Agent skill

Import Into

by babarot in babarot/gh-infra

A skill your agent uses when pulling live GitHub state back into existing gh-infra manifests with gh infra import --into, especially for write/patch/skip decisions, shared file sources…

MITAuto-check passed

Install Import Into

skills CLI
$ npx skills add babarot/gh-infra --skill import-into -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install babarot/gh-infra import-into --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/babarot/gh-infra.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/import-into .claude/skills/import-into && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
import-into
GitHub stars
136
Token cost
~746 tokens
SKILL.md length
350 words
Files
4 (incl. references)
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when pulling live GitHub state back into existing gh-infra manifests with gh infra import --into, especially for write/patch/skip decisions, shared file sources…

  • Works in 7 steps: Parse local manifests → Match target repositories against… → Fetch live state from GitHub → …
  • Pulling live GitHub state back into existing gh-infra manifests with gh infra import --into
  • SKILL.md covers When To Use, Command, How It Works and File Write Modes, plus 5 more sections
  • Calls gh

What it does

Import Into is an agent skill from babarot/gh-infra. Use when pulling live GitHub state back into existing gh-infra manifests with gh infra import --into, especially for write/patch/skip decisions, shared file sources, template-backed files, and import safety rules.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/behavior.md`, `references/template-safety.md` and `references/write-modes.md`).

It works with GitHub. The repository describes itself as: Declarative GitHub infrastructure management via YAML. The licence is MIT.

When your agent uses it

  • Pulling live GitHub state back into existing gh-infra manifests with gh infra import --into
  • Especially for write/patch/skip decisions
  • Shared file sources
  • Template-backed files

Example prompts

  • “/import-into”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Parse local manifests
  2. Match target repositories against Repository, RepositorySet, and FileSet
  3. Fetch live state from GitHub
  4. Diff local vs remote
  5. Show plan output
  6. For file changes, open the interactive diff viewer
  7. Write approved local changes

What it can do on your machine

Read from SKILL.md and the folder at commit 7e6443a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Import Into loads about 746 tokens when it runs, and up to ~1.3k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 350 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~746
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from babarot/gh-infra at commit 7e6443a, republished under its MIT licence (© babarot). 350 words, ~746 tokens.

Download SKILL.mdSave it as .claude/skills/import-into/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
import-into
description
Use when pulling live GitHub state back into existing gh-infra manifests with `gh infra import --into`, especially for write/patch/skip decisions, shared file sources, template-backed files, and import safety rules.

Import Into

Use this skill for gh infra import --into=....

This workflow is different from normal import, plan, and apply:

  • it updates local manifests from live GitHub state
  • it may rewrite YAML, local source files, or manifest patches
  • it has file-level write modes and skip safety rules

When To Use

Use this skill when the user wants to:

  • pull GitHub state back into existing manifests
  • reconcile drift from GitHub UI into local YAML
  • decide between write, patch, and skip
  • understand why a file was skipped during import
  • update shared templates safely after repository-side drift

Command

bash
gh infra import <owner/repo> [owner/repo ...] --into=<path>

<path> may be a file or a directory of manifests.

How It Works

  1. Parse local manifests
  2. Match target repositories against Repository, RepositorySet, and FileSet
  3. Fetch live state from GitHub
  4. Diff local vs remote
  5. Show plan output
  6. For file changes, open the interactive diff viewer
  7. Write approved local changes

File Write Modes

  • write: update the normal local target
  • patch: store the drift under patches:
  • skip: ignore for this run

Typical defaults:

  • inline content: write
  • single-use local source: write
  • shared local source: patch
  • existing patches: entry: patch
  • many create_only entries: skip

Safety Rules

There are two skip modes:

  • default skip: safe enough to import, but skipped by default
  • hard skip: cannot be written back safely

Hard-skip cases include:

  • github:// sources
  • template-backed files whose placeholders cannot be reverse-mapped safely
Show full SKILL.md (122 more words)Show less

Template-Backed Files

For templates such as <% .Repo.Name %> and <% .Repo.FullName %>, gh-infra compares:

  1. rendered local template
  2. remote GitHub file

It then tries to reconstruct updated local template source while preserving placeholders.

Use write only when you want to update the underlying shared source. Use patch when drift should stay repository-specific.

What Gets Updated

  • repository settings: patched into YAML
  • inline file content: written back into the manifest
  • local source: ./... files: written back to the source file
  • shared local source files: often better stored as patches

What Does Not Get Imported

  • secrets: GitHub does not return secret values
  • github:// sources: no local write target
  • template-backed files that cannot be reverse-mapped safely

© babarot, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/import-into of babarot/gh-infra.

  • SKILL.md
  • references/behavior.md
  • references/template-safety.md
  • references/write-modes.md

Open the folder on GitHubat commit 7e6443a

Compare with similar skills

Import Into next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Import Into compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Import Into this skillbabarot/gh-infra136—~746Automated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated yesterday
    Research & ScienceAuto-check: notes

More from babarot/gh-infra

  • File Manifest

    babarot/gh-infra

    Complete YAML schema reference for File and FileSet resources.

    136 GitHub stars~768 tokensUpdated 10 days ago
    Auto-check passed
  • Gh Infra

    babarot/gh-infra

    Overview of gh-infra and command workflow (import, validate, plan, apply).

    136 GitHub stars~1.1k tokensUpdated 10 days ago
    Auto-check passed
  • Repository Manifest

    babarot/gh-infra

    Complete YAML schema reference for Repository and RepositorySet resources.

    136 GitHub stars~914 tokensUpdated 10 days ago
    Auto-check passed
  • Vhs Demo

    babarot/gh-infra

    A skill your agent uses when running demo recordings, diagnosing recording failures, or regenerating GIFs from existing MP4s.

    136 GitHub stars~1.2k tokensUpdated 10 days ago
    Auto-check passed
  • Vhs Tape Authoring

    babarot/gh-infra

    A skill your agent uses when creating new VHS demo tapes or editing existing ones.

    136 GitHub stars~1.4k tokensUpdated 10 days ago
    Auto-check passed
  • CI CD

    babarot/gh-infra

    CI/CD integration patterns for gh-infra: auto-apply on merge, scheduled drift detection, self-managed vs central-management layouts, and authentication setup for GitHub Actions workflows.

    136 GitHub stars~482 tokensUpdated 10 days ago
    Auto-check passed

Works with

Questions about Import Into

What does Import Into do?

A skill your agent uses when pulling live GitHub state back into existing gh-infra manifests with gh infra import --into, especially for write/patch/skip decisions, shared file sources…. Import Into is an agent skill from babarot/gh-infra. Use when pulling live GitHub state back into existing gh-infra manifests with gh infra import --into, especially for write/patch/skip decisions, shared file sources, template-backed files, and import safety rules.

When should I use Import Into?

Import Into fits situations like: pulling live GitHub state back into existing gh-infra manifests with gh infra import --into; especially for write/patch/skip decisions; shared file sources; template-backed files.

How do I install Import Into in Claude Code?

Run `npx skills add babarot/gh-infra --skill import-into -a claude-code`. Or copy the skill folder (skills/import-into in babarot/gh-infra) into .claude/skills/import-into in your project. Claude Code loads it when a task matches its description.

How do I install Import Into in Codex?

Run `npx skills add babarot/gh-infra --skill import-into -a codex`. Or copy the skill folder (skills/import-into in babarot/gh-infra) into .agents/skills/import-into in your project. Codex loads it when a task matches its description.

Can I use Import Into in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add babarot/gh-infra --skill import-into -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/import-into, .gemini/skills/import-into, .github/skills/import-into and .opencode/skills/import-into in your project.

What does Import Into need to run?

Going by SKILL.md and its folder, Import Into needs the command-line tools its instructions call (gh).

Does Import Into access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Import Into safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Import Into use?

Import Into is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Import Into use?

About 746 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 598 tokens, read only when the agent opens those files.

What are the alternatives to Import Into?

Skills that share tags, products or a category with Import Into: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Diagnosing Superpowers Sessions (obra/superpowers, 297k stars), Greploop (onyx-dot-app/onyx, 32k stars) and GitHub Deep Research (bytedance/deer-flow, 84k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Import Into?

babarot (a GitHub user) maintains it in babarot/gh-infra, which has 136 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 29, 2026.

Source: babarot/gh-infra on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.