Fix Provider logo

Fix Provider

OrganizationPopular
wrtnlabs
fix-provider

Fix Provider, Collector, Transformer compilation errors

Overview

Publisherwrtnlabs
Repositoryautobe
Skill namefix-provider
Stars
1.4K
Forks
156
Bundled files
Instructions only
LicenseAGPL-3.0
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 wrtnlabs on GitHub. Read the source before you install it.

Installation

Install the Fix Provider 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/wrtnlabs/autobe/tree/main/internals/template/realize/.claude/skills/fix-provider
  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/wrtnlabs/autobe.git /tmp/autobe
mkdir -p .claude/skills
cp -r /tmp/autobe/internals/template/realize/.claude/skills/fix-provider .claude/skills/fix-provider
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fix Provider 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 Fix Provider 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 Fix Provider 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.

Fix Provider Errors

Fix provider, collector, and transformer compilation errors according to code conventions.

FORBIDDEN

NEVER use:

  • as keyword (type assertion)
  • any type

Fix type issues by properly defining Collectors and Transformers.


Purpose

Fix compilation errors in provider files to ensure npm run build:main passes.

Workflow

┌─────────────────────────────────────┐
│  Step 1: Run Build                  │
│  npm run build:main                 │
└───────────────┬─────────────────────┘
                │
                ▼
┌─────────────────────────────────────┐
│  Step 2: Parse Provider Errors      │
│  - as any usage                     │
│  - Type mismatches                  │
│  - Missing imports                  │
└───────────────┬─────────────────────┘
                │
                ▼
┌─────────────────────────────────────┐
│  Step 3: Fix by Convention          │
│  - Create Collectors                │
│  - Create Transformers              │
│  - Remove type assertions           │
└───────────────┬─────────────────────┘
                │
                ▼
┌─────────────────────────────────────┐
│  Step 4: Re-run Build               │
│  Loop until 0 errors                │
└─────────────────────────────────────┘

Step 1: Run Build

bash
npm run build:main 2>&1 | head -100

Capture provider-related errors.


Step 2: Find Issues

bash
# Find as any usage
grep -rn "as any" src/providers/ --include="*.ts"

# Find any type
grep -rn ": any" src/providers/ --include="*.ts"

# Find type assertions
grep -rn " as " src/providers/ --include="*.ts" | grep -v "import"

Step 3: Fix by Convention

Create Collector (if missing)

typescript
// src/collectors/{Prefix}{Entity}Collector.ts
import { I{Prefix}{Entity} } from "@ORGANIZATION/PROJECT-api/lib/structures/I{Prefix}{Entity}";
import { Prisma } from "@prisma/sdk";
import { v4 } from "uuid";

export namespace {Prefix}{Entity}Collector {
  export function collect(props: {
    body: I{Prefix}{Entity}.ICreate;
  }): Prisma.{table_name}CreateInput {
    const id = v4();
    const now = new Date();

    return {
      id,
      field_name: props.body.field_name,
      optional_field: props.body.optional_field ?? null,
      parent: props.body.parent_id
        ? { connect: { id: props.body.parent_id } }
        : undefined,
      created_at: now,
      updated_at: now,
      deleted_at: null,
    };
  }
}

Create Transformer (if missing)

typescript
// src/transformers/{Prefix}{Entity}Transformer.ts
import { I{Prefix}{Entity} } from "@ORGANIZATION/PROJECT-api/lib/structures/I{Prefix}{Entity}";
import { {table_name} } from "@prisma/sdk";

export namespace {Prefix}{Entity}Transformer {
  export function transform(record: {table_name}): I{Prefix}{Entity} {
    return {
      id: record.id,
      name: record.name,
      status: record.status,
      created_at: record.created_at.toISOString(),
      updated_at: record.updated_at.toISOString(),
      deleted_at: record.deleted_at
        ? record.deleted_at.toISOString()
        : null,
    };
  }

  export function toSummary(record: {table_name}): I{Prefix}{Entity}.ISummary {
    return {
      id: record.id,
      name: record.name,
      status: record.status,
      created_at: record.created_at.toISOString(),
    };
  }

  export function transformMany(records: {table_name}[]): I{Prefix}{Entity}[] {
    return records.map(transform);
  }

  export function toSummaryList(records: {table_name}[]): I{Prefix}{Entity}.ISummary[] {
    return records.map(toSummary);
  }
}

Fix POST Provider

typescript
// Before
const createData: any = { ... };
return { id: created.id as string & tags.Format<"uuid">, ... };

// After
import { {Prefix}{Entity}Collector } from "../collectors/{Prefix}{Entity}Collector";
import { {Prefix}{Entity}Transformer } from "../transformers/{Prefix}{Entity}Transformer";

export async function post{Prefix}{Entity}(props: {
  body: I{Prefix}{Entity}.ICreate;
}): Promise<I{Prefix}{Entity}> {
  const data = {Prefix}{Entity}Collector.collect({ body: props.body });
  const created = await MyGlobal.prisma.{table}.create({ data });
  return {Prefix}{Entity}Transformer.transform(created);
}

Fix GET Provider

typescript
// Before
return {
  id: record.id as string & tags.Format<"uuid">,
  ...
};

// After
import { {Prefix}{Entity}Transformer } from "../transformers/{Prefix}{Entity}Transformer";

export async function get{Prefix}{Entity}(props: { id: string }): Promise<I{Prefix}{Entity}> {
  const record = await MyGlobal.prisma.{table}.findUnique({ where: { id: props.id } });
  if (!record) throw new HttpException("Not found", 404);
  return {Prefix}{Entity}Transformer.transform(record);
}

Step 4: Verify

bash
npm run build:main

Repeat Steps 2-4 until no provider errors.


Common Fixes

Error PatternFix
as anyCreate proper Collector/Transformer
Type assertionUse Transformer for conversion
Missing importAdd import statement
Null referenceAdd null check before transform

Exit Condition

  • npm run build:main completes with no errors
  • No as any in providers
  • No type assertions in providers
  • All providers use Collector + Transformer

Frequently asked questions

What does the Fix Provider AI skill do?

Fix Provider, Collector, Transformer compilation errors

Why use Fix Provider on TypingMind?

Because you install it once and use it with any model. Fix Provider 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 Fix Provider in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wrtnlabs/autobe/tree/main/internals/template/realize/.claude/skills/fix-provider. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Fix Provider?

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 Fix Provider?

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

Is the Fix Provider AI skill free?

Yes. It is published on GitHub by wrtnlabs under the AGPL-3.0 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 👇