question-forge SKILL.md skillA

question-forge from hraness/personal-monorepo-template is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hraness/personal-monorepo-template/question-forge@git:20260813.224f50f

Pins git:20260813.224f50f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hraness/personal-monorepo-template
Path
.agents/skills/question-forge/SKILL.md
Versions recorded
1
Latest version
git:20260813.224f50f, committed Aug 13, 2026
Size
4,800 bytes
Repository stars
4
License
MIT

Take a surface question and forge the question actually worth asking — diagnose what's broken in the asked question (smuggled answers, wrong level, false binary, self-protection), transform it, and return a better question WITHOUT answering it. Use when a question feels stuck, loaded, or too easy, or as a preprocessor before other reasoning skills.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Question Forge

Use this skill to reformulate a question rather than answer it. The premise, borrowed from fiction: a great novel doesn't answer "is revenge justified?" — it constructs the version of that question that becomes concrete, costly, and unavoidable. The illumination is in the formulation. Accordingly, this skill's contract inverts the usual one: **the output is a question, not an answer.**

## Purpose

Most questions arrive broken in predictable ways. Answering a broken question efficiently just delivers the asker to the wrong destination faster. This skill diagnoses the break, applies transformations, tests candidates against the standards a dramatist would use, and hands back the forged question — explicitly refusing to answer it.

## Procedure

### 1. Dispatch check (mandatory, first)

If the question is genuinely operational — factual, technical, well-posed ("why is the build failing?", "what's the capital gains rate?") — say the question is fine and answer it normally. Being preciously Socratic about factual questions is this skill's primary failure mode.

### 2. Diagnose the asked question

Common breaks:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hraness/personal-monorepo-template/question-forge@sha256:c2d3cd46337046a0

The line at the top of this page pins the label git:20260813.224f50f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ubabcautqzrpq43h.svg)](https://markdownregistry.com/a/art_ubabcautqzrpq43h)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Aug 13, 2026.

versioncommittedcommitsizeaudit
git:20260813.224f50f latest2026-08-13 224f50f 4,800 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4800 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

hraness/personal-monorepo-template · 4 stars · license MIT · pushed 2026-10-13 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ubabcautqzrpq43h
GET https://markdownregistry.com/api/v1/resolve?ref=hraness/personal-monorepo-template/question-forge
GET https://markdownregistry.com/api/v1/blob/c2d3cd46337046a08e5efd6a747bf8c488ab331723ec951b491f67f99aa3e045

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from hraness/personal-monorepo-template

AGENTS.md@.agents/skills AGENTS.md file
hraness/personal-monorepo-template · .agents/skills/AGENTS.md
git:20260829.1e16cdd · audit A · 4 stars
AGENTS.md@.agents/skills/assumption-audit AGENTS.md file
hraness/personal-monorepo-template · .agents/skills/assumption-audit/AGENTS.md
git:20260813.224f50f · audit A · 4 stars
assumption-audit SKILL.md skill
hraness/personal-monorepo-template · .agents/skills/assumption-audit/SKILL.md · Extract every assumption hidden in a claim, plan, or belief, classify each by load-bearingness and testability, and…
git:20260813.224f50f · audit A · 4 stars
AGENTS.md@.agents/skills/decision-matrix AGENTS.md file
hraness/personal-monorepo-template · .agents/skills/decision-matrix/AGENTS.md
git:20260813.224f50f · audit A · 4 stars
decision-matrix SKILL.md skill
hraness/personal-monorepo-template · .agents/skills/decision-matrix/SKILL.md · Structure a choice between concrete options: elicit the real criteria and their weights, score each option honestly…
git:20260813.224f50f · audit A · 4 stars
AGENTS.md@.agents/skills/direct-setup AGENTS.md file
hraness/personal-monorepo-template · .agents/skills/direct-setup/AGENTS.md
git:20260813.2328887 · audit A · 4 stars
direct-setup SKILL.md skill
hraness/personal-monorepo-template · .agents/skills/direct-setup/SKILL.md · Add or revise a Direct deterministic development composition around product-owned ports, strict JSON worlds, scenarios…
git:20260813.2328887 · audit A · 4 stars
AGENTS.md@.agents/skills/direct-verify AGENTS.md file
hraness/personal-monorepo-template · .agents/skills/direct-verify/AGENTS.md
git:20260813.2328887 · audit A · 4 stars
direct-verify SKILL.md skill
hraness/personal-monorepo-template · .agents/skills/direct-verify/SKILL.md · Verify an existing Direct composition, including strict activation, deterministic settlement, semantic scenario…
git:20260813.2328887 · audit A · 4 stars
AGENTS.md@.agents/skills/first-principles-thinking AGENTS.md file
hraness/personal-monorepo-template · .agents/skills/first-principles-thinking/AGENTS.md
git:20260813.224f50f · audit A · 4 stars
first-principles-thinking SKILL.md skill
hraness/personal-monorepo-template · .agents/skills/first-principles-thinking/SKILL.md · Use first-principles thinking as a tool for any question, design problem, strategy, decision, or explanation where the…
git:20260813.224f50f · audit A · 4 stars
AGENTS.md@.agents/skills/percolate-kb AGENTS.md file
hraness/personal-monorepo-template · .agents/skills/percolate-kb/AGENTS.md
git:20260928.c17f23d · audit A · 4 stars

Every file in hraness/personal-monorepo-template

Browse by kind, by grade A, or by owner.