Create Formal Verification Skill logo

Create Formal Verification Skill

Community
jtaroreh
create-formal-verification-skill

Generate and apply formal specification models (TLA+, Alloy, Dafny, or state-machine model checkers) strictly for high-consequence concurrency, distributed consensus, complex state machines, and parsers.

Overview

Publisherjtaroreh
Repositoryagystack
Skill namecreate-formal-verification-skill
Stars
120
Forks
12
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 jtaroreh on GitHub. Read the source before you install it.

Installation

Install the Create Formal Verification Skill 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/jtaroreh/agystack/tree/main/skills/create-formal-verification-skill
  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/jtaroreh/agystack.git /tmp/agystack
mkdir -p .claude/skills
cp -r /tmp/agystack/skills/create-formal-verification-skill .claude/skills/create-formal-verification-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Formal Verification Skill 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 Create Formal Verification Skill 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 Create Formal Verification Skill 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.

Create Formal Verification Skill

Generate project-local formal verification specifications and model checkers for high-consequence algorithms. Formal methods verify invariants mathematically across entire state spaces. They carry high authoring and maintenance costs, so strict gating is mandatory.

Applicability Gating Criteria

Before authoring a formal specification or model checking harness, evaluate the target system against the gating criteria.

Strictly Reserved Targets

Formal verification is strictly reserved for these high-consequence domains:

  1. Concurrency protocols: Multi-threaded synchronization primitives, lockless data structures, and non-blocking algorithms where interleavings defy testing.
  2. Distributed consensus: Raft, Paxos, leader election, quorum replication, and split-brain recovery protocols under network partitions.
  3. Complex state machines: Multi-actor lifecycle transitions with concurrent events, timeout hazards, and asynchronous state resets.
  4. Critical parsers and serializers: Untrusted input decoders, binary serialization boundaries, and cryptographic envelope validators where ambiguity introduces security vulnerabilities.

Reject Non-Applicable Targets

Immediately reject requests to formally verify non-applicable targets:

  • Ordinary CRUD APIs and database mutation endpoints.
  • Standard UI components, view layouts, styling systems, and render loops.
  • Simple linear business logic and sequential request-response handlers.
  • Routine configuration parsers, environment loaders, and CLI option parsing.

When a target is non-applicable, reject formal verification immediately. Redirect to standard automated unit tests, integration harnesses, property-based testing, or verification skills (/create-verification-skill).

Authoring Process for Applicable Targets

When a target satisfies the gating criteria, proceed with model authoring:

  1. Define state and actions. Name state variables and state boundaries. Formulate explicit next-state relations.
  2. Specify safety invariants. State properties that must never be violated (such as mutual exclusion or absence of deadlocks).
  3. Specify liveness properties. State conditions that must eventually occur (such as request fulfillment or eventual consensus).
  4. Run model checker. Model check finite state configurations to exhaustively search for counterexamples.
  5. Map counterexamples to code. Translate any model checker counterexample directly into a reproducible unit test in the target codebase.

Frequently asked questions

What does the Create Formal Verification Skill AI skill do?

Generate and apply formal specification models (TLA+, Alloy, Dafny, or state-machine model checkers) strictly for high-consequence concurrency, distributed consensus, complex state machines, and parsers.

Why use Create Formal Verification Skill on TypingMind?

Because you install it once and use it with any model. Create Formal Verification Skill 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 Create Formal Verification Skill in TypingMind?

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

Which AI models can use Create Formal Verification Skill?

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 Create Formal Verification Skill?

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

Is the Create Formal Verification Skill 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

Set up your own AI workspace now

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