formalize-problem SKILL.md skillA

formalize-problem from sebastianelvis/reaper is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sebastianelvis/reaper/formalize-problem@git:20260912.5e86435

Pins git:20260912.5e86435 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
sebastianelvis/reaper
Path
skills/formalize-problem/SKILL.md
Versions recorded
5
Latest version
git:20260912.5e86435, committed Sep 12, 2026
First version recorded
Apr 12, 2026
Size
4,252 bytes
Repository stars
10
License
Apache-2.0

This skill defines a research question as testable hypotheses. You use it to specify model assumptions, properties, and success or failure conditions.

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

# Formalize Problem

You must read and apply the [language rules](../reaper/references/language.md) before you write any output.

## Usage

You invoke this skill by name with a quoted research goal. Slash-command hosts use `/formalize-problem "<goal>"`.

```
formalize-problem "determine if the security proof in Section 4 holds under asynchrony"
```

## Instructions

### 1. Read Inputs

You read these inputs:

- `reaper-workspace/notes/clarified-goal.md` supplies the goal, scope, assumptions, and success criteria.
- `reaper-workspace/notes/paper-summary.md` supplies the paper's claims, if this file exists.
- The argument supplies the initial goal. You prefer the refined goal in `clarified-goal.md`.

You read Key Prior Results and Gaps Identified in `reaper-workspace/notes/literature.md`. You read individual paper entries when hypothesis checks need them. Without a paper summary, you use the literature review as the main technical input. You read it in more detail in this case.

### 2. Define the Core Question

You state the exact claim with its property and adversary model.

### 3. Specify Model Assumptions
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sebastianelvis/reaper/formalize-problem@sha256:28f910efc543e400

The line at the top of this page pins the label git:20260912.5e86435, 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_aeew3tbesvpvtkvi.svg)](https://markdownregistry.com/a/art_aeew3tbesvpvtkvi)

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

Versions

The registry has recorded 5 versions of this file, between Apr 12, 2026 and Sep 12, 2026, about one every 38 days.

versioncommittedcommitsizeaudit
git:20260912.5e86435 latest2026-09-12 5e86435 4,252 BA view · diff
git:20260502.5bc84e82026-05-02 5bc84e8 6,457 BA view · diff
git:20260418.f3979682026-04-18 f397968 7,337 BA view · diff
git:20260418.b61c0522026-04-18 b61c052 7,351 BA view · diff
git:20260412.0de6bfa2026-04-12 0de6bfa 6,231 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 (4252 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

sebastianelvis/reaper · 10 stars · license Apache-2.0 · pushed 2026-09-28 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_aeew3tbesvpvtkvi
GET https://markdownregistry.com/api/v1/resolve?ref=sebastianelvis/reaper/formalize-problem
GET https://markdownregistry.com/api/v1/blob/28f910efc543e400aab840ae2efbb5d91ea2ae5248bc8c489f3f6632479fea80

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 sebastianelvis/reaper

CLAUDE.md CLAUDE.md file
sebastianelvis/reaper · CLAUDE.md
git:20260912.18b334b · audit A · 10 stars
analyze-paper SKILL.md skill
sebastianelvis/reaper · skills/analyze-paper/SKILL.md · This skill extracts claims, models, proofs, and limitations from a research paper. You use it to analyze or summarize…
git:20260912.5e86435 · audit A · 10 stars
brainstorm SKILL.md skill
sebastianelvis/reaper · skills/brainstorm/SKILL.md · This skill creates and ranks research hypotheses from current findings. You use it after formalization or between…
git:20260912.5e86435 · audit A · 10 stars
clarify-goal SKILL.md skill
sebastianelvis/reaper · skills/clarify-goal/SKILL.md · This skill asks questions to define a research goal. You use it when the scope, assumptions, or success criteria are…
git:20260928.53b1c6a · audit A · 10 stars
critique SKILL.md skill
sebastianelvis/reaper · skills/critique/SKILL.md · This skill reviews research findings with user feedback, Codex, or self-review. You use it to check results or direct…
git:20260912.18b334b · audit A · 10 stars
investigate SKILL.md skill
sebastianelvis/reaper · skills/investigate/SKILL.md · This skill tests hypotheses with proofs, counterexamples, and analysis. You use it to verify, prove, or refute research…
git:20260912.18b334b · audit A · 10 stars
reaper SKILL.md skill
sebastianelvis/reaper · skills/reaper/SKILL.md · This skill runs the full Reaper research pipeline. You use it with a research goal and an optional paper.
git:20260928.6123299 · audit A · 10 stars
review-literature SKILL.md skill
sebastianelvis/reaper · skills/review-literature/SKILL.md · This skill searches and reads related academic work. You use it to find prior results, related papers, or competing…
git:20260928.53b1c6a · audit A · 10 stars
search-paper SKILL.md skill
sebastianelvis/reaper · skills/search-paper/SKILL.md · This skill finds papers, downloads PDFs, traces citations, and identifies publication venues. You use it for academic…
git:20260912.5e86435 · audit A · 10 stars
write-paper SKILL.md skill
sebastianelvis/reaper · skills/write-paper/SKILL.md · This skill writes a formal LaTeX research paper from investigation results. You use it to present findings with…
git:20260928.53b1c6a · audit A · 10 stars

Every file in sebastianelvis/reaper

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