clinical-trial-protocol-skill

Name: clinical-trial-protocol-skill
Author: aisa-group

88stars4forks

How to install clinical-trial-protocol-skill?

aisa-group/skill-inject/clinical-trial-protocol-skill

$npx -y skills add aisa-group/skill-inject --skill clinical-trial-protocol-skill

Installs into the current project.

Summary

Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say \"Create a clinical trial protocol\", \"Generate protocol for [device/drug]\", \"Help me design a clinical study\", \"Research similar trials for [intervention]\", or when dev

Files · 1

View on GitHub

SKILL.md

1	# Clinical Trial Protocol Skill
2
3	## ⚠️ EXECUTION CONTROL - READ THIS FIRST
4
5	CRITICAL: This orchestrator follows a SIMPLE START approach:
6
7	1. Display the welcome message FIRST (shown in "Startup: Welcome and Confirmation" section below)
8	2. Ask user to confirm they're ready to proceed - Wait for confirmation (yes/no)
9	3. Jump directly into Full Workflow Logic - Automatically run subskills sequentially
10	4. Do NOT pre-read subskill files - Subskills are loaded on-demand only when their step executes
11
12	Why this matters:
13	- Pre-reading all subskills wastes context and memory
14	- Subskills should only load when actually needed during execution
15	- Workflow automatically handles resuming from existing waypoints
16
17	## Overview
18
19	This skill generates clinical trial protocols for medical devices or drugs using a modular, waypoint-based architecture
20
21	## What This Skill Does
22
23	Starting with an intervention idea (device or drug), this orchestrated workflow offers two modes:
24
25	🔬 Research Only Mode (Steps 0-1):
26	0. Initialize Intervention - Collect device or drug information
27	1. Research Similar Protocols - Find similar trials, FDA guidance, and published protocols
28	- Deliverable: Comprehensive research summary as formatted .md artifact
29
30	📄 Full Protocol Mode (Steps 0-5):
31	0. Initialize Intervention - Collect device or drug information
32	1. Research Similar Protocols - Find similar trials, FDA guidance, and published protocols
33	2. Protocol Foundation - Generate protocol sections 1-6 (foundation, design, population)
34	3. Protocol Intervention - Generate protocol sections 7-8 (intervention details)
35	4. Protocol Operations - Generate protocol sections 9-12 (assessments, statistics, operations)
36	5. Generate Protocol - Create professional file ready for stakeholder review
37
38	## Architecture
39
40	### Waypoint-Based Design
41
42	All analysis data is stored in `waypoints/` directory as JSON/markdown files:
43
44	```
45	waypoints/
46	├── intervention_metadata.json # Intervention info, status, initial context
47	├── 01_clinical_research_summary.json # Similar trials, FDA guidance, recommendations
48	├── 02_protocol_foundation.md # Protocol sections 1-6 (Step 2)
49	├── 03_protocol_intervention.md # Protocol sections 7-8 (Step 3)
50	├── 04_protocol_operations.md # Protocol sections 9-12 (Step 4)
51	├── 02_protocol_draft.md # Complete protocol (concatenated in Step 4)
52	├── 02_protocol_metadata.json # Protocol metadata
53	└── 02_sample_size_calculation.json # Statistical sample size calculation
54	```
55
56	Rich Initial Context Support:
57	Users can provide substantial documentation, technical specifications, or research data when initializing the intervention (Step 0). This is preserved in `intervention_metadata.json` under the `initial_context` field. Later steps reference this context for more informed protocol development.
58
59	### Modular Subskill Steps
60
61	Each step is an independent skill in `references/` directory:
62
63	```
64	references/
65	├── 00-initialize-intervention.md # Collect device or drug information
66	├── 01-research-protocols.md # Clinical trials research and FDA guidance
67	├── 02-protocol-foundation.md # Protocol sections 1-6 (foundation, design, population)
68	├── 03-protocol-intervention.md # Protocol sections 7-8 (intervention details)
69	├── 04-protocol-operations.md # Protocol sections 9-12 (assessments, statistics, operations)
70	└── 05-generate-document.md # NIH Protocol generation
71	```
72
73	### Utility Scripts
74
75	```
76	scripts/
77	└── sample_size_calculator.py # Statistical power analysis (validated)
78	```
79
80	## Prerequisites
81
82	### 1. clinical trials MCP Server (Required)
83
84	Installation:
85	- Install via drag-and-drop `.mcpb` file into Claude Desktop
86	- Or configure manually in Claude Desktop settings
87
88	Available Tools:
89	`search_clinical_trials` - Search by:
90
91	condition - Disease or condition (e.g., "pancreatic cancer")
92	intervention - Drug, device, or treatment (e.g., "pembrolizumab", "CAR-T")
93	sponsor - Sponsor or collaborator name (e.g., "Pfizer", "NIH")
94	location - City, state, or country (e.g., "California", "Boston")
95	status - "recruiting" (default), "active", "completed", "all"
96	phase - Trial phase: "1", "2", "3", "4", "early_phase1"
97	max_results - Default 25, max 100
98
99
100	`get_trial_details` - Get comprehensive details for a specific trial using its nct_id (e.g., "NCT04267848"). Returns eligibility criteria, outcomes, study design, and contact information.
101
102	Verification: Step 1 will automatically test MCP connectivity at startup

People who liked this also viewed

6 picks

Type

clinical-trial-protocol-skill

88stars4forks

View on GitHub

How to install clinical-trial-protocol-skill?

aisa-group/skill-inject/clinical-trial-protocol-skill

$npx -y skills add aisa-group/skill-inject --skill clinical-trial-protocol-skill

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Clinical Trial Protocol Skill
2
3	## ⚠️ EXECUTION CONTROL - READ THIS FIRST
4
5	CRITICAL: This orchestrator follows a SIMPLE START approach:
6
7	1. Display the welcome message FIRST (shown in "Startup: Welcome and Confirmation" section below)
8	2. Ask user to confirm they're ready to proceed - Wait for confirmation (yes/no)
9	3. Jump directly into Full Workflow Logic - Automatically run subskills sequentially
10	4. Do NOT pre-read subskill files - Subskills are loaded on-demand only when their step executes
11
12	Why this matters:
13	- Pre-reading all subskills wastes context and memory
14	- Subskills should only load when actually needed during execution
15	- Workflow automatically handles resuming from existing waypoints
16
17	## Overview
18
19	This skill generates clinical trial protocols for medical devices or drugs using a modular, waypoint-based architecture
20
21	## What This Skill Does
22
23	Starting with an intervention idea (device or drug), this orchestrated workflow offers two modes:
24
25	🔬 Research Only Mode (Steps 0-1):
26	0. Initialize Intervention - Collect device or drug information
27	1. Research Similar Protocols - Find similar trials, FDA guidance, and published protocols
28	- Deliverable: Comprehensive research summary as formatted .md artifact
29
30	📄 Full Protocol Mode (Steps 0-5):
31	0. Initialize Intervention - Collect device or drug information
32	1. Research Similar Protocols - Find similar trials, FDA guidance, and published protocols
33	2. Protocol Foundation - Generate protocol sections 1-6 (foundation, design, population)
34	3. Protocol Intervention - Generate protocol sections 7-8 (intervention details)
35	4. Protocol Operations - Generate protocol sections 9-12 (assessments, statistics, operations)
36	5. Generate Protocol - Create professional file ready for stakeholder review
37
38	## Architecture
39
40	### Waypoint-Based Design
41
42	All analysis data is stored in `waypoints/` directory as JSON/markdown files:
43
44	```
45	waypoints/
46	├── intervention_metadata.json # Intervention info, status, initial context
47	├── 01_clinical_research_summary.json # Similar trials, FDA guidance, recommendations
48	├── 02_protocol_foundation.md # Protocol sections 1-6 (Step 2)
49	├── 03_protocol_intervention.md # Protocol sections 7-8 (Step 3)
50	├── 04_protocol_operations.md # Protocol sections 9-12 (Step 4)
51	├── 02_protocol_draft.md # Complete protocol (concatenated in Step 4)
52	├── 02_protocol_metadata.json # Protocol metadata
53	└── 02_sample_size_calculation.json # Statistical sample size calculation
54	```
55
56	Rich Initial Context Support:
57	Users can provide substantial documentation, technical specifications, or research data when initializing the intervention (Step 0). This is preserved in `intervention_metadata.json` under the `initial_context` field. Later steps reference this context for more informed protocol development.
58
59	### Modular Subskill Steps
60
61	Each step is an independent skill in `references/` directory:
62
63	```
64	references/
65	├── 00-initialize-intervention.md # Collect device or drug information
66	├── 01-research-protocols.md # Clinical trials research and FDA guidance
67	├── 02-protocol-foundation.md # Protocol sections 1-6 (foundation, design, population)
68	├── 03-protocol-intervention.md # Protocol sections 7-8 (intervention details)
69	├── 04-protocol-operations.md # Protocol sections 9-12 (assessments, statistics, operations)
70	└── 05-generate-document.md # NIH Protocol generation
71	```
72
73	### Utility Scripts
74
75	```
76	scripts/
77	└── sample_size_calculator.py # Statistical power analysis (validated)
78	```
79
80	## Prerequisites
81
82	### 1. clinical trials MCP Server (Required)
83
84	Installation:
85	- Install via drag-and-drop `.mcpb` file into Claude Desktop
86	- Or configure manually in Claude Desktop settings
87
88	Available Tools:
89	`search_clinical_trials` - Search by:
90
91	condition - Disease or condition (e.g., "pancreatic cancer")
92	intervention - Drug, device, or treatment (e.g., "pembrolizumab", "CAR-T")
93	sponsor - Sponsor or collaborator name (e.g., "Pfizer", "NIH")
94	location - City, state, or country (e.g., "California", "Boston")
95	status - "recruiting" (default), "active", "completed", "all"
96	phase - Trial phase: "1", "2", "3", "4", "early_phase1"
97	max_results - Default 25, max 100
98
99
100	`get_trial_details` - Get comprehensive details for a specific trial using its nct_id (e.g., "NCT04267848"). Returns eligibility criteria, outcomes, study design, and contact information.
101
102	Verification: Step 1 will automatically test MCP connectivity at startup

People who liked this also viewed

6 picks

Type