Research
- 124 installs
- 17.2k repo stars
- Updated August 1, 2026
- danielmiessler/personal_ai_infrastructure
Run structured deep-research loops from PAI to gather sources, compare claims, and synthesize briefs when exploring markets, threats, technologies, or decisions before committing build scope.
About
The research skill from danielmiessler/personal_ai_infrastructure equips Personal AI Infrastructure to execute multi-step investigation workflows—finding sources, cross-checking claims, and producing decision-ready briefs during early discovery and ongoing learning.
- Deep source gathering
- Structured synthesis
- Evidence comparison
- Discovery briefs
- PAI research loops
Research by the numbers
- 124 all-time installs (skills.sh)
- Ranked #3,781 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/danielmiessler/personal_ai_infrastructure --skill researchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 124 |
|---|---|
| repo stars | ★ 17.2k |
| Last updated | August 1, 2026 |
| Repository | danielmiessler/personal_ai_infrastructure ↗ |
What it does
Run structured deep-research loops from PAI to gather sources, compare claims, and synthesize briefs when exploring markets, threats, technologies, or decisions before committing build scope.
Files
Research Skill
Modes
| Mode | Depth | Sources | Time |
|---|---|---|---|
| Quick | Surface scan | 2-3 sources | <1 min |
| Standard | Balanced coverage | 4-6 sources | 2-5 min |
| Extensive | Broad sweep | 8-12 sources | 5-10 min |
| Deep | Exhaustive | 15+ sources | 10-30 min |
Workflow
1. Decompose the research question into 3-10 sub-queries 2. Search using web search across multiple angles 3. Extract key findings, data points, and insights 4. Synthesize into a structured report 5. Verify claims with cross-referencing
Output Format
## Research: [Topic]
### Key Findings
- [Finding 1 with source]
- [Finding 2 with source]
### Analysis
[Synthesis of findings]
### Sources
- [Source 1](url)
- [Source 2](url)Rules
- Always cite sources
- Flag conflicting information
- Distinguish facts from opinions
- Note confidence levels
- Prefer primary sources over secondary
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10