Skills Explorer Add Skills

migration

An agent skill by JuliusBrussee, from JuliusBrussee/caveman. Tags: configuration, database, deployment, migration.

What it does

Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add JuliusBrussee/caveman --skill migration

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/JuliusBrussee/caveman
cp -r caveman/skills/migration ~/.claude/skills/migration

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is documentation-only: it describes how to plan reversible migrations, but ships no executable scripts, network calls, or file-modifying logic. The main consideration is process safety around the actual migration work you pair with it, not the skill files themselves.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)`SKILL.md` and `agents/openai.yaml` contain only prose/configuration; there are no shell commands, code evaluation, or native scripts.
Network access0 (none)No URLs, download steps, API calls, or data exfiltration paths appear in the shipped files.
Filesystem reach0 (none)The skill does not read, write, or delete files; it only instructs the agent to plan changes safely.
Secrets & credentials0 (none)There is no request to access tokens, keys, passwords, `.env` files, or other credential stores.
Privilege & persistence0 (none)No sudo, service installation, global configuration, or shell/OS setting changes are present.
Instruction hijack surface0 (none)The files do not tell the agent to ignore instructions, hide actions, or follow remote content; they only set a migration-focused prompt.
Irreversible actions0 (none)The skill does not itself execute deployments, deletions, or other side effects; it only advises to stop before destructive contraction.
Transparency0 (none)Everything in the skill is human-readable markdown/YAML; there are no binaries, blobs, or generated artifacts.

Before installing

Rated 2026-10-16 by an automated review of 2 files from the skill's repository.

Source

Repository
JuliusBrussee/caveman (all skills from this repository)
Path
skills/migration/SKILL.md
Branch
main
Updated
2026-10-05