unbury skillA
unbury is agent-read markdown (skill) from randroids-dojo/skills: 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 languages,.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns 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
mdr add randroids-dojo/skills/unbury@git:20260917.84e0fe5mdr add randroids-dojo/skills/unbury@sha256:c07d9e5f21748f8cPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_hcciyaq67eqmujry)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260917.84e0fe5 latest | 2026-09-17 | 84e0fe5 | 13,772 B | A | view · diff |
| git:20260917.8eb004c | 2026-09-17 | 8eb004c | 9,277 B | A | view · diff |
| git:20260917.e2d3698 | 2026-09-17 | e2d3698 | 8,518 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13772 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
randroids-dojo/skills · 46 stars · license MIT · pushed 2026-09-21 · 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/c07d9e5f21748f8ccb63c855dcac04b5d7b5bc2290e8441106668c0d44c67c0d
Your agent 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.