Acsl Annotation Assistant logo

Acsl Annotation Assistant

Community
ArabelaTso
acsl-annotation-assistant

Create ACSL (ANSI/ISO C Specification Language) formal annotations for C/C++ programs. Use this skill when working with formal verification, adding function contracts (requires/ensures), loop invariants, assertions, memory safety annotations, or any ACSL specifications. Supports Frama-C verification and generates comprehensive formal specifications for C/C++ code.

Overview

PublisherArabelaTso
RepositorySkills-4-SE
Skill nameacsl-annotation-assistant
Stars
258
Forks
25
Bundled files
3
LicenseApache-2.0
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 ArabelaTso on GitHub. Read the source before you install it.

Installation

Install the Acsl Annotation Assistant 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/ArabelaTso/Skills-4-SE/tree/main/skills/acsl-annotation-assistant
  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/ArabelaTso/Skills-4-SE.git /tmp/Skills-4-SE
mkdir -p .claude/skills
cp -r /tmp/Skills-4-SE/skills/acsl-annotation-assistant .claude/skills/acsl-annotation-assistant
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Acsl Annotation Assistant 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 Acsl Annotation Assistant 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 Acsl Annotation Assistant 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.

ACSL Annotation Assistant

Generate comprehensive ACSL (ANSI/ISO C Specification Language) annotations for C/C++ programs to support formal verification with tools like Frama-C.

Core Capabilities

1. Function Contracts

Add complete function specifications with preconditions and postconditions:

c
/*@
  requires \valid(array + (0..n-1));
  requires n > 0;
  ensures \result >= 0 && \result < n;
  ensures \forall integer i; 0 <= i < n ==> array[\result] >= array[i];
  assigns \nothing;
*/
int find_max_index(int *array, int n);

2. Loop Annotations

Generate loop invariants, variants, and assigns clauses:

c
/*@
  loop invariant 0 <= i <= n;
  loop invariant \forall integer k; 0 <= k < i ==> sum == \sum(0, k, array);
  loop assigns i, sum;
  loop variant n - i;
*/
for (i = 0; i < n; i++) {
    sum += array[i];
}

3. Memory Safety Specifications

Add pointer validity and separation annotations:

c
/*@
  requires \valid(dest + (0..n-1));
  requires \valid_read(src + (0..n-1));
  requires \separated(dest + (0..n-1), src + (0..n-1));
  ensures \forall integer i; 0 <= i < n ==> dest[i] == \old(src[i]);
  assigns dest[0..n-1];
*/
void memcpy_safe(char *dest, const char *src, size_t n);

4. Assertions and Assumptions

Insert runtime and verification assertions:

c
//@ assert 0 <= index && index < array_length;
//@ assume divisor != 0;

5. Axiomatic Definitions and Predicates

Define reusable logical predicates and axioms:

c
/*@
  predicate sorted{L}(int *a, integer n) =
    \forall integer i, j; 0 <= i <= j < n ==> a[i] <= a[j];
*/

/*@
  axiomatic Sum {
    logic integer sum{L}(int *a, integer low, integer high);

    axiom sum_empty{L}:
      \forall int *a, integer i; sum(a, i, i) == 0;

    axiom sum_next{L}:
      \forall int *a, integer low, high;
        low < high ==> sum(a, low, high) == sum(a, low, high-1) + a[high-1];
  }
*/

Annotation Workflow

Step 1: Analyze the Function

Before annotating:

  • Identify inputs, outputs, and side effects
  • Determine memory access patterns
  • Understand algorithmic properties (sorting, searching, etc.)
  • Note any implicit assumptions

Step 2: Add Function Contract

Start with the function-level specification:

  1. Preconditions (requires): What must be true when function is called
  2. Postconditions (ensures): What will be true when function returns
  3. Assigns clause: What memory locations may be modified
  4. Behavioral specification: Normal and exceptional behaviors if applicable

Step 3: Annotate Loops

For each loop, specify:

  1. Loop invariant: Properties that hold before and after each iteration
  2. Loop variant: Decreasing measure proving termination
  3. Loop assigns: Memory modified within the loop

Step 4: Add Assertions

Insert intermediate assertions to:

  • Document algorithmic properties
  • Help verification tools
  • Clarify complex logic

Step 5: Define Helper Predicates

Create reusable logical definitions for:

  • Common patterns (sorted arrays, valid ranges)
  • Domain-specific properties
  • Complex mathematical relationships

Common ACSL Constructs

Memory Validity

c
\valid(ptr)                    // Single valid pointer
\valid(ptr + (low..high))      // Valid range
\valid_read(ptr)               // Read-only validity
\separated(ptr1, ptr2)         // No aliasing

Quantifiers

c
\forall type var; condition ==> property
\exists type var; condition && property

Logic Functions

c
\old(expr)                     // Value at function entry
\at(expr, Label)               // Value at specific point
\result                        // Function return value
\nothing                       // Empty set (for assigns)

Integer Ranges

c
\forall integer i; low <= i < high ==> array[i] >= 0

Behaviors

c
/*@
  behavior valid_input:
    assumes n > 0;
    requires \valid(array + (0..n-1));
    ensures \result >= 0;

  behavior invalid_input:
    assumes n <= 0;
    ensures \result == -1;

  complete behaviors;
  disjoint behaviors;
*/

Verification Considerations

For Frama-C WP Plugin

When generating annotations for WP verification:

  • Use assigns clauses to specify frame conditions
  • Prefer \valid over raw pointer checks
  • Use \separated for pointer disjointness
  • Add loop assigns for all loops
  • Include loop variant for termination proofs

Common Verification Patterns

Array bounds safety:

c
/*@ requires 0 <= index < length;
    requires \valid(array + index);
*/

Null pointer checks:

c
/*@ requires ptr != \null;
    requires \valid(ptr);
*/

Overflow prevention:

c
/*@ requires INT_MIN <= a + b <= INT_MAX; */

Output Format

Generate annotations in standard ACSL comment syntax:

  • Multi-line contracts: /*@ ... */
  • Single-line assertions: //@ assertion
  • Place contracts immediately before function declarations
  • Place loop annotations immediately before loop headers
  • Include explanatory comments when annotations are complex

Best Practices

  1. Start simple: Begin with basic contracts, then refine
  2. Be precise: Avoid over-specification or under-specification
  3. Document assumptions: Make implicit assumptions explicit
  4. Use predicates: Factor out common patterns
  5. Test incrementally: Verify annotations with Frama-C as you go
  6. Include rationale: Add comments explaining non-obvious specifications

Example: Complete Annotated Function

c
/*@
  predicate valid_array(int *a, integer n) =
    \valid(a + (0..n-1)) && n > 0;
*/

/*@
  requires valid_array(array, n);
  ensures \result >= 0 && \result < n;
  ensures \forall integer i; 0 <= i < n ==> array[\result] >= array[i];
  assigns \nothing;
*/
int find_max_index(int *array, int n) {
    int max_idx = 0;

    /*@
      loop invariant 0 <= i <= n;
      loop invariant 0 <= max_idx < n;
      loop invariant \forall integer k; 0 <= k < i ==>
                     array[max_idx] >= array[k];
      loop assigns i, max_idx;
      loop variant n - i;
    */
    for (int i = 1; i < n; i++) {
        if (array[i] > array[max_idx]) {
            max_idx = i;
        }
    }

    return max_idx;
}

Resources

This skill includes reference materials for ACSL:

references/

  • acsl_reference.md - Comprehensive ACSL syntax reference
  • common_patterns.md - Frequently used annotation patterns
  • frama_c_integration.md - Tips for using with Frama-C

Load these references as needed for detailed syntax information or advanced patterns.

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 Acsl Annotation Assistant AI skill do?

Create ACSL (ANSI/ISO C Specification Language) formal annotations for C/C++ programs. Use this skill when working with formal verification, adding function contracts (requires/ensures), loop invariants, assertions, memory safety annotations, or any ACSL specifications. Supports Frama-C verification and generates comprehensive formal specifications for C/C++ code.

Why use Acsl Annotation Assistant on TypingMind?

Because you install it once and use it with any model. Acsl Annotation Assistant 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 Acsl Annotation Assistant in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/acsl-annotation-assistant. 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 Acsl Annotation Assistant?

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 Acsl Annotation Assistant?

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

Is the Acsl Annotation Assistant AI skill free?

Yes. It is published on GitHub by ArabelaTso under the Apache-2.0 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 👇