Skip to content
Back to skills

Qra

ASecurity

Extract Question-Reasoning-Answer pairs from text. Use --context for domain-focused extraction. Validates answers are grounded in source text.

  • 666 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 2, 2026
ai-agentspythonbashsecuritydocumentation

Works with

  • cli

Security analysis

A100/100

Scanned September 2, 2026

npx -y skills add majiayu000/claude-skill-registry --skill qra --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Qra?

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

Security grade badge for Qra
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majiayu000-qra/badge)](https://www.skillsdirectory.com/skills/majiayu000-qra)

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: qra
description: >
  Extract Question-Reasoning-Answer pairs from text.
  Use --context for domain-focused extraction.
  Validates answers are grounded in source text.
allowed-tools: Bash, Read
triggers:
  - extract QRA
  - extract Q&A
  - extract knowledge
  - create Q&A pairs
  - knowledge extraction
  - generate questions from
metadata:
  short-description: Extract grounded Q&A pairs from text
---

# QRA Skill

Extract Question-Reasoning-Answer pairs from text and store in memory.

## Happy Path

```bash
# Extract from text file
./run.sh --file document.md --scope research

# With domain focus (recommended)
./run.sh --file notes.txt --scope project --context "security expert"

# Preview before storing
./run.sh --file transcript.txt --dry-run

# From stdin
cat meeting_notes.txt | ./run.sh --scope meetings
```

## Parameters

| Flag | Description |
|------|-------------|
| `--file` | Text or markdown file |
| `--text` | Raw text content |
| `--scope` | Memory scope (default: research) |
| `--context` | Domain focus, e.g. "ML researcher" |
| `--dry-run` | Preview without storing |
| `--json` | JSON output |

## What It Does

1. **Split** text into logical sections
2. **Extract** Q&A pairs via LLM (parallel batch)
3. **Validate** answers are grounded in source
4. **Store** to memory via `memory-agent learn`

## When to Use

- Text content (not PDFs - use `distill` for PDFs)
- Meeting transcripts
- Code documentation
- Notes and summaries
- Any plain text you want to remember

## Examples

```bash
# Meeting transcript
./run.sh --file meeting.txt --scope team --context "project manager"

# Code documentation
./run.sh --file README.md --scope code --context "Python developer"

# From clipboard/pipe
pbpaste | ./run.sh --scope notes --dry-run
```

## Environment Variables (Optional Tuning)

| Variable | Default | Description |
|----------|---------|-------------|
| `QRA_CONCURRENCY` | 6 | Parallel LLM requests |
| `QRA_GROUNDING_THRESH` | 0.6 | Grounding similarity threshold |
| `QRA_NO_GROUNDING` | - | Set to 1 to skip validation |

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…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.