loft SKILL.md skillA

loft from yeachan-heo/oh-my-claudecode is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yeachan-heo/oh-my-claudecode/loft@git:20260912.85ca3bc

Pins git:20260912.85ca3bc in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yeachan-heo/oh-my-claudecode
Path
skills/loft/SKILL.md
Versions recorded
2
Latest version
git:20260912.85ca3bc, committed Sep 12, 2026
First version recorded
Sep 5, 2026
Size
5,515 bytes
Repository stars
40,624
License
MIT

Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks. Use when a design question stalls in words, when a navigator map carries a loft ticket, or when a spec discussion reaches "we would have to see 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

# Loft

**Cut no steel until the shape is fair.** Shipwrights loft the hull's lines full-scale and fair them before a single plate is cut. Loft applies the same order to design questions: when words have run out — two plausible answers, neither falsifiable by talk — build a cheap runnable artifact, let the captain react to it, and fold that reaction into the decision.

**The role contract.** The crew builds the artifact; the captain's only job is to react — and that reaction **is** the decision. The artifact is an instrument for seeing, never a head start on the deliverable.

## When to loft

- a design question stalls in prose: repeatedly rephrased, still not settleable ("how should the path page look", "does this state model feel right")
- a navigator map carries a `loft` ticket
- a spec discussion reaches "we would have to see it first"

Do **not** loft when:

- the question is answerable from repo evidence or by asking the captain (that is interviewing, not lofting)
- the destination itself is unclear (that is fog — `/oh-my-claudecode:ask-navigator`)
- the answer already lives in an ADR (do not re-loft settled decisions)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yeachan-heo/oh-my-claudecode/loft@sha256:60f98c8e1db2d5fb

The line at the top of this page pins the label git:20260912.85ca3bc, 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_uoakvtncfzjpojn4.svg)](https://markdownregistry.com/a/art_uoakvtncfzjpojn4)

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

Versions

The registry has recorded 2 versions of this file, between Sep 5, 2026 and Sep 12, 2026, about one every 7 days.

versioncommittedcommitsizeaudit
git:20260912.85ca3bc latest2026-09-12 85ca3bc 5,515 BA view · diff
git:20260905.4e8d9cc2026-09-05 4e8d9cc 5,513 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 (5515 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

yeachan-heo/oh-my-claudecode · 40,624 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uoakvtncfzjpojn4
GET https://markdownregistry.com/api/v1/resolve?ref=yeachan-heo/oh-my-claudecode/loft
GET https://markdownregistry.com/api/v1/blob/60f98c8e1db2d5fba1d1288cd2e0c7a048517c3a914e4226ec9c86ff2fd27357

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 yeachan-heo/oh-my-claudecode

CLAUDE.md@.github CLAUDE.md file
yeachan-heo/oh-my-claudecode · .github/CLAUDE.md
git:20261103.0564555 · audit A · 40,624 stars
AGENTS.md AGENTS.md file
yeachan-heo/oh-my-claudecode · AGENTS.md
git:20261013.dba5ef3 · audit A · 40,624 stars
CLAUDE.md CLAUDE.md file
yeachan-heo/oh-my-claudecode · CLAUDE.md
git:20261103.0564555 · audit A · 40,624 stars
AGENTS.md@docs AGENTS.md file
yeachan-heo/oh-my-claudecode · docs/AGENTS.md
git:20260311.fc226e7 · audit A · 40,624 stars
CLAUDE.md@docs CLAUDE.md file
yeachan-heo/oh-my-claudecode · docs/CLAUDE.md
git:20261103.0564555 · audit A · 40,624 stars
AGENTS.md@skills AGENTS.md file
yeachan-heo/oh-my-claudecode · skills/AGENTS.md
git:20261011.3d50d68 · audit A · 40,624 stars
agent-doc-discipline SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/agent-doc-discipline/SKILL.md · Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule…
git:20261009.3e432c2 · audit A · 40,624 stars
ai-slop-cleaner SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/ai-slop-cleaner/SKILL.md · Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
git:20260507.8690a21 · audit A · 40,624 stars
architecture-survey SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/architecture-survey/SKILL.md · Periodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules…
git:20260913.629d16f · audit A · 40,624 stars
ask-navigator SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/ask-navigator/SKILL.md · Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision…
git:20261011.3d50d68 · audit A · 40,624 stars
ask SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/ask/SKILL.md · Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, Cursor, or Muse via `omc ask`, with…
git:20261013.859b146 · audit A · 40,624 stars
autopilot SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/autopilot/SKILL.md · Full autonomous execution from idea to working code
git:20261101.4d728ec · audit A · 40,624 stars

Every file in yeachan-heo/oh-my-claudecode

Other files named loft

loft SKILL.md skill
naimkatiman/continuous-improvement · third-party/oh-my-claudecode/skills/loft/SKILL.md · Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway…
git:20260906.bface5c · audit A · 9 stars

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