Setup Validate logo

Setup Validate

Community
jmagly
setup-validate

Validate a `setup.aiwg.io/v1` SetupManifest file against the schema and run cons

Overview

Publisherjmagly
Repositoryaiwg
Skill namesetup-validate
Stars
225
Forks
34
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jmagly on GitHub. Read the source before you install it.

Installation

Install the Setup Validate AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/agentic-installer/skills/setup-validate
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jmagly/aiwg.git /tmp/aiwg
mkdir -p .claude/skills
cp -r /tmp/aiwg/agentic/code/addons/agentic-installer/skills/setup-validate .claude/skills/setup-validate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Setup Validate in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Setup Validate on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Setup Validate is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

setup-validate

Validate a setup.aiwg.io/v1 SetupManifest file against the schema and run consistency checks.

Trigger Phrases

  • "validate setup manifest"
  • "check setup.manifest.yaml"
  • "aiwg setup-validate [manifest]"
  • "lint installer manifest"
  • "verify my setup manifest"

Parameters

manifest (positional, optional)

Path to the setup.manifest.yaml. Default: ./setup.manifest.yaml.

--schema (optional)

Path to schema file. Default: auto-located from AIWG installation.

--strict (optional)

Fail on warnings in addition to errors.

--fix (optional)

Reserved for future safe autofixes. The current CLI validates and reports only.

Validation Checks

Schema Validation

  • apiVersion must be setup.aiwg.io/v1
  • kind must be SetupManifest
  • Required fields present: metadata.name, spec.platforms, spec.steps
  • All step types are one of: script, detect, ask, verify, agentic, platform-route, chain, os-config
  • Param types are one of: string, path, boolean, integer, choice
  • metadata.install_type must be one of: user, developer, ci (if present)
  • metadata.execution_mode must be deterministic or provider-orchestrated (if present)

Reference Checks

  • Every script: path exists relative to the manifest directory
  • Every chain: manifest path exists
  • Every platform-route route value resolves to an existing script
  • depends_on step IDs all exist in the manifest
  • Recovery triggers list references valid step IDs
  • os-config steps: config_id must reference a valid entry in spec.os_config

Developer Manifest Checks (when metadata.install_type: developer)

These checks apply only to manifests with install_type: developer:

Errors
  • os-config steps must reference a valid config_id in the spec.os_config block
  • interactive_required: true params must not have a default value — a default defeats the purpose of requiring interactive input
  • Each platform declared in spec.platforms must have at least one platform-specific step or os_config entry
Warnings (unless --strict, then errors)
  • Developer manifest with no os_config block: warn unless metadata.description explicitly states why no OS configuration is needed
  • os_config entries with requires_relogin: true but no corresponding os-config step — the entry is declared but never applied
  • os_config entries with interactive: true but no user-facing explanation in description

Consistency Checks (warnings unless --strict)

  • Steps without id — suggest auto-generated IDs
  • Sequential steps that logically depend on prior steps but have no depends_on
  • Params declared but never referenced in scripts or when conditions
  • Prerequisites with no install_hint (hard to debug without one)
  • Verify expressions that look like they'd always pass (e.g., true)
  • interactive_required: true params that also have required: true — the required flag is redundant when interactive_required is set

Script Safety Checks

  • Scripts that exist: read first 5 lines to confirm they source lib scripts
  • Warn if a script template is used directly without customization (template placeholder text detected)

Agentic Step Audit

  • Warn on any type: agentic step in a deterministic manifest — print a reminder that agentic steps are exception handling only
  • Do not warn merely because a provider-orchestrated manifest uses agentic steps
  • Error if type: agentic step has no instruction field

Output Format

Validating: setup.dev.manifest.yaml

  Schema:        ✓ Valid (setup.aiwg.io/v1 / SetupManifest)
  Install type:  developer
  Metadata:      ✓ name=myapp-dev version=1.0.0
  Platform:      ✓ linux (ubuntu, debian), macos
  Params:        ✓ 4 params (INSTALL_DIR required, LOCAL_DOMAIN interactive_required, SSH_EMAIL interactive_required, IDE interactive_required)
  Prerequisites: ✓ 2 checked (git >=2.30, docker)
  OS Config:     ✓ 3 entries (docker-group [linux, requires_relogin], inotify-watches [linux], xcode-cli-tools [macos, interactive])

  Steps (7):
    ✓ clone             script      installer/scripts/clone.sh [exists]
    ✓ setup-git-config  script      installer/scripts/dev/setup-git-config.sh [exists]
    ✓ setup-ssh-key     script      installer/scripts/dev/setup-ssh-key.sh [exists]
    ✓ apply-docker-group  os-config  config_id=docker-group [valid]
    ✓ apply-inotify     os-config   config_id=inotify-watches [valid]
    ✓ configure-dev     script      installer/scripts/dev/configure-dev.sh [exists]
    ✓ verify-dev        script      installer/scripts/dev/verify-dev.sh [exists]

  Recovery (1):
    ✓ full-reset  script [exists]

  Warnings (1):
    ⚠ xcode-cli-tools os_config entry declared but no os-config step applies it

Result: VALID (1 warning)

Error Example

  Errors (2):
    ✗ Step 'apply-docker-group': config_id 'docker-group' not found in os_config block
    ✗ Param 'LOCAL_DOMAIN': interactive_required=true but has a default value — remove the default

Result: INVALID — fix errors before running

Auto-fix (--fix)

--fix is reserved for future safe autofixes. The current agent-facing CLI validates and reports only; it does not mutate manifests.

References

  • Schema: agentic/code/addons/agentic-installer/schemas/v1/setup-manifest.schema.json
  • Run skill: agentic/code/addons/agentic-installer/skills/setup-run/SKILL.md
  • Generate skill: agentic/code/addons/agentic-installer/skills/setup-generate/SKILL.md

Frequently asked questions

What does the Setup Validate AI skill do?

Validate a `setup.aiwg.io/v1` SetupManifest file against the schema and run cons

Why use Setup Validate on TypingMind?

Because you install it once and use it with any model. Setup Validate is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Setup Validate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/agentic-installer/skills/setup-validate. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Setup Validate?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Setup Validate?

As many as you like. As long as a model supports skills, you can use Setup Validate with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Setup Validate AI skill free?

Yes. It is published on GitHub by jmagly under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇