Validate Addon logo

Validate Addon

Community
jmagly
validate-addon

Validate an entire AIWG addon package for completeness and release readiness

Overview

Publisherjmagly
Repositoryaiwg
Skill namevalidate-addon
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 Validate Addon 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/aiwg-dev/skills/validate-addon
  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/aiwg-dev/skills/validate-addon .claude/skills/validate-addon
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Validate Addon 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 Validate Addon 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 Validate Addon 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.

Validate Addon

You check an entire AIWG addon directory for completeness and release readiness, then produce a detailed structured report covering manifest integrity, artifact completeness, placement violations, and any blocking issues.

Triggers

  • "validate this addon" → check the addon in the current or named directory
  • "is this addon ready to release" → run full release readiness check
  • "check the addon" → validate the named addon
  • "pre-release check on my addon" → run validate-addon
  • "addon readiness report" → full validation with report output
  • "validate addon at " → validate the addon at the given path

Trigger Patterns Reference

PatternExampleAction
Current directory"validate this addon"Validate addon at cwd
Named addon"check the aiwg-dev addon"Find addon by name and validate
Path-specific"validate addon at agentic/code/addons/my-addon"Validate at given path
Release gate"is this addon ready to release"Full validation, block on any FAIL
Quick check"any issues with this addon"Run validation, summarize findings

Process

  1. Locate the addon:

    • If path given: use it
    • If name given: find agentic/code/addons/<name>/manifest.json
    • If current directory: look for manifest.json in cwd or walk up to nearest addon root
  2. Read and validate manifest.json:

    • File exists at addon root
    • Valid JSON (parseable)
    • Required fields present: id, type, name, version, description
    • type equals "addon"
    • version follows CalVer format (YYYY.M.PATCH, no leading zeros)
    • core field present (boolean)
    • autoInstall field present (boolean)
    • If devOnly: true: confirm this is intentional (it excludes from aiwg use all)
  3. Check README.md:

    • File exists at addon root
    • Non-empty content
  4. Validate each skill listed in manifest: For each entry in manifest.json skills array:

    • skills/<name>/SKILL.md exists
    • description: frontmatter present
    • # Title section present
    • ## Behavior or ## Process section present
    • Collect any missing skills (in manifest but no SKILL.md) and orphaned skills (SKILL.md exists but not in manifest)
  5. Validate each agent listed in manifest: For each entry in manifest.json agents array:

    • Agent .md file exists
    • YAML frontmatter present
    • name:, description:, model:, tools: fields in frontmatter
    • Collect missing and orphaned agents
  6. Validate each rule listed in manifest: For each entry in manifest.json rules array:

    • rules/<name>.md exists
    • RULES-INDEX.md exists in rules/
    • Rule name appears in RULES-INDEX.md
  7. Check for placement violations:

    • Search corresponding provider directories (.claude/skills/, .github/agents/, etc.) for any files whose names match this addon's artifacts
    • For each match: verify a source file exists in agentic/code/
    • Flag any deployed files with no source as violations
  8. Check for .aiwg/ references in addon artifacts:

    • Search all SKILL.md, agent .md, and command .md files under the addon for @.aiwg/ path references
    • Flag any found: these only resolve inside the AIWG repository itself
  9. Compile report:

    Addon Validation: <addon-name> v<version>
    Path: agentic/code/addons/<name>/
    
    Manifest:
      PASS  manifest.json present and valid JSON
      PASS  required fields: id, type, name, version, description
      PASS  version format: 2026.4.0 (CalVer, no leading zeros)
      PASS  devOnly: true (excluded from `aiwg use all` — intentional)
    
    README:
      PASS  README.md present
    
    Skills (3 listed):
      PASS  validate-component: SKILL.md present, frontmatter complete
      PASS  validate-addon: SKILL.md present, frontmatter complete
      FAIL  dev-doctor: listed in manifest but SKILL.md missing
    
    Agents (0 listed):
      PASS  no agents declared
    
    Rules (4 listed):
      PASS  skill-placement: rule file present, in RULES-INDEX.md
      PASS  no-circular-skill-calls: rule file present, in RULES-INDEX.md
      PASS  component-completeness: rule file present, in RULES-INDEX.md
      FAIL  addon-boundaries: not found in RULES-INDEX.md
    
    Placement violations:
      PASS  no orphaned deployed files found
    
    .aiwg/ references:
      PASS  no .aiwg/ path references in deployable artifacts
    
    Result: FAIL — 2 blocking issues
    
    Blocking issues:
      1. skills/dev-doctor/SKILL.md missing — create the file or remove from manifest
      2. addon-boundaries not in rules/RULES-INDEX.md — add an entry
    
    Warnings:
      none
  10. Report result: Surface the structured report to the user. Highlight blocking issues in the summary line. For each failure, include the specific remediation step.

Examples

Example 1: Fully valid addon

User: "Is the aiwg-dev addon ready to release?"

Output:

Addon Validation: aiwg-dev v1.0.0
Path: agentic/code/addons/aiwg-dev/

Manifest:          PASS (all required fields, valid CalVer)
README:            PASS
Skills (3):        PASS (all present and complete)
Agents (0):        PASS
Rules (4):         PASS (all present and in RULES-INDEX.md)
Placement:         PASS (no violations)
.aiwg/ refs:       PASS

Result: PASS — addon is release-ready

Example 2: Addon with gaps found

User: "check the my-new-addon addon"

Output:

Addon Validation: my-new-addon v2026.4.0
Path: agentic/code/addons/my-new-addon/

Manifest:          PASS
README:            FAIL — README.md missing
Skills (2):
  PASS  my-skill: complete
  FAIL  other-skill: SKILL.md missing (listed in manifest but file not found)
Rules (1):         PASS
Placement:         WARN — .claude/skills/orphan-skill/ found with no agentic/code/ source

Result: FAIL — 2 blocking issues, 1 warning

Blocking issues:
  1. README.md missing — create at agentic/code/addons/my-new-addon/README.md
  2. skills/other-skill/SKILL.md missing — create the file or remove from manifest

Warnings:
  W1. .claude/skills/orphan-skill/ has no source in agentic/code/ — may be a placement violation
      See: agentic/code/addons/aiwg-dev/rules/skill-placement.md

References

  • @$AIWG_ROOT/agentic/code/addons/aiwg-dev/rules/component-completeness.md — Completeness requirements per artifact type
  • @$AIWG_ROOT/agentic/code/addons/aiwg-dev/rules/skill-placement.md — Placement violation detection
  • @$AIWG_ROOT/agentic/code/addons/aiwg-dev/rules/addon-boundaries.md — .aiwg/ reference detection
  • @$AIWG_ROOT/agentic/code/addons/aiwg-dev/skills/validate-component/SKILL.md — Per-component validation

Frequently asked questions

What does the Validate Addon AI skill do?

Validate an entire AIWG addon package for completeness and release readiness

Why use Validate Addon on TypingMind?

Because you install it once and use it with any model. Validate Addon 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 Validate Addon in TypingMind?

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

Which AI models can use Validate Addon?

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 Validate Addon?

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

Is the Validate Addon 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 👇