Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write comprehensive literature reviews following a systematic 7-phase workflow.
.claude/skills/medical-imaging-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-21 | ✗→✓ | ▲ Improved | — | — |
| case-04 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
Write comprehensive literature reviews following a systematic 7-phase workflow.
CLAUDE.md - Writing guidelines and terminologyIMPLEMENTATION_PLAN.md - Staged execution planmanuscript_draft.md - Main manuscriptTopic sentence (main claim)
→ Supporting evidence (citations + data)
→ Analysis (critical evaluation)
→ Transition to next paragraphUse multi-source strategy for comprehensive coverage:
| Source | Best For | Tools | |--------|----------|-------| | ArXiv | Latest DL methods, preprints | search_papers, read_paper | | PubMed | Clinical validation, peer-reviewed | pubmed_search_articles | | Zotero | Existing library, organized refs | zotero_search_items |
For MCP configuration details, see references/MCP_SETUP.md.
markdown# [Title]: State of the Art and Future Directions ## Key Points - [3-5 bullets summarizing main findings] ## Abstract ## 1. Introduction ### 1.1 Clinical Background ### 1.2 Technical Challenges ### 1.3 Scope and Contributions ## 2. Datasets and Evaluation Metrics ### 2.1 Public Datasets (Table 1) ### 2.2 Evaluation Metrics ## 3. Deep Learning Methods ### 3.1 [Category 1] ### 3.2 [Category 2] (Table 2: Method Comparison) ## 4. Downstream Applications ## 5. Commercial Products & Clinical Translation (Table 3) ## 6. Discussion ### 6.1 Current Limitations ### 6.2 Future Directions ## 7. Conclusion ## References
markdown### 3.X [Method Category] [1-2 paragraph introduction with motivation] **[Method Name]:** [Author] et al. [ref] proposed [method], which [innovation]: - [Key component 1] - [Key component 2] Achieves Dice of X.XX on [dataset]. **Limitations:** Despite advantages, [category] methods face: (1) [limit 1]; (2) [limit 2].
markdown# Data citation "...achieved Dice of 0.89 [23]" # Method citation "Gu et al. [45] proposed..." # Multi-citation "Several studies demonstrated... [12, 15, 23]" # Comparative "While [12] focused on..., [15] addressed..."
| File | Purpose | |------|---------| | references/WORKFLOW.md | Detailed 7-phase workflow | | references/TEMPLATES.md | CLAUDE.md and IMPLEMENTATION_PLAN.md templates | | references/DOMAINS.md | Domain-specific method categories | | references/MCP_SETUP.md | MCP server configuration | | references/QUALITY_CHECKLIST.md | Pre-submission quality checklist |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +48 percentage points is the difference between those two pass rates over the 23 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.