Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Auto Research

ASecurity

Premier research workflow for systematic investigation, synthesis, and verification. Use for literature reviews, competitive analysis, deep dives, market research, or any task requiring structured research with source attribution.

8 stars
0 votes
0 copies
1 views
Added 9/6/2026
researchgogitapi

Works with

api

Security Analysis

A100/100

Scanned 9/6/2026

Install to Claude Code

$npx -y skills add v1truv1us/ai-eng-system --skill auto-research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Auto Research?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Auto Research
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/v1truv1us-auto-research/badge)](https://www.skillsdirectory.com/skills/v1truv1us-auto-research)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: auto-research
description: Premier research workflow for systematic investigation, synthesis, and verification. Use for literature reviews, competitive analysis, deep dives, market research, or any task requiring structured research with source attribution.
---

# Auto Research

Systematic research orchestration for pi. Replaces Claude CoWork research workflows with a native pi skill set.

## Workflow

```
Clarify → Investigate → Synthesize → Validate → Output
```

### 1. Clarify Scope

Before researching, confirm with the user:
- What questions need answering?
- What are the boundaries?
- What depth is needed?
- What format for output?

### 2. Investigate

Use the best tool for the source type:

| Source Type | Tool |
|-------------|------|
| Web docs, APIs, current info | `intelli_research` from intelli-search skill |
| Specific URLs | `web_fetch` from pi-browse |
| Local files | `read` |
| Multiple local files | Batch `read` or `rg` |
| GitHub repos | Clone and `read` |

Always use `intelli_research` with a `focusPrompt`. Without it, extractions are generic.

### 3. Synthesize

Organize findings:
- Group by theme or question
- Identify patterns, consensus, debates
- Note contradictions between sources
- Distinguish fact from interpretation

### 4. Validate

- Cross-reference key claims across multiple sources
- Assess source reliability (peer-reviewed > official > journalism > blog > forum)
- Flag uncertainty rather than guessing
- Mark speculative claims as such

### 5. Output

Choose the right output format based on depth needed.

## Output Formats

### Research Brief (Quick)

```markdown
## Research Brief: [Topic]
**Date**: [Date] | **Confidence**: [Level]

### Key Findings
1. [Finding with source]
2. [Finding with source]

### Sources
- [Source](url) - [Brief description]

### Next Steps
- [Follow-up recommendations]
```

### Comprehensive Report (Deep)

```markdown
## [Title]

### Executive Summary
[2-3 paragraph overview]

### Background
[Context and importance]

### Methodology
[How research was conducted]

### Findings
[Detailed with inline citations]

### Analysis
[Interpretation and synthesis]

### Limitations
[Acknowledged constraints]

### References
[Full citations]
```

### Verification Report (Fact-Check)

```markdown
## Verification: [Claim]

**Verdict**: [VERIFIED / PARTIALLY VERIFIED / UNVERIFIED / CONTRADICTED]

### Evidence
| Source | Claim | Confidence |
|--------|-------|------------|
| [Name] | [Quote] | H/M/L |

**Confidence**: [H/M/L with reasoning]
```

## Source Markers

Use inline markers to indicate source type:
- `[A]` Academic / peer-reviewed
- `[O]` Official / government / primary
- `[N]` News / journalism
- `[I]` Industry / technical docs
- `[E]` Expert opinion / blog

## Knowledge Types

Label every factual claim:
- `FACT`: Verifiable with direct source
- `LIKELY`: Consistent with multiple sources
- `SPECULATIVE`: Based on reasoning, not direct evidence
- `UNKNOWN`: Beyond current knowledge, stated clearly

## File Organization

For multi-session research, use this structure:

```
/Research/
└── [Project]/
    ├── 01-sources/      # PDFs, notes, source materials
    ├── 02-analysis/     # Analysis documents
    ├── 03-synthesis/    # Synthesized findings
    └── 04-output/       # Final reports
```

Naming conventions:
- Sources: `YYYY-MM-DD_[topic]_source.[ext]`
- Analysis: `YYYY-MM-DD_[topic]_analysis.md`
- Outputs: `[topic]_report_[version]_[date].md`

## Research Task Templates

### Literature Review
> Analyze all documents in this folder as a literature review on [topic]. For each source, extract: main thesis, methodology, key findings, and how it connects to other sources. Identify consensus and debates.

### Competitive Analysis
> Research [topic/competitor] using all available sources. Create a competitive analysis covering: market position, key offerings, strengths, weaknesses, and differentiation. Include source citations.

### Fact Verification
> Verify the following claims: [list claims]. For each, provide: verification status, supporting evidence, source quality assessment, and confidence level.

### Deep Research
> Conduct comprehensive research on [topic]. Include: executive summary, key findings with source attribution, analysis and implications, limitations and uncertainties, recommendations for further research. Cite all sources with URLs.

Attribution

v1truv1usv1truv1us
View sourceMore from v1truv1us →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report co...

494352 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

813271 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end p...

494351 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →