InnerVault

auto-improve

IndexedGitHub, crimeacs

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), revert the rest. The git history is the improvement log.

Open the source (opens github.com) https://github.com/crimeacs/auto-improve

What it is

Prompts from crimeacs.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

Get the code

git clone https://github.com/crimeacs/auto-improve.git

Standard git access to a public repository

Setup steps: not provided by the source. Follow the instructions on the source.

Related

  1. Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.

    Stale GitHub, Anil-matcha 1,147 ★MITUpdated 46 days ago

    git clone https://github.com/Anil-matcha/awesome-gpt-6-astra.git
  2. skillcheck

    Prompts

    Blind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.

    Stale GitHub, sx4im 30 ★MITUpdated 15 days ago

    git clone https://github.com/sx4im/skillcheck.git
  3. codex-keysmith

    Prompts

    Versioned Codex instruction deployment with preview, ownership manifests, hook isolation, scenario evaluation, and recovery.

    Stale GitHub, Jia-Ethan 4,740 ★MITUpdated 52 days ago

    git clone https://github.com/Jia-Ethan/codex-keysmith.git
  4. A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and managed agents, emerging agent runtimes, and production AI workflow patterns.

    Stale GitHub, Prompthon-IO 316 ★Custom licence (see repository)Updated 33 days ago

    git clone https://github.com/Prompthon-IO/agent-systems-handbook.git
  5. futureagi-sdk

    Prompts

    Production-grade AI evaluation, prompt management & observability SDK. Automated evaluations with sub-100ms guardrails. No human-in-the-loop required. Python + TypeScript.

    Stale GitHub, future-agi 52 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/future-agi/futureagi-sdk.git
  6. ponytail

    Prompts

    Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

    Stale GitHub, DietrichGebert 181.6k ★MITUpdated 20 days ago

    git clone https://github.com/DietrichGebert/ponytail.git