Correct

Community

jtaroreh

correct

Structured repository hardening against agent mistakes. Classifies recurring defects and enforces the fix hierarchy where architecture and structural checks precede rules and prompts.

Overview

Publisher	jtaroreh
Repository	`agystack`
Skill name	`correct`
Stars	120
Forks	12
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

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 jtaroreh on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/jtaroreh/agystack/tree/main/skills/correct
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.

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/jtaroreh/agystack.git /tmp/agystack
mkdir -p .claude/skills
cp -r /tmp/agystack/skills/correct .claude/skills/correct

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Correct 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 Correct 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 Correct 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.

Correct

Harden repositories against recurring agent mistakes and systemic defects. When an agent makes an error, do not simply patch the immediate failure or add an ad-hoc instruction. Classify the defect and enforce structural defenses at the highest level of the fix hierarchy.

Mistake Classification

Group mistakes into distinct classes to identify appropriate structural countermeasures:

Constraint misunderstanding. The agent ignores instructions, misinterprets bounds, or violates system constraints.
Hallucinated APIs. The agent invents parameters, functions, flags, or tools that do not exist in the platform or runtime.
Fragile patterns. The agent uses brittle regex parsing, race-prone file operations, unstructured text extraction, or unvalidated assumptions.
Regressions. The agent breaks previously working tests, overwrites unrelated code, or reverts recent fixes.

Fix Hierarchy

When remediating an agent defect, apply solutions at the highest possible layer in the fix hierarchy. Architecture and structural checks precede rules and prompt instructions:

Architecture. Make illegal states unrepresentable. Enforce structural boundaries, capability restrictions, and invariants by construction.
Type checks. Statically typed schemas, discriminated unions, and compiler gates that fail immediately on invalid invocations.
Linter and automated tests. Deterministic static analysis, linters, pre-commit hooks, and behavioral unit tests that catch errors in automated loops.
Instructions and prompts. Guidelines and prompt instructions are the last line of defense, never the first.

Hardening Process

Follow these steps to remediate mistakes:

Reproduce the mistake with an automated test or deterministic reproduction script.
Classify the mistake into its category.
Determine the highest applicable layer in the fix hierarchy.
Implement the structural guard such as a typed interface, lint rule, or architectural boundary.
Verify that the failure is blocked before falling back to prompt prose.

Frequently asked questions

What does the Correct AI skill do?

Structured repository hardening against agent mistakes. Classifies recurring defects and enforces the fix hierarchy where architecture and structural checks precede rules and prompts.

Why use Correct on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jtaroreh/agystack/tree/main/skills/correct. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Correct?

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 Correct?

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

Is the Correct AI skill free?

Yes. It is published on GitHub by jtaroreh 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

Openclaw Debugging

openclaw

OrganizationPopular

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Openclaw Live Updater

openclaw

OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

Openclaw Pr Maintainer

openclaw

OrganizationPopular

Review, triage, repair, or land OpenClaw issues and pull requests with current-source evidence and the native maintainer workflow.

Openclaw Refactor Docs

openclaw

OrganizationPopular

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Correct

Mistake Classification

Fix Hierarchy

Hardening Process

Frequently asked questions

Related AI Skills

Set up your own AI workspace now