unbury SKILL.md skillA

unbury from randroids-dojo/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add randroids-dojo/skills/unbury@git:20261007.3aa27e4

Pins git:20261007.3aa27e4 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
randroids-dojo/skills
Path
plugins/unbury/SKILL.md
Versions recorded
4
Latest version
git:20261007.3aa27e4, committed Oct 7, 2026
First version recorded
Sep 17, 2026
Size
14,109 bytes
Repository stars
46
License
MIT

Rewrite AI-generated or AI-influenced technical writing so a competent engineer builds the correct mental model as fast as possible, without losing technical accuracy. Use when the user asks to de-slop, humanize, tighten, or clarify a PR description, code review comment, design doc, architecture explanation, issue, Slack update, release notes, proposal, or AI research summary, or says text sounds AI-written or buries the point. Do not use for visual or UI slop, for translating between…

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

# Unbury

Turn exhaustive AI-style explanation into edited engineering communication. The reader is a technically competent engineer who does not yet know the situation. Every edit serves one measure:

**How quickly does that reader build the correct mental model?**

This is not "sound less like AI" and not "make it casual." The output should read like a strong engineer explaining something clearly to another strong engineer. Technical accuracy, necessary qualifications, and the artifact's native format all survive the edit.

The target is minimum cognitive load, not minimum word count. The rewrite may be much shorter, about the same length, or occasionally longer; all three are fine if the reader reaches the correct model faster and every decision-critical fact survives. One added sentence can lower the load when it saves the reader from inferring a consequence they needed. Do not use a compression percentage as a target.

## Workflow
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add randroids-dojo/skills/unbury@sha256:a21fcbbdc3f0ab86

The line at the top of this page pins the label git:20261007.3aa27e4, 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_hcciyaq67eqmujry.svg)](https://markdownregistry.com/a/art_hcciyaq67eqmujry)

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

Versions

The registry has recorded 4 versions of this file, between Sep 17, 2026 and Oct 7, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20261007.3aa27e4 latest2026-10-07 3aa27e4 14,109 BA view · diff
git:20260917.84e0fe52026-09-17 84e0fe5 13,772 BA view · diff
git:20260917.8eb004c2026-09-17 8eb004c 9,277 BA view · diff
git:20260917.e2d36982026-09-17 e2d3698 8,518 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 (14109 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

randroids-dojo/skills · 46 stars · license MIT · pushed 2026-11-09 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hcciyaq67eqmujry
GET https://markdownregistry.com/api/v1/resolve?ref=randroids-dojo/skills/unbury
GET https://markdownregistry.com/api/v1/blob/a21fcbbdc3f0ab86db6c5b206052c60fa0befa9231f86cace0dc236965bfae53

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 randroids-dojo/skills

AGENTS.md AGENTS.md file
randroids-dojo/skills · AGENTS.md
git:20261007.5fcf66a · audit A · 46 stars
CLAUDE.md CLAUDE.md file
randroids-dojo/skills · CLAUDE.md
git:20260223.c1c7c81 · audit B · 46 stars
blender-production SKILL.md skill
randroids-dojo/skills · plugins/blender-production/SKILL.md · Build, refine, inspect, render, and visually verify Blender projects using Python and available MCP tools. Use when…
git:20260913.122b73f · audit A · 46 stars
decision SKILL.md skill
randroids-dojo/skills · plugins/decision/SKILL.md · Structure a decision as one or two multiple-choice questions at a time, with tradeoffs and a recommendation for every…
git:20260830.a009b78 · audit A · 46 stars
funclimb SKILL.md skill
randroids-dojo/skills · plugins/funclimb/SKILL.md · Run bounded, evidence-grounded FunClimb improvement experiments on a game project, preserving its identity and using an…
git:20261108.68a21eb · audit A · 46 stars
godot SKILL.md skill
randroids-dojo/skills · plugins/godot/SKILL.md · Develop, test, automate, export, and deploy Godot 4.x games. Use when working with Godot projects, GDScript, GdUnit4…
git:20260830.a009b78 · audit A · 46 stars
present SKILL.md skill
randroids-dojo/skills · plugins/present/SKILL.md · Plan, build, or revise clear presentations, pitches, explanatory documents, and interactive HTML arguments using…
git:20261007.9a40861 · audit A · 46 stars
randroid SKILL.md skill
randroids-dojo/skills · plugins/randroid/SKILL.md · Route requests to the focused Randroid development workflows and explain which capability to use. Use when the user…
git:20260912.65128a6 · audit A · 46 stars
randroid-address-pr-comments SKILL.md skill
randroids-dojo/skills · plugins/randroid/skills/randroid-address-pr-comments/SKILL.md · Address actionable pull-request review feedback end to end by locating the PR, resolving each current comment…
git:20260830.a009b78 · audit A · 46 stars
randroid-clean-slop SKILL.md skill
randroids-dojo/skills · plugins/randroid/skills/randroid-clean-slop/SKILL.md · Diagnose generic visual and copy patterns in existing interfaces, games, and 3D assets through actual screenshots or…
git:20260912.65128a6 · audit A · 46 stars
randroid-game-feel SKILL.md skill
randroids-dojo/skills · plugins/randroid/skills/randroid-game-feel/SKILL.md · Improve a game's core interaction, responsiveness, feedback, and playable iteration. Use when a game feels like an app…
git:20260912.65128a6 · audit A · 46 stars
randroid-loop SKILL.md skill
randroids-dojo/skills · plugins/randroid/skills/randroid-loop/SKILL.md · Run a bounded research or implementation loop with persistent Dots task tracking and an explicitly selected git…
git:20260830.a009b78 · audit A · 46 stars

Every file in randroids-dojo/skills

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