICE}
- **未充足臨床ニーズ**: [具体的記述]
### 関連ガイドライン・推奨
| 発行元 | 現在の推奨 | エビデンスレベル | 参照 |
|--------|-----------|----------------|------|
| NCCN | ... | ... | URL |
| ESMO | ... | ... | URL |
| 日本血液学会 | ... | ... | URL |
## 2. 臨床価値評価
### 2.1 患者アウトカムへの影響
| 項目 | スコア | 根拠 |
|------|--------|------|
| 生存改善可能性 | X/5 | ... |
| QOL改善可能性 | X/5 | ... |
| 有害事象回避 | X/5 | ... |
| 治療負担軽減 | X/5 | ... |
| 個別化治療貢献 | X/5 | ... |
| **小計** | X.X/5.0 | |
### 2.2 臨床意思決定への影響
| 項目 | スコア | 根拠 |
|------|--------|------|
| エビデンスギャップ充足 | X/5 | ... |
| 治療選択への影響 | X/5 | ... |
| 患者説明への活用 | X/5 | ... |
| リスク層別化貢献 | X/5 | ... |
| 適正使用貢献 | X/5 | ... |
| **小計** | X.X/5.0 | |
### 2.3 医療システムへの影響
| 項目 | スコア | 根拠 |
|------|--------|------|
| ガイドライン改訂可能性 | X/5 | ... |
| 保険収載・償還影響 | X/5 | ... |
| 医療資源適正化 | X/5 | ... |
| 医療格差是正 | X/5 | ... |
| 医療安全向上 | X/5 | ... |
| **小計** | X.X/5.0 | |
### 2.4 エビデンス質と適用性
| 項目 | スコア | 根拠 |
|------|--------|------|
| 内的妥当性 | X/5 | ... |
| 外的妥当性 | X/5 | ... |
| 効果の大きさ | X/5 | ... |
| 精度 | X/5 | ... |
| 一貫性 | X/5 | ... |
| **小計** | X.X/5.0 | |
## 3. 総合臨床価値スコア
| カテゴリ | スコア | 重み | 加重スコア |
|---------|--------|------|-----------|
| Patient Outcomes | X.X | 0.35 | X.XX |
| Clinical Decision | X.X | 0.30 | X.XX |
| Healthcare System | X.X | 0.20 | X.XX |
| Evidence Quality | X.X | 0.15 | X.XX |
| **総合** | - | - | **X.XX/5.0** |
### 臨床価値レベル: **[Transformative/High/Moderate/Limited/Minimal]**
## 4. EHR-RWDによる臨床価値向上
### クレームDB研究との差別化による追加価値
| 観点 | クレームDB | EHR-RWD | 臨床価値への貢献 |
|------|-----------|---------|-----------------|
| 詳細臨床情報 | × | ○ | 患者選択精度向上 |
| 検査値推移 | × | ○ | 効果/安全性評価精度向上 |
| 経過記録 | × | ○ | アウトカム定義精度向上 |
## 5. 限界と不確実性
1. [限界1]
2. [限界2]
3. [不確実性要因]
## 6. 臨床的推奨
### 研究実施推奨度: **[強く推奨 / 推奨 / 条件付推奨 / 非推奨]**
### 理由
[推奨理由の詳細]
### 想定される臨床インパクト
[研究結果が陽性だった場合の臨床実践への影響予測]
注意事項
- 患者視点の重視: 患者アウトカムへの影響を最重要視
- 現実的評価: 理論的価値と実臨床での実装可能性を区別
- エビデンスの質: 研究デザインの限界が臨床価値を制限する点を考慮
- 根拠の明示: 各評価に文献的根拠またはエキスパートオピニオンを明記
- 比較対象の明確化: 現在の標準治療・既存エビデンスとの比較で価値を評価
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/clinical-value-assessment-mmlj2nxi/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/clinical-value-assessment-mmlj2nxi' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/clinical-value-assessment-mmlj2nxi/download' --output '.skill-downloads/clinical-value-assessment-mmlj2nxi/SKILL.md.part' && mv '.skill-downloads/clinical-value-assessment-mmlj2nxi/SKILL.md.part' '.skill-downloads/clinical-value-assessment-mmlj2nxi/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/clinical-value-assessment-mmlj2nxi/SKILL.md' && test -s '.skill-downloads/clinical-value-assessment-mmlj2nxi/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/clinical-value' && cp -R '.skill-downloads/clinical-value-assessment-mmlj2nxi' '.claude/skills/clinical-value'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/clinical-value-assessment-mmlj2nxi'openskills read 'clinical-value-assessment-mmlj2nxi'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/clinical-value-assessment-mmlj2nxi/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Agent-Driven Parameter Optimization
Data & AI
Guide for optimizing configurable systems with a measurable objective, using bounded trials and evidence-based recommendations.
ICP Visitor Outreach
Data & AI
Identify signed-up users matching the ideal customer profile but stalled, and draft personalized outreach to re-engage them.