Skip to content
Back to skills

Research Engine

ASecurity

Autonomous research pipeline — topic to structured documents with HTML/PDF output. Proven at HEL (28 docs, 91K words) and OOPS (9 docs, 20K words) scale.

  • 69 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added May 30, 2026
ai-agentsgobashnodegit

Security analysis

A100/100

Scanned May 30, 2026

npx -y skills add Tibsfox/gsd-skill-creator --skill research-engine --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Research Engine?

Add the live security badge to your README. It updates with every re-scan.

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

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: research-engine
description: Autonomous research pipeline — topic to structured documents with HTML/PDF output. Proven at HEL (28 docs, 91K words) and OOPS (9 docs, 20K words) scale.
version: 1.0.0
type: skill
category: research
status: stable
origin: tibsfox
modified: false
first_seen: 2026-03-31
first_path: .claude/skills/research-engine/SKILL.md
superseded_by: null
---
# Research Engine

Activates when user requests deep research, investigation, or analysis of a topic that will produce multiple structured documents.

## Pipeline

```
TOPIC → DECOMPOSE → PARALLEL RESEARCH → AGGREGATE → STRUCTURE → BUILD → PUBLISH
```

### Stage 1: Decompose
Break the research topic into 4-12 investigation tracks. Each track becomes one document.

### Stage 2: Parallel Research
Launch research agents (2-6 in parallel) with specific investigation briefs. Use `run_in_background: true` for independence.

### Stage 3: Aggregate
Collect findings. Check for contradictions. Identify cross-references.

### Stage 4: Structure
Organize into a numbered document series with:
- Index page (index.html)
- Individual research documents (research/NN-slug.md)
- Knowledge graph (knowledge-nodes.json)
- Retrospective (retrospective.md)

### Stage 5: Build
Convert markdown to HTML and PDF using pandoc + xelatex:
```bash
bash build.sh  # Uses template.tex and html-template.html
```

### Stage 6: Publish
Commit, tag, merge to main, push, create GitHub release, FTP sync to configured remote host.

## Quality Standards

- Minimum 1,500 words per document
- Every claim needs evidence or explicit reasoning
- Cross-references between documents
- Fact-check pass before final publish
- Three output formats: markdown (source), HTML (reading), PDF (sharing)

## Project Codes

Each research project gets a 3-4 letter code added to series.js:
- HEL (Helium Supply Chain)
- OOPS (Ecosystem Alignment)
- OPEN (Unsolved Problems)

## Build Infrastructure

Templates at the project level:
- `template.tex` — LaTeX template for branded PDFs
- `html-template.html` — Standalone HTML template
- `build.sh` — Automated pandoc build script

Attribution

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

Loading comments…