Add Feature logo

Add Feature

OrganizationPopular
wrtnlabs
add-feature

Implement new feature with self-testing loop until 100% pass

Overview

Publisherwrtnlabs
Repositoryautobe
Skill nameadd-feature
Stars
1.4K
Forks
156
Bundled files
3
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Add Feature 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/add-feature
  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/add-feature .claude/skills/add-feature
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Add Feature 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 Add Feature 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 Add Feature 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.

Add Feature

Implement a new feature and iterate until all tests pass (100% success rate).

FORBIDDEN

NEVER use:

  • as keyword (type assertion)
  • any type

Feature Description

$ARGUMENTS


Workflow Overview

┌─────────────────────────────────────┐
│  Phase 1: Implementation            │
│  - Controller                       │
│  - Provider                         │
│  - Collector/Transformer            │
│  - Interface                        │
└───────────────┬─────────────────────┘
                │
                ▼
┌─────────────────────────────────────┐
│  Phase 2: Test Design               │
│  - Happy path tests                 │
│  - Error case tests                 │
│  - Edge case tests                  │
└───────────────┬─────────────────────┘
                │
                ▼
┌─────────────────────────────────────┐
│  Phase 3: Test Loop                 │
│  while (pass_rate < 100%) {         │
│    run tests                        │
│    analyze failures                 │
│    fix code                         │
│  }                                  │
└───────────────┬─────────────────────┘
                │
                ▼
┌─────────────────────────────────────┐
│  Complete                           │
│  All tests pass!                    │
└─────────────────────────────────────┘

Phase 1: Implementation

See: flow-implement.md

  1. Analyze Requirements

    • Understand the feature from $ARGUMENTS
    • Identify affected entities
    • Determine API endpoints needed
  2. Create/Update Interface

    • Define DTOs (ICreate, IUpdate, ISummary, IRequest)
    • Add typia tags for validation
  3. Create/Update Collector

    • Transform ICreate → Prisma.CreateInput
  4. Create/Update Transformer

    • Transform Prisma record → Interface
  5. Create/Update Provider

    • Implement business logic
    • Use Collector for create operations
    • Use Transformer for responses
  6. Create/Update Controller

    • Define routes with TypedRoute
    • Add authentication decorators
    • Connect to Provider
  7. Verify Build

    bash
    npm run build:main

Phase 2: Test Design

See: flow-test-design.md

Design comprehensive test scenarios including:

Happy Path (Normal Cases)

  • ✅ Create entity successfully
  • ✅ Read entity successfully
  • ✅ Update entity successfully
  • ✅ Delete entity successfully
  • ✅ List entities with pagination

Error Cases

  • ❌ Create with missing required fields
  • ❌ Create with invalid field format
  • ❌ Read non-existent entity (404)
  • ❌ Update non-existent entity (404)
  • ❌ Delete non-existent entity (404)
  • ❌ Unauthorized access (401)
  • ❌ Forbidden action (403)

Edge Cases

  • ⚠️ Empty string input
  • ⚠️ Null values for optional fields
  • ⚠️ Maximum length strings
  • ⚠️ Minimum/maximum numeric values
  • ⚠️ Special characters in strings
  • ⚠️ Duplicate creation attempt
  • ⚠️ Concurrent modification
  • ⚠️ Parent entity doesn't exist
  • ⚠️ Circular reference attempt
  • ⚠️ Soft-deleted entity access

Phase 3: Test Loop

See: flow-test-loop.md

REPEAT:
  1. Build tests
     npm run build:test

  2. Run tests
     npm run test -- --include "{feature}"

  3. If all pass → DONE

  4. If failures:
     a. Analyze failure reason
     b. Determine if test code issue or business logic issue
     c. Fix the appropriate code
     d. Go to step 1

UNTIL: 100% pass rate

Exit Conditions

✅ Success Criteria:

  • npm run build:main passes
  • npm run build:test passes
  • npm run test passes with 100% success rate
  • All happy path tests pass
  • All error case tests pass
  • All edge case tests pass

❌ Failure (requires manual intervention):

  • Circular dependency detected
  • External service unavailable
  • Database schema change required
  • Requirements ambiguity

Output

When complete, provide:

markdown
## Feature Implementation Complete

### Summary
- Feature: {description}
- Files created/modified: X
- Test scenarios: Y
- Pass rate: 100%

### Files Changed
- src/api/structures/I{Entity}.ts
- src/controllers/{path}/{Controller}.ts
- src/providers/{provider}.ts
- src/collectors/{Collector}.ts
- src/transformers/{Transformer}.ts
- test/prepare/prepare_random_{entity}.ts
- test/generate/generate_random_{entity}.ts
- test/features/api/{entity}/*.ts

### Test Results
- Total: X tests
- Passed: X
- Failed: 0

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Add Feature AI skill do?

Implement new feature with self-testing loop until 100% pass

Why use Add Feature on TypingMind?

Because you install it once and use it with any model. Add Feature 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 Add Feature in TypingMind?

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

Which AI models can use Add Feature?

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 Add Feature?

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

Is the Add Feature 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 👇