git:20260609.c54df30 to git:20260930.c83ad00

---

name: ma-scout

description: Meta-analysis topic discovery and feasibility assessment. Professor-first (profile → gap) or Topic-first (question → gap → co-author). Pre-protocol phase from idea to ranked topic list.

triggers: ma-scout, MA 주제 찾기, professor MA, 메타분석 주제, MA gap, topic-first MA, 트렌드 MA, meta-analysis topic, 교수님 분석, 연구 분석

tools: Read, Write, Edit, Bash, Grep, Glob

model: opus

---

# MA Scout Skill

For actual MA execution (PROSPERO, screening, analysis), hand off to `/meta-analysis`.

## Mode Selection

| Signal | Mode |

|--------|------|

| Professor name or profile URL provided | **A: Professor-first** |

| Clinical question, keyword, trend, or "find me a topic" | **B: Topic-first** |

| Both supplied (e.g., "this topic with this professor") | **A** (topic as filter) |

If ambiguous, ask the user whether to search by professor (supervisor-first) or by

topic (question-first).

## Inputs

### Mode A: Professor-first

- Minimum required: **name + at least one profile URL or PubMed link**

### Mode B: Topic-first

- Minimum required: **clinical question or keyword**

## Workflow

> **Mode A (Professor-first):** Phase 0 → 1 → 2 → 3 → 4 → 5

> **Mode B (Topic-first):** T-Phase 0 → T-1 → T-2 → T-3 → T-4 → T-5

> Phase 2 (MA Gap Analysis) and Phase 4 (README template) are shared between both modes.

# MODE A: PROFESSOR-FIRST WORKFLOW

### Phase 0: Disambiguation & Context Confirmation

- 2nd: Google Scholar profile (WebSearch `"[Full Name]" radiology scholar`)

- 3rd: ResearchGate profile (WebSearch `"[Full Name]" researchgate radiology`)

- 4th: ScholarWorks / SKKU / university faculty page (if URL provided)

### Phase 1: Profile Exploration (E-utilities API)

**Step 1 — Total publication count + PMID list:**

```bash

'"[Full Name]"[Author]' 200 \

```

**Step 2 — Fetch metadata for MeSH-based clustering (parallel):**

```bash

# Get PMIDs from Step 1, then fetch summaries

"PMID1,PMID2,..." \

```

```bash

'"[Full Name]"[Author] AND "keyword1"' 5

'"[Full Name]"[Author] AND "keyword2"' 5

# ... repeat for each suspected pillar keyword

```

**Step 4 — MeSH term extraction for automatic pillar clustering:**

```bash

# Fetch full XML for top-cited papers to extract MeSH headings

"PMID1,PMID2,...,PMID20" \

| python3 -c "

import sys, xml.etree.ElementTree as ET

from collections import Counter

root = ET.fromstring(sys.stdin.read())

mesh_counts = Counter()

for article in root.findall('.//PubmedArticle'):

for mh in article.findall('.//MeshHeading/DescriptorName'):

mesh_counts[mh.text] += 1

for term, count in mesh_counts.most_common(30):

print(f'{count:3d} {term}')

"

```

→ Top MeSH terms reveal natural research pillars (e.g., "Colonography, Computed Tomographic" = CTC pillar).

| Pillar | Domain | Representative keywords | MeSH terms | Est. # papers |

|--------|--------|-------------------------|-----------|---------------|

| 1 | ... | ... | ... | ~N+ |

### Phase 2: MA Gap Analysis (Multi-Source)

#### 2a. PubMed E-utilities — Existing MAs + Primary studies

```bash

# Existing MAs (structured count)

'[pillar keywords] AND ("meta-analysis"[pt] OR "systematic review"[pt])' 50

# Primary studies with extractable outcomes

'[pillar keywords] AND ("sensitivity" OR "specificity" OR "accuracy" OR "prognosis" OR "outcome")' 50

```

#### 2b. Consensus MCP — Semantic MA gap detection

Use `mcp__claude_ai_Consensus__search` to find existing SRs/MAs that PubMed keyword search might miss:

```

query: "systematic review OR meta-analysis [pillar topic] [imaging modality]"

```

Consensus returns citation-ranked results — check if any highly-cited MA already covers the proposed scope.

#### 2c. Scholar Gateway — Semantic similarity search

#### 2d. bioRxiv/medRxiv — In-press competition detection

```

query: "[pillar keywords] meta-analysis OR systematic review"

```

#### 2e. Assessment matrix

| Factor | Criteria |

|--------|----------|

| MA gap | 0 existing = best, 1-3 = check scope overlap, >5 = saturated |

| Primary k | ≥8 for DTA, ≥6 for prognostic (minimum), ≥15 ideal |

| Recency | Last MA >5 years old = update opportunity |

| Competition | Check 2024-2026 for very recent MAs that block entry |

#### 2f. PROSPERO competition check (MANDATORY)

#### 2g. Realistic k estimation

- Apply conservative discount: **k_realistic ≈ raw_count × 0.15–0.30** for DTA topics

- Flag if k_realistic < 8 (DTA) or < 6 (prognostic) as ⚠️ feasibility risk

- Report both raw and realistic estimates, e.g., `estimated k: ~130 (raw) → ~20–40 (extractable DTA data)`

### Phase 3: Topic Ranking

| Criteria | Weight | Description |

|----------|--------|-------------|

| **Professor fit** | Highest | Core area of the professor's career, publication count, distinctive contribution |

| **MA gap** | High | No prior MA > ≥5 yr since last MA > recent MA exists |

| **Feasibility (k)** | High | Number of includable studies and extractability of 2×2 or HR data |

| **Clinical impact** | Medium | Whether the topic directly informs clinical decision-making |

| **Execution ease** | Medium | Completable from literature alone; difficulty of managing heterogeneity |

**Output: Ranked Topic Table**

| Rank | Topic | Professor's Pillar | Prior MA | Estimated k (raw→realistic) | PROSPERO competition | Verdict |

|------|-------|--------------------|----------|-----------------------------|----------------------|---------|

| 1 | ... | ... | 0 | ~98 → 15–30 | None | ✅ Best fit |

### Phase 4: Folder & README Scaffolding

**Goal:** Create project folders and README for each viable topic.

- Professor folder: `{initials}_{name}` (e.g., `KDK_Kim`, `LKS_Lee`)

- Check existing folders with `ls` before creating

### Phase 5: Output Summary

1. Save the ranked topic table and README files to the working directory.

# MODE B: TOPIC-FIRST WORKFLOW

### T-Phase 0: Topic Clarification & Scope

```

user input: "AI for lung nodule malignancy prediction"

→ variant 1: AI vs radiologist for lung nodule malignancy prediction (DTA)

→ variant 2: Radiomics for lung nodule malignancy (DTA)

→ variant 3: Deep learning for incidental pulmonary nodule management (prognostic)

```

3. **User selects 1-3 angles** to investigate further.

### T-Phase 1: Landscape Scan (Multi-Source)

#### 1a. PubMed — Existing MA count

```bash

'[topic keywords] AND ("meta-analysis"[pt] OR "systematic review"[pt])' 50

```

#### 1b. PubMed — Primary study pool

```bash

'[topic keywords] AND ("sensitivity" OR "specificity" OR "hazard" OR "outcome")' 100

```

#### 1c. Consensus MCP — Semantic MA discovery

```

query: "systematic review [topic] [modality]"

```

Check for MAs using different terminology.

#### 1d. bioRxiv/medRxiv — Preprint competition

```

query: "[topic] meta-analysis"

server: "medrxiv"

```

#### 1e. PROSPERO — Registered protocols

WebSearch: `site:crd.york.ac.uk/prospero [topic keywords]`

**Output: Landscape Summary Table**

| Variant | Existing MAs | Primary k (raw) | k (realistic) | PROSPERO | Preprint MA | Verdict |

|---------|--------------|-----------------|---------------|----------|-------------|---------|

| 1 | 3 | 120 | 18-36 | 1 | 0 | ⚠️ Competitive |

| 2 | 0 | 85 | 13-25 | 0 | 0 | ✅ Optimal |

### T-Phase 2: Feasibility Deep-Dive

- **Gap certainty** — are existing MAs truly non-overlapping with proposed scope?

- **k quality** — are primary studies heterogeneous enough to warrant MA, or too uniform?

- **User's domain fit** — does this align with user's radiology AI / imaging expertise?

### T-Phase 3: Topic Ranking (Topic-first weights)

| Criteria | Weight | Description |

|----------|--------|-------------|

| **MA gap** | Highest | No existing MA > update opportunity > saturated |

| **Feasibility (k)** | Highest | k_realistic ≥ 8 (DTA) or ≥ 6 (prognostic) |

| **User domain fit** | High | Does it match the user's area of expertise? |

| **Clinical impact** | Medium | Potential to change guidelines; directly tied to clinical decisions |

| **Co-author availability** | Medium | Access to a domain expert (existing relationship or easy to reach) |

| **Execution ease** | Medium | Can be done solo vs requires expert interpretation |

**Output: Ranked Topic Table**

| Rank | Topic | Existing MAs | Est. k | PROSPERO | Co-author needed | Overall |

|------|-------|--------------|--------|----------|------------------|---------|

| 1 | ... | 0 | 25 | None | Optional | ✅ Optimal |

### T-Phase 4: Co-Author Matching (Optional)

**Goal:** If the user wants a senior co-author, find candidates.

**Strategy 2 — PubMed reverse search:**

```bash

# Find prolific authors in this specific topic

'[topic keywords] AND ("{user_country}"[Affiliation])' 100

```

**Output:** Co-author recommendation table or a "solo-viable" judgment.

### T-Phase 5: Folder & README Scaffolding (Topic-first)

- [ ] No 2024-2026 competing MA in press or preprint

1. **Search Execution** — E-utilities with broadened synonyms (retmax=200)

- Primary search: `[topic] AND [outcome keywords]`

- Existing MA search: `[topic] AND ("meta-analysis"[pt] OR "systematic review"[pt])`

2. **Metadata Collection** — `fetch_json` → `esummary` (batch 40-50 PMIDs)

4. **PRISMA Flow Draft** — Identification → Screening → Eligibility → Included (estimated)

6. **Output Files**:

- `candidates.md` — full triage table + PRISMA flow + gap finding

- `README.md` — updated Preliminary Search section with actual numbers