Migrate Agent Skill

Name: Migrate
Author: pricklywiggles

Use this skill to bring a project's stack-it artifacts from an older layout to the current one: move the generated stack reference out of…

Install this skill Read the source first Free Written by pricklywiggles

Context cost: 21.1k tokensestimated from the bundle, loaded when it triggers
Bundle: 59 files · 92.8 kB14 scripts among them — read before you run
Licence: not declarednone named by its author
Last change: —no release on file
Servers it uses: Noneruns standalone

What it does

Use this skill to bring a project's stack-it artifacts from an older layout to the current one: move the generated stack reference out of CLAUDE.md into the two-file reference (`docs/stack.md`, the small file every agent loads, and `docs/stack-notes.md`, the one they open on demand), add the one-line `AGENTS.md` pointer that every coding agent reads, leave CLAUDE.md as a thin `@AGENTS.md` bridge, and stamp the lockfile with the current `format`. It restructures files and pointers.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

documentation

Filed under

Learning & Documentation

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md25.9 kB · preview

--- name: migrate ---

6# Migrate

8Bring a project's stack-it artifacts from the layout an older version wrote to the layout the current one expects. This skill **restructures**: it moves generated text out of files it no longer belongs in, creates the pointer files agents read, and stamps the lockfile with the current format. It never generates or refreshes stack content. The most it ever writes is the old CLAUDE.md text moved into docs/stack-notes.md, inside the markers or below them when that file already exists, plus a one-line stub in either docs file where nothing moved. document-stack owns the content; this skill owns the shape.

10It runs two ways: on its own when a user asks, and from document-stack when that skill detects a project behind the current format.

12## Step 1: Detect the format

14**Ownership comes first, before any signal is read.** docs/stack.md and docs/stack-notes.md are stack-it's only if each is a regular file whose **first line starts with** > Generated by stack-it document-stack, format N. Match on that prefix alone: the sentence after it changed between versions, so a whole-line comparison would read every older file as somebody else's. A symlink at either path, or a first line that doesn't start that way, is not ours: stop there, show the user what is in it, and ask before touching anything. The order matters. A lockfile with no format key sitting beside a hand-written docs/stack.md reads as a format 1 project, and acting on that signal would start a migration across the very file the ownership rule exists to protect.

16Once both docs files are ours or absent, read every signal, then take the highest. Don't stop at the first one you find.

18- docs/stack.md and docs/stack-notes.md: the N on the header line of each owned file.

19- .claude/stack-it/stack.yaml: its top-level format key. A lockfile with no key reads as 1.

20- CLAUDE.md: a  marker reads as 1. Read CLAUDE.md from disk, since Claude Code strips HTML comments from loaded context and the marker won't be visible in a CLAUDE.md you already have in context. The start marker alone is enough to read the signal; removing the block still needs the full pair (see **Marker integrity**). A marker inside a fenced code block is not a signal, the same as in **Marker integrity**.

22No signal at all means nothing has been written yet, so there's nothing to migrate.

24The current format is **2**. If **any** signal reads higher than 2, stop and write nothing: a newer stack-it wrote this project, so tell the user to upgrade the plugin rather than downgrade their files. A newer decide-stack can stamp format: 3 on the lockfile while docs/stack.md still says 2, which is why the highest signal wins and the first hit doesn't. Otherwise the project's format is the highest signal you read.

This is a preview of SKILL.md. Download or install the skill to get the whole thing.

In the file

SKILL.md4,233 words

Files59

Licencenot declared

Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈350

always loaded

The name and description, so the model knows the skill exists and when to reach for it.

20,750

on trigger

The instruction body and 58 supporting files, read only when the skill fires.

10.5%

of a 200k window

Ten skills this size would not fit in the window together.

050k100k150k200k context window

21.1k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for

Writes filesnot declared

Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

If this is not it

7661 other skills in Learning & Documentation

What is in the bundle

59 files, 92.8 kB on disk. Mostly text — the instructions the model reads — with 14 scripts in it that your client would run only if the instructions tell it to.

SKILL.md25.9 kB
evals/evals.json24.7 kB
evals/fixtures/already-current/AGENTS.md0.4 kB
evals/fixtures/already-current/CLAUDE.md0.1 kB
evals/fixtures/already-current/pyproject.toml0.4 kB
evals/fixtures/already-current/README.md0.6 kB
evals/fixtures/v1-block-only/CLAUDE.md0.3 kB
evals/fixtures/v1-block-only/pyproject.toml0.4 kB
evals/fixtures/v1-block-only/README.md0.5 kB
evals/fixtures/v1-broken-markers/CLAUDE.md0.6 kB
evals/fixtures/v1-invalid-lockfile/CLAUDE.md0.6 kB
evals/fixtures/v1-no-lockfile/CLAUDE.md1.2 kB
evals/fixtures/v1-no-lockfile/pyproject.toml0.4 kB
evals/fixtures/v1-no-lockfile/README.md0.6 kB
evals/fixtures/v1-unstamped-no-block/pyproject.toml0.4 kB
evals/fixtures/v1-unstamped-no-block/README.md0.2 kB
evals/fixtures/v1-with-lockfile/CLAUDE.md0.6 kB
evals/fixtures/v1-with-lockfile/pyproject.toml0.4 kB
evals/fixtures/v1-with-lockfile/README.md0.5 kB
evals/fixtures/v2-leftover-block/AGENTS.md0.4 kB
evals/fixtures/v2-leftover-block/CLAUDE.md0.5 kB
evals/fixtures/v2-notes-missing/AGENTS.md0.4 kB
evals/fixtures/v2-notes-missing/CLAUDE.md0.1 kB
evals/fixtures/v2-notes-missing/pyproject.toml0.4 kB
evals/fixtures/v2-notes-missing/README.md0.6 kB
evals/fixtures/v2-stack-missing/AGENTS.md0.4 kB
evals/fixtures/v2-stack-missing/CLAUDE.md0.1 kB
evals/fixtures/v2-stack-missing/pyproject.toml0.4 kB
evals/fixtures/v2-stack-missing/README.md0.6 kB
evals/fixtures/already-current/app/main.py0.8 kB
evals/fixtures/already-current/docs/stack.md1.5 kB
evals/fixtures/already-current/docs/stack-notes.md1.4 kB
evals/fixtures/already-current/tests/test_app.py0.4 kB
evals/fixtures/v1-block-only/app/main.py0.8 kB
evals/fixtures/v1-block-only/tests/test_app.py0.4 kB
evals/fixtures/v1-no-lockfile/app/main.py0.8 kB
evals/fixtures/v1-no-lockfile/tests/test_app.py0.4 kB
evals/fixtures/v1-unstamped-no-block/app/main.py0.8 kB
evals/fixtures/v1-unstamped-no-block/tests/test_app.py0.4 kB
evals/fixtures/v1-with-lockfile/app/main.py0.8 kB
evals/fixtures/v1-with-lockfile/tests/test_app.py0.4 kB
evals/fixtures/v2-leftover-block/docs/stack.md1.3 kB
evals/fixtures/v2-leftover-block/docs/stack-notes.md1.3 kB
evals/fixtures/v2-notes-missing/app/main.py0.8 kB
evals/fixtures/v2-notes-missing/docs/stack.md1.5 kB
evals/fixtures/v2-notes-missing/tests/test_app.py0.4 kB
evals/fixtures/v2-stack-missing/app/main.py0.8 kB
evals/fixtures/v2-stack-missing/docs/stack-notes.md1.4 kB
evals/fixtures/v2-stack-missing/tests/test_app.py0.4 kB
evals/fixtures/already-current/.claude/stack-it/stack.yaml1.4 kB
evals/fixtures/v1-block-only/.claude/stack-it/stack.yaml1.4 kB
evals/fixtures/v1-broken-markers/.claude/stack-it/stack.yaml1.4 kB
evals/fixtures/v1-invalid-lockfile/.claude/stack-it/stack.yaml0.7 kB
evals/fixtures/v1-unstamped-no-block/.claude/stack-it/stack.yaml1.4 kB
evals/fixtures/v1-with-lockfile/.claude/stack-it/stack.yaml1.4 kB
evals/fixtures/v2-leftover-block/.claude/stack-it/stack.yaml1.4 kB
evals/fixtures/v2-notes-missing/.claude/stack-it/stack.yaml1.4 kB
evals/fixtures/v2-stack-missing/.claude/stack-it/stack.yaml1.4 kB
evals/fixtures/v2-stamped-lockfile-only/.claude/stack-it/stack.yaml1.4 kB

What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 14 scripts beside the text, so the bundle is 59 files you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Migrate · 21.1k tokens when loaded · macOS, Linux
mkdir -p .claude/skills && t=$(mktemp -d) &&
  curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/pricklywiggles-migrate/bundle.tar.gz &&
  tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/migrate" ] &&
  { [ ! -e .claude/skills/migrate ] || { mv .claude/skills/migrate "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } &&
  mv "$t/migrate" .claude/skills/ && echo "Installed .claude/skills/migrate"

On Windows, or any OS with Node 20+

npx mcprush@latest skill add pricklywiggles/migrate

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/migrate/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/pricklywiggles-migrate/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/migrate" ] && { [ ! -e ~/.claude/skills/migrate ] || { mv ~/.claude/skills/migrate "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/migrate" ~/.claude/skills/ && echo "Installed ~/.claude/skills/migrate" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/migrate/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/

Claude DesktopCustomize › Skills

ChatGPTSkills › Create › Upload

Cursor.cursor/skills/

VS Code.github/skills/

Codex CLI.agents/skills/

Gemini CLI.gemini/skills/

Grok Build.grok/skills/

Microsoft CopilotSkills › Upload a skill

PerplexityComputer › Skills › Upload a skill

DeepSeek Harness.dsh/skills/

Zed.agents/skills/

Devin Desktop.devin/skills/

Windsurf (legacy).windsurf/skills/

OpenAI Agents SDKInstructions or sandbox Skills

HTTP / APIa request parameter

This release

Versionnot versioned

Publishedno release date on file

PriceFree

Referencepricklywiggles/migrate

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

pricklywiggles

Publishes on mcprush.

0 servers listed15 skills listednot claimed

Profile

Publisher

Servers0

Claim this skill