Installable skillMIT

Haqq Content Workbench

Create, verify, and package Islamic-ethics content for discussion.

BY modbenderUPDATED Oct 28, 2026
INTENDED FOR✳Claude Code>_Codex◈OpenClaw↗CursorInstall in a listed agent.

instructions.md

---
name: haqq-content-workbench-55cc94946476
description: "Create, verify, and package Islamic-ethics content for discussion.
  Use when the user asks for: (1) summarizing long texts, (2) checking
  sources/claims, (3) producing multiple post variants to avoid duplication, (4)
  generating discussion questions, or (5) archiving ideas for later publishing."
---


# Haqq Content Workbench

## Overview
Produce accurate, discussion-ready content grounded in the user’s reference text while avoiding duplication and weak sourcing.

## Workflow (use what you need)

### 1) Summarize a long text
- Extract 5–10 key points.
- Preserve the author’s intent; do not add new claims.
- Output: **Summary + 3 key takeaways**.

### 2) Source/claim check
- List any claims that require a source.
- If you cannot verify, label: **"needs source"**.
- Never invent citations.

### 3) Create post variants (anti-duplicate)
- Produce 3 distinct variants with different structure:
  1) **Hook + 2 short paragraphs + question**
  2) **Bullet points + closing question**
  3) **Short story/analogy + lesson + question**
- Keep each variant under 120–160 words.

### 4) Generate discussion questions
- Provide 5–8 questions.
- Mix: reflective, critical, and practical questions.

### 5) Archive ideas for later publishing
- Store outputs in a compact format: **Title / Angle / Draft / Question / Tags**.

## Reference Texts
`references/al-amr-al-mutlaq.md` — The complete reference text (the absolute command) for quoting, summarizing, or formulating questions.

## Templates & Patterns
Use the templates in `references/templates.md` for consistent outputs.
COMPATIBILITY & REFERENCES

Platform guidance

Imported from the listed AgentSkill.sh category. Complete supplied package files and notices are retained. Required external tools and credentials are not installed. No bundled code was executed during import. Individual agent task behavior has not been tested.