Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Acorn Theorem Prover Verifier

ASecurity

Verify and write proofs using the Acorn theorem prover for mathematical and cryptographic formalization. Use when working with Acorn proof files (.ac), verifying theorems, formalizing mathematical or cryptographic protocols, or writing proofs in the Acorn language. Triggers on:…

19 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgobashci/cddocumentation

Works with

climcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill acorn-theorem-prover-verifier --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Acorn Theorem Prover Verifier?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Acorn Theorem Prover Verifier
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-acorn-theorem-prover-verifier/badge)](https://www.skillsdirectory.com/skills/rondoflow-acorn-theorem-prover-verifier)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: acorn-theorem-prover-verifier
description: "Verify and write proofs using the Acorn theorem prover for mathematical and cryptographic formalization. Use when working with Acorn proof files (.ac), verifying theorems, formalizing mathematical or cryptographic protocols, or writing proofs in the Acorn language. Triggers on:…"
category: "Content & Writing"
author: community
version: "1.0.0"
icon: pencil
---

# Acorn Prover

## Setup (MUST DO WHEN RUNNING FIRST TIME)

If `config.env` does not exist in the skill directory:

1. **Ask the user** for the following paths:
   - `ACORN_LIB` - Path to acornlib (e.g., `/path/to/acornprover/acornlib`)
   - `ACORN_PROJECT` - Path to project directory for `.ac` files (e.g., `/path/to/acorn-playground`)

2. **Verify** the paths exist using `list_dir` or equivalent. If a path is invalid, inform the user and ask again.

3. **Run setup.sh** with the validated paths:

```bash
bash skills/acorn-prover/scripts/setup.sh "<ACORN_LIB>" "<ACORN_PROJECT>"
```

4. **Source the config** to get `ACORN_LIB`, `ACORN_PROJECT`, and `USE_MISE` variables:

```bash
source skills/acorn-prover/config.env
```

If any of the above are blank / not set, inform the user to set the variable manually.
If any of the above are changed, ask the user for new paths and run setup again.

## Configuration

Config values are stored in `skills/acorn-prover/config.env`:

| Variable        | Description                     |
| --------------- | ------------------------------- |
| `ACORN_LIB`     | Path to acornlib                |
| `ACORN_PROJECT` | Project directory for .ac files |
| `USE_MISE`      | `true` if mise is available     |

## Verify Proofs

If `USE_MISE=true`:

```bash
mise run acorn verify <filename>.ac
```

Otherwise, use the direct CLI:

```bash
acorn --lib "$ACORN_LIB" verify <filename>.ac
```

## Reverify Proofs (CI/CD)

Check that all proofs are cached with no AI searches required:

```bash
# With mise
mise run acorn reverify

# Or direct CLI
acorn --lib "$ACORN_LIB" reverify
```

Use for CI pipelines to ensure all proofs are complete.

## Training Data Generation

Generate training data (problem-proof pairs) for AI model development:

```bash
# With mise
mise run acorn training ./training_data

# Or direct CLI
acorn --lib "$ACORN_LIB" training ./training_data
```

Argument: `DIR` - Directory to output training data.

## Documentation Generation

Generate library reference documentation:

```bash
# With mise
mise run acorn docs ./docs/library

# Or direct CLI
acorn --lib "$ACORN_LIB" docs ./docs/library
```

Argument: `DIR` - Directory to output documentation.

## Workflow

1. Source config: `source skills/acorn-prover/config.env`
2. Write proof file in `$ACORN_PROJECT/`
3. Run the appropriate command (verify, reverify, training, docs)
4. **Always show the full command output to the user** (success or error)
5. Debug errors using the common errors table in [references/syntax.md](references/syntax.md)
6. Iterate until verification passes

## Quick Syntax Overview

```acorn
from nat import Nat
from add_comm_group import AddCommGroup

// Theorems - auto-proved or with hints
theorem example(a: Nat, b: Nat) {
    a < b implies a != b
}

// Typeclasses - axioms are named blocks, no "axiom" keyword
typeclass A: AddGroup extends Zero, Neg, Add {
    inverse_right(a: A) { a + -a = A.0 }
}

// Structures
structure Pair[T, U] { first: T  second: U }

// Inductive types - constructors MUST be lowercase
inductive MyBool { tru fls }
```

Key points:

- Built-in logic keywords (`not`, `and`, `or`, `implies`, `iff`, `true`, `false`) are reserved - do not redefine
- Constructor names must be lowercase
- Typeclass axioms use named blocks, not the `axiom` keyword

## Standard Library (`acornlib`)

Key modules in `$ACORN_LIB/src`:

| Module              | Contents                                   |
| ------------------- | ------------------------------------------ |
| `nat/`              | Natural number axioms, induction, addition |
| `add_group.ac`      | `AddGroup` with `a + -a = A.0`             |
| `add_comm_group.ac` | Abelian groups (`AddCommGroup`)            |

## References

- **Full syntax, error table, examples**: See [references/syntax.md](references/syntax.md)
- **Context7 docs**: Use `context7` MCP with `/acornprover/acorn` or `/acornprover/acornlib` for latest documentation

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →