New to Claude Skills? Learn how to install them →

sickn33 on GitHub

AI Native File Format

Free

Embed trust and provenance metadata into files.

Get this skill

Free · Opens the source repo

What AI Native File Format does

The AI Native File Format (AKF) is designed to enhance the integrity of AI-generated and AI-modified files by embedding essential metadata that indicates trust scores, source provenance, and compliance details. This skill allows developers and designers to ensure that their files are not only created or modified with AI but also carry the necessary information for auditing and compliance. It supports over 20 file formats, including DOCX, PDF, images, and code, making it versatile for various use cases.

With AKF, users can easily stamp files with relevant metadata after creation or modification. This is particularly useful in scenarios where transparency and accountability are critical, such as during compliance audits for regulations like the EU AI Act, HIPAA, and SOX. The skill also provides commands to read and inspect existing metadata, allowing users to verify the trustworthiness of files before making any changes.

The skill is particularly beneficial for teams working in regulated industries or those that require rigorous documentation of their processes. By integrating AKF into their workflows, users can streamline the review and handoff processes, ensuring that all stakeholders have access to the necessary provenance information. This capability not only enhances trust in AI-generated content but also facilitates smoother collaboration among team members.

Overall, AKF is a practical tool for anyone looking to maintain high standards of compliance and trust in their digital assets. By embedding metadata directly into files, it helps users navigate the complexities of regulatory requirements while providing a clear audit trail for their AI-related activities.

When to use it

Use this skill when you need to add or verify metadata related to trust and provenance in AI-generated or modified files.

When not to use it

This skill is not suitable for tasks outside the scope of metadata management or when environment-specific validation is required.

What you can build with it

Compliance Auditing for AI Content

Use AKF to audit AI-generated files for compliance with regulations like HIPAA and the EU AI Act.

Stamping AI-Generated Files

After generating content with AI, use AKF to stamp files with trust scores and provenance metadata.

Verifying File Integrity

Before modifying existing files, inspect their metadata to ensure trustworthiness and compliance.

How to install AI Native File Format

View source

1. Install with the skills CLI

npx skills add sickn33/agentic-awesome-skills/akf-trust-metadata --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by sickn33

AKF — The AI Native File Format

Every photo has EXIF. Every song has ID3. AKF is the native metadata format for AI-generated content.

When to Use

Use this skill when you need to stamp, inspect, or audit provenance and trust metadata on AI-generated or AI-modified files for compliance, review, or handoff workflows.

After creating or modifying files

akf stamp <file> --agent <agent-name> --evidence "<what you did>"

Evidence examples:

  • "generated from user prompt"
  • "refactored existing code"
  • "tests pass"
  • "docs reviewed"

Before modifying existing files

akf read <file>          # Check existing trust metadata
akf inspect <file>       # See detailed trust scores

Compliance auditing

akf audit <file> --regulation eu_ai_act    # EU AI Act Article 50
akf audit <file> --regulation hipaa         # HIPAA
akf audit <file> --regulation sox           # SOX
akf audit <file> --regulation nist_ai       # NIST AI RMF

Classification

  • --label confidential for finance/secret/internal paths
  • --label public for README, docs, examples
  • Default: internal

Install

pip install akf

Links

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Frequently asked questions about AI Native File Format

Similar skills