InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. humanizer-ru

    Skills

    Очеловечить текст нейросети: убирает длинное тире, канцелярит и штампы ChatGPT, не трогая факты. Правила для любой нейросети + скилл для Claude Code, Cursor, Codex. · Make AI text sound human: Russian + English rules and a Claude Code skill.

    Stale GitHub, thevseprod 44 ★MITUpdated 29 days ago

    git clone https://github.com/thevseprod/humanizer-ru.git
  2. promptbudget-mcp

    MCP servers

    Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.

    Stale Official MCP Registry, io.github.MukundaKatta Updated 6 months ago 1 note

    @mukundakatta/promptbudget-mcp@0.2.0
  3. humane-proxy

    MCP servers

    AI safety middleware — detects self-harm and criminal intent in LLM prompts.

    Stale Official MCP Registry, io.github.Vishisht16 Updated 4 months ago 2 notes

    humane-proxy@0.6.0
  4. SOTA-skills

    Skills

    Engineering best practices that AI coding agents actually apply — 40+ skills, from secure coding and cloud to compliance and UX writing. BUILD + AUDIT modes. Measured: best-practice coverage 59% → 98% vs. the same model unguided.

    Indexed GitHub, martinholovsky 28 ★CC-BY-4.0Updated 2 days ago

    git clone https://github.com/martinholovsky/SOTA-skills.git
  5. phi-guard-mcp

    MCP servers

    Local-first PHI detection for source code, LLM prompts, logs, and analytics

    Stale Official MCP Registry, io.github.Abidit Updated 2 months ago 1 note

    phi-guard-mcp@0.2.0
  6. agent-godmode

    MCP servers

    Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts.

    Stale Official MCP Registry, io.github.mdvohra Updated 6 months ago 1 note

    agent-godmode@0.1.9
  7. DoboCache

    MCP servers

    Stabilizes LLM prompt-cache prefixes so provider caching hits. One command setup, no baseURL edit.

    Indexed Official MCP Registry, io.github.dobo123123 Updated yesterday 1 note

    dobocache@0.9.2
  8. Claude Code Skill Factory — A powerful open-source toolkit for building and deploying production-ready Claude Skills, Code Agents, custom Slash Commands, and LLM Prompts at scale. Easily generate structured skill templates, automate workflow integration, and accelerate AI agent development with a clean, developer-friendly setup.

    Stale GitHub, alirezarezvani 886 ★MITUpdated 12 months ago

    git clone https://github.com/alirezarezvani/claude-code-skill-factory.git
  9. 500+ original websites built by AI coding agents — Claude, GPT, Gemini, Grok, Kimi, GLM, DeepSeek. Live demos, copy-paste prompts and DESIGN.md for Claude Code, Cursor and Codex. Vibe coding website templates, updated with every new model.

    Indexed GitHub, liyupi 16 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/liyupi/awesome-vibe-coding-websites.git
  10. Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar

    Stale Official MCP Registry, io.github.alphaparkinc Updated 27 days ago 1 note

    https://github.com/Alpha-Park/genpark-context-window-token-pruner-skill/releases/download/v1.0.1/genpark-context-window-token-pruner-skill-v1.0.1.mcpb
  11. Claude Code / Agent Skill: /prompt-optimizer polishes your existing AI prompts — fixes wording, grammar and structure without adding scope, changing constraints or touching commands, paths and code. 提示词优化技能:只改表达,不改语义。Works with Claude Code, Codex and any chat AI.

    Indexed GitHub, talki-io 6 ★MITUpdated 4 days ago

    git clone https://github.com/talki-io/prompt-optimizer.git
  12. archetype

    Prompts

    A curated library of reusable LLM prompts for domain experts, personas, creative practice, structured workflows, and archetype generation.

    Indexed GitHub, 1arry1iu 59 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/1arry1iu/archetype.git
  13. Agent skill for authentic Arabic writing: strips English calques and translated phraseology (العرنجية) from Arabic text. Works with Claude Code, Codex, Antigravity, VS Code. Based on Ahmad Al-Ghamdi's treatise — مهارة الكتابة العربية الفصيحة ونبذ العرنجية

    Stale GitHub, specailm5 6 ★MITUpdated 11 days ago

    git clone https://github.com/specailm5/arabic-writing-skill.git
  14. Maximal Marginal Relevance (MMR) exemplar selector optimizing semantic relevance and diversity for LLM prompt engineering

    Stale GitHub, Alpha-Park 7 ★Updated 28 days ago

    git clone https://github.com/Alpha-Park/genpark-few-shot-mmr-diversity-selector-skill.git
  15. Peer

    Skills

    Peer makes Claude act like an experienced colleague you can use as a sounding board, so you can work through ideas and problems without the frustrating AI habits of echoing you back, flattering you, agreeing too easily and shotgunning lists at you. It holds its view when you push back without a reason, and changes it when you give one.

    Indexed GitHub, andykear 22 ★CC-BY-4.0Updated 2 days ago

    git clone https://github.com/andykear/Peer.git
  16. Act as a **Prompt Generator for Large Language Models**. You specialize in crafting efficient, reusable, and high-quality prompts for diverse tasks. **Objective:** Create a directly usable LLM prompt for the following…

    Indexed prompts.chat (CC0 prompt collection), zzfmvp@gmail.com CC0-1.0

  17. SYSTEM: You are an LLM prompt executor. USER TASK: Create a vertical 9:16 infographic for TikTok. TITLE (ONLY ONE TITLE — display this at the top): [Fraud Playbook: Voice Cloning Attacks (2026)] LAYOUT (choose ONE)…

    Indexed prompts.chat (CC0 prompt collection), tracker4devices@gmail.com CC0-1.0

  18. SYSTEM: You are an LLM prompt executor. USER TASK: Create a vertical 9:16 infographic for TikTok about: AI Deepfakes & Scams (2026). LAYOUT (choose ONE): Use: 1-6 box Number boxes with circled numbers. Flow…

    Indexed prompts.chat (CC0 prompt collection), tracker4devices@gmail.com CC0-1.0

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.