InnerVault

agentic-ai-prompt-research

Stale GitHub, Leonxlnx

Research into how agentic AI coding assistants work. Reconstructed prompt patterns, agent coordination, and security classification

Open the source (opens github.com) https://github.com/leonxlnx/agentic-ai-prompt-research

What it is

Prompts from Leonxlnx.

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/Leonxlnx/agentic-ai-prompt-research.git

Standard git access to a public repository

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

Related

  1. All official Claude system prompts in one open-source repo from Claude Fable 5.2 to Claude Haiku 3 23 models from Anthropic's release notes, plus original analysis, tool schemas, and AI-safety research.

    Indexed GitHub, KalarisLabs 230 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/KalarisLabs/claude-systems-prompts.git
  2. Academic Research Skills for Claude Code: research → write → review → revise → finalize

    Indexed GitHub, Imbad0202 57.1k ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/Imbad0202/academic-research-skills.git
  3. 🔴 VERY LARGE AI TOOL LIST! 🔴 Curated list of AI Tools - Updated 2026

    Stale GitHub, eudk 599 ★CC0-1.0Updated 5 months ago

    git clone https://github.com/eudk/awesome-ai-tools.git
  4. Open-source Agent Skills for planning, drafting, revising, and polishing SCI/SSCI papers—while preserving evidence, citations, and claim strength.

    Stale GitHub, Yila-AI 138 ★Apache-2.0Updated 26 days ago

    git clone https://github.com/Yila-AI/awesome-research-skills.git
  5. AI Paper Reviewer: LLM-based tool for academic paper review

    Indexed GitHub, FanBroWell 50 ★MITUpdated yesterday

    git clone https://github.com/FanBroWell/AI-paper-reviewer.git
  6. deepdive

    Prompts

    Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.

    Indexed GitHub, Socialpranker 371 ★MITUpdated yesterday

    git clone https://github.com/Socialpranker/deepdive.git