Audit Explanatory Compression logo

Audit Explanatory Compression

Organization
yogsoth-ai
audit-explanatory-compression

Test whether an elegant/simple explanation earns its compression by forbidding alternatives, subsuming independent facts, or making risky predictions, rather than merely relabeling observations with a compact vocabulary.

Overview

Publisheryogsoth-ai
Repositoryde-anthropocentric-research-engine
Skill nameaudit-explanatory-compression
Stars
505
Forks
43
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by yogsoth-ai on GitHub. Read the source before you install it.

Installation

Install the Audit Explanatory Compression 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/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/audit-explanatory-compression
  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/yogsoth-ai/de-anthropocentric-research-engine.git /tmp/de-anthropocentric-research-engine
mkdir -p .claude/skills
cp -r /tmp/de-anthropocentric-research-engine/skills/audit-explanatory-compression .claude/skills/audit-explanatory-compression
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Audit Explanatory Compression 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 Audit Explanatory Compression 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 Audit Explanatory Compression 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.

audit-explanatory-compression

Purpose

Test whether an elegant explanation earns compression by excluding alternatives, subsuming independent facts, or making risky predictions.

Input contract

yaml
mode_contracts:
  earned-simplicity: &compression_audit_input
    required: [explanation, covered_facts, alternatives]
    optional: [predictions, evidence]
    constraints: [facts_and_alternatives_must_be_independently_enumerated]
  decorative-simplicity: *compression_audit_input
  risky-prediction: *compression_audit_input

Execution protocol

Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.

  1. You MUST load skill classify-simplicity-evidence to classify the explanation's compression evidence.
  2. You MUST load skill test-risky-prediction to derive and test risky predictions.
  3. You MUST load skill construct-critique to attack the explanation. You MUST load skill score-object to score its remaining support. Deviation: omit prediction testing only when no nontrivial prediction can be derived, and mark the explanation non-discriminating.

Output contract

yaml
mode_contracts:
  earned-simplicity: &compression_audit_output
    produces: [forbidden_set, risky_predictions, accommodation_audit, deletion_test_result, elegance_verdict, earning_prediction]
    delta_fields: [findings, evidence_updates, uncertainties, decisions]
  decorative-simplicity: *compression_audit_output
  risky-prediction: *compression_audit_output

Thresholds and quality gates

  • Earned simplicity requires at least one independent fact compressed and one risky alternative-forbidding prediction, each evidence-linked.
  • Decorative simplicity is a failure when it merely renames observations.

Failure and counterexamples

Do not reward brevity alone. Mark weak when independent facts, exclusions, or predictions are absent.

Provenance map

  • resolved: elegance-trap-probe

Preserved source criteria ledger

sourcesource linekindsource criterion
v4 architecturenode desctextualDistinguish earned simplicity from decorative relabeling.

Context checkpoint / Delta notes

Append covered facts, alternatives, risky predictions, critique, and score rationale.

Mode branches

  • earned-simplicity: seek independent compression and exclusions.
  • decorative-simplicity: test for relabeling.
  • risky-prediction: prioritize prospective constraints.

Frequently asked questions

What does the Audit Explanatory Compression AI skill do?

Test whether an elegant/simple explanation earns its compression by forbidding alternatives, subsuming independent facts, or making risky predictions, rather than merely relabeling observations with a compact vocabulary.

Why use Audit Explanatory Compression on TypingMind?

Because you install it once and use it with any model. Audit Explanatory Compression 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 Audit Explanatory Compression in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/audit-explanatory-compression. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Audit Explanatory Compression?

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 Audit Explanatory Compression?

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

Is the Audit Explanatory Compression AI skill free?

Yes. It is published on GitHub by yogsoth-ai 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 👇