deep-research

Name: deep-research
Author: OpsinTech

91stars18forks

How to install deep-research?

opsintech/opsintech-platform/deep-research

$npx -y skills add OpsinTech/opsintech-platform --skill deep-research

Installs into the current project.

Summary

Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial s

Files · 1

View on GitHub

SKILL.md

1	# Deep Research Skill
2
3	## Overview
4
5	This skill provides a systematic methodology for conducting thorough web research. Load this skill BEFORE starting any content generation task to ensure you gather sufficient information from multiple angles, depths, and sources.
6
7	## When to Use This Skill
8
9	Always load this skill when:
10
11	### Research Questions
12	- User asks "what is X", "explain X", "research X", "investigate X"
13	- User wants to understand a concept, technology, or topic in depth
14	- The question requires current, comprehensive information from multiple sources
15	- A single web search would be insufficient to answer properly
16
17	### Content Generation (Pre-research)
18	- Creating presentations (PPT/slides)
19	- Creating frontend designs or UI mockups
20	- Writing articles, reports, or documentation
21	- Producing videos or multimedia content
22	- Any content that requires real-world information, examples, or current data
23
24	## Core Principle
25
26	Never generate content based solely on general knowledge. The quality of your output directly depends on the quality and quantity of research conducted beforehand. A single search query is NEVER enough.
27
28	## Research Methodology
29
30	### Phase 1: Broad Exploration
31
32	Start with broad searches to understand the landscape:
33
34	1. Initial Survey: Search for the main topic to understand the overall context
35	2. Identify Dimensions: From initial results, identify key subtopics, themes, angles, or aspects that need deeper exploration
36	3. Map the Territory: Note different perspectives, stakeholders, or viewpoints that exist
37
38	Example:
39	```
40	Topic: "AI in healthcare"
41	Initial searches:
42	- "AI healthcare applications 2024"
43	- "artificial intelligence medical diagnosis"
44	- "healthcare AI market trends"
45
46	Identified dimensions:
47	- Diagnostic AI (radiology, pathology)
48	- Treatment recommendation systems
49	- Administrative automation
50	- Patient monitoring
51	- Regulatory landscape
52	- Ethical considerations
53	```
54
55	### Phase 2: Deep Dive
56
57	For each important dimension identified, conduct targeted research:
58
59	1. Specific Queries: Search with precise keywords for each subtopic
60	2. Multiple Phrasings: Try different keyword combinations and phrasings
61	3. Fetch Full Content: Use `web_fetch` to read important sources in full, not just snippets
62	4. Follow References: When sources mention other important resources, search for those too
63
64	Example:
65	```
66	Dimension: "Diagnostic AI in radiology"
67	Targeted searches:
68	- "AI radiology FDA approved systems"
69	- "chest X-ray AI detection accuracy"
70	- "radiology AI clinical trials results"
71
72	Then fetch and read:
73	- Key research papers or summaries
74	- Industry reports
75	- Real-world case studies
76	```
77
78	### Phase 3: Diversity & Validation
79
80	Ensure comprehensive coverage by seeking diverse information types:
81
82	\| Information Type \| Purpose \| Example Searches \|
83	\|-----------------\|---------\|------------------\|
84	\| Facts & Data \| Concrete evidence \| "statistics", "data", "numbers", "market size" \|
85	\| Examples & Cases \| Real-world applications \| "case study", "example", "implementation" \|
86	\| Expert Opinions \| Authority perspectives \| "expert analysis", "interview", "commentary" \|
87	\| Trends & Predictions \| Future direction \| "trends 2024", "forecast", "future of" \|
88	\| Comparisons \| Context and alternatives \| "vs", "comparison", "alternatives" \|
89	\| Challenges & Criticisms \| Balanced view \| "challenges", "limitations", "criticism" \|
90
91	### Phase 4: Synthesis Check
92
93	Before proceeding to content generation, verify:
94
95	- [ ] Have I searched from at least 3-5 different angles?
96	- [ ] Have I fetched and read the most important sources in full?
97	- [ ] Do I have concrete data, examples, and expert perspectives?
98	- [ ] Have I explored both positive aspects and challenges/limitations?
99	- [ ] Is my information current and from authoritative sources?
100
101	If any answer is NO, continue researching before generating content.
102
103	## Search Strategy Tips
104
105	### Effective Query Patterns
106
107	```
108	# Be specific with context
109	❌ "AI trends"
110	✅ "enterprise AI adoption trends 2024"
111
112	# Include authoritative source hints
113	"[topic] research paper"
114	"[topic] McKinsey report"
115	"[topic] industry analysis"
116
117	# Search for specific content types
118	"[topic] case study"
119	"[topic] statistics"
120	"[topic] expert interview"
121
122	# Use temporal qualifiers — always use the ACTUAL current year from <current_date>
123	"[topic] 2026" # ← replace with real current year, never hardcode a past year
124	"[topic] latest"
125	"[topic] recent developments"
126	```
127
128	### Temporal Awareness
129
130	Always check `<current_date>` in your context before forming ANY search query.
131
132	`<current_d

People who liked this also viewed

6 picks

Type

deep-research

91stars18forks

View on GitHub

How to install deep-research?

opsintech/opsintech-platform/deep-research

$npx -y skills add OpsinTech/opsintech-platform --skill deep-research

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Deep Research Skill
2
3	## Overview
4
5	This skill provides a systematic methodology for conducting thorough web research. Load this skill BEFORE starting any content generation task to ensure you gather sufficient information from multiple angles, depths, and sources.
6
7	## When to Use This Skill
8
9	Always load this skill when:
10
11	### Research Questions
12	- User asks "what is X", "explain X", "research X", "investigate X"
13	- User wants to understand a concept, technology, or topic in depth
14	- The question requires current, comprehensive information from multiple sources
15	- A single web search would be insufficient to answer properly
16
17	### Content Generation (Pre-research)
18	- Creating presentations (PPT/slides)
19	- Creating frontend designs or UI mockups
20	- Writing articles, reports, or documentation
21	- Producing videos or multimedia content
22	- Any content that requires real-world information, examples, or current data
23
24	## Core Principle
25
26	Never generate content based solely on general knowledge. The quality of your output directly depends on the quality and quantity of research conducted beforehand. A single search query is NEVER enough.
27
28	## Research Methodology
29
30	### Phase 1: Broad Exploration
31
32	Start with broad searches to understand the landscape:
33
34	1. Initial Survey: Search for the main topic to understand the overall context
35	2. Identify Dimensions: From initial results, identify key subtopics, themes, angles, or aspects that need deeper exploration
36	3. Map the Territory: Note different perspectives, stakeholders, or viewpoints that exist
37
38	Example:
39	```
40	Topic: "AI in healthcare"
41	Initial searches:
42	- "AI healthcare applications 2024"
43	- "artificial intelligence medical diagnosis"
44	- "healthcare AI market trends"
45
46	Identified dimensions:
47	- Diagnostic AI (radiology, pathology)
48	- Treatment recommendation systems
49	- Administrative automation
50	- Patient monitoring
51	- Regulatory landscape
52	- Ethical considerations
53	```
54
55	### Phase 2: Deep Dive
56
57	For each important dimension identified, conduct targeted research:
58
59	1. Specific Queries: Search with precise keywords for each subtopic
60	2. Multiple Phrasings: Try different keyword combinations and phrasings
61	3. Fetch Full Content: Use `web_fetch` to read important sources in full, not just snippets
62	4. Follow References: When sources mention other important resources, search for those too
63
64	Example:
65	```
66	Dimension: "Diagnostic AI in radiology"
67	Targeted searches:
68	- "AI radiology FDA approved systems"
69	- "chest X-ray AI detection accuracy"
70	- "radiology AI clinical trials results"
71
72	Then fetch and read:
73	- Key research papers or summaries
74	- Industry reports
75	- Real-world case studies
76	```
77
78	### Phase 3: Diversity & Validation
79
80	Ensure comprehensive coverage by seeking diverse information types:
81
82	\| Information Type \| Purpose \| Example Searches \|
83	\|-----------------\|---------\|------------------\|
84	\| Facts & Data \| Concrete evidence \| "statistics", "data", "numbers", "market size" \|
85	\| Examples & Cases \| Real-world applications \| "case study", "example", "implementation" \|
86	\| Expert Opinions \| Authority perspectives \| "expert analysis", "interview", "commentary" \|
87	\| Trends & Predictions \| Future direction \| "trends 2024", "forecast", "future of" \|
88	\| Comparisons \| Context and alternatives \| "vs", "comparison", "alternatives" \|
89	\| Challenges & Criticisms \| Balanced view \| "challenges", "limitations", "criticism" \|
90
91	### Phase 4: Synthesis Check
92
93	Before proceeding to content generation, verify:
94
95	- [ ] Have I searched from at least 3-5 different angles?
96	- [ ] Have I fetched and read the most important sources in full?
97	- [ ] Do I have concrete data, examples, and expert perspectives?
98	- [ ] Have I explored both positive aspects and challenges/limitations?
99	- [ ] Is my information current and from authoritative sources?
100
101	If any answer is NO, continue researching before generating content.
102
103	## Search Strategy Tips
104
105	### Effective Query Patterns
106
107	```
108	# Be specific with context
109	❌ "AI trends"
110	✅ "enterprise AI adoption trends 2024"
111
112	# Include authoritative source hints
113	"[topic] research paper"
114	"[topic] McKinsey report"
115	"[topic] industry analysis"
116
117	# Search for specific content types
118	"[topic] case study"
119	"[topic] statistics"
120	"[topic] expert interview"
121
122	# Use temporal qualifiers — always use the ACTUAL current year from <current_date>
123	"[topic] 2026" # ← replace with real current year, never hardcode a past year
124	"[topic] latest"
125	"[topic] recent developments"
126	```
127
128	### Temporal Awareness
129
130	Always check `<current_date>` in your context before forming ANY search query.
131
132	`<current_d

People who liked this also viewed

6 picks

Type