grasp SKILL.md skillA

grasp from saadshahd/moo.md is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add saadshahd/moo.md/grasp@git:20260906.e7fe02d

Pins git:20260906.e7fe02d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
saadshahd/moo.md
Path
hold/skills/grasp/SKILL.md
Versions recorded
1
Latest version
git:20260906.e7fe02d, committed Sep 6, 2026
Size
2,189 bytes
Repository stars
38
License
MIT

Build a walkthrough the user works through until they can pass a quiz on it. Use when the user needs to understand something deeply and be quizzed on it.

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

Read around the thing before reading it. Write with the clarity and flow of Martin Kleppmann: smooth transitions, callouts at key concepts and edge cases. One idea per section; cut what no quiz question needs, the skippable layer excepted. Where nothing in the thing or its history says why, write that the reason is not recorded. Never guess one.

Four sections, in this order.

**Background** — what the reader must already hold: deep context marked skippable, then the slice the thing touches. For a change, the world as it was before it. How the job queue works at all is the skippable layer; the retry branch this change edits is the slice.

**Intuition** — the goal and the core idea before the thing itself. Toy data — three rows and one duplicate, not the production table — and a few drawn diagrams, never ASCII, reused through the walkthrough.

**Walkthrough** — the thing itself, literate: prose that carries its key passages, in conceptual order, never source order. The write that sets the flag, then the read that trusts it, then the test that pins the order, whatever the files sort to; the claim, then the evidence, then the exception, whatever a paper's sections do.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add saadshahd/moo.md/grasp@sha256:9a2646e3cbe820de

The line at the top of this page pins the label git:20260906.e7fe02d, 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_xlp65apwmvn6udwd.svg)](https://markdownregistry.com/a/art_xlp65apwmvn6udwd)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 6, 2026.

versioncommittedcommitsizeaudit
git:20260906.e7fe02d latest2026-09-06 e7fe02d 2,189 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 (2189 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

saadshahd/moo.md · 38 stars · license MIT · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xlp65apwmvn6udwd
GET https://markdownregistry.com/api/v1/resolve?ref=saadshahd/moo.md/grasp
GET https://markdownregistry.com/api/v1/blob/9a2646e3cbe820dea485f5aa9fe9ada57312879a21c986312abcbef66651b84f

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 saadshahd/moo.md

moo-authoring SKILL.md skill
saadshahd/moo.md · .claude/skills/moo-authoring/SKILL.md · Use when adding or changing a skill, hook, or runtime file in this repo — including deciding which unit a new…
git:20260927.debc454 · audit A · 38 stars
CLAUDE.md CLAUDE.md file
saadshahd/moo.md · CLAUDE.md
git:20260925.d8db119 · audit A · 38 stars
land SKILL.md skill
saadshahd/moo.md · hold/skills/land/SKILL.md · Build a stepped deck an audience works through until one thing of it stays with them. Use when the user needs an…
git:20260906.e7fe02d · audit A · 38 stars
learn SKILL.md skill
saadshahd/moo.md · hold/skills/learn/SKILL.md · Help the user understand something well enough to explain it. Use when the user needs to understand something and it is…
git:20260906.e7fe02d · audit A · 38 stars
toy SKILL.md skill
saadshahd/moo.md · hold/skills/toy/SKILL.md · Build a world the human drives until how a thing behaves is intuitive. Use when the user needs to hold how something…
git:20260906.e7fe02d · audit A · 38 stars
anchor SKILL.md skill
saadshahd/moo.md · hope/skills/anchor/SKILL.md · Rewrite a rule so anyone applies it the same way. Use when a stated rule or claim takes the reader's judgment to apply.
git:20260927.d54c79c · audit A · 38 stars
clarify SKILL.md skill
saadshahd/moo.md · hope/skills/clarify/SKILL.md · Turn words with two readings into one confirmed ask. Use when the user's words admit two readings that would build…
git:20260927.d54c79c · audit A · 38 stars
compose SKILL.md skill
saadshahd/moo.md · hope/skills/compose/SKILL.md · Plan the skills an ask needs, invoke each as its condition arrives. Use when the ask has multiple aspects that…
git:20260927.d54c79c · audit A · 38 stars
consult SKILL.md skill
saadshahd/moo.md · hope/skills/consult/SKILL.md · Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice…
git:20260930.db9fe4c · audit A · 38 stars
deepen SKILL.md skill
saadshahd/moo.md · hope/skills/deepen/SKILL.md · Hold an ask to the bar a top professional in its field would set — a deeper ask, never a bigger one. Use when an ask is…
git:20261016.c6bfd23 · audit A · 38 stars
draft SKILL.md skill
saadshahd/moo.md · hope/skills/draft/SKILL.md · Build the thing the user can't specify, choices surfaced. Use when the user needs something to react to before they can…
git:20260927.d54c79c · audit A · 38 stars
elicit SKILL.md skill
saadshahd/moo.md · hope/skills/elicit/SKILL.md · Draw out what the user holds but can't say. Use when the user knows something they cannot yet express.
git:20260927.d54c79c · audit A · 38 stars

Every file in saadshahd/moo.md

Other files named grasp

grasp SKILL.md skill
jongwony/epistemic-protocols · katalepsis/skills/grasp/SKILL.md · Something in play — code, a document, a result — the user can't follow yet or nods along to unsure: they can then say…
git:20261019.f304853 · audit A · 173 stars
grasp SKILL.md skill
yuzc-001/grasp · skill/SKILL.md · Use when an agent needs the visible local Grasp browser runtime for multi-step web tasks or public-web extraction…
git:20260401.e14155d · audit A · 74 stars
grasp SKILL.md skill
renky1025/agent-skills · grasp/SKILL.md · 深度掌握任意主题:以十维认知框架跑完 7 阶段交互协议,产出知识地图、维度诊断矩阵和分阶段学习路线图。适用于快速吃透一个陌生领域、系统梳理已有知识、检测认知盲区或规划进阶路线。触发词:grasp、速通、拆解、吃透、掌握某个主题、学习路线图、…
git:20260925.32ce6c0 · audit A · 11 stars

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