InnerVault

Library

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

Results

  1. # Context Preservation & Migration Prompt [ for AGENT.MD pass THE `## SECTION` if NOT APPLICABLE ] Generate a comprehensive context artifact that preserves all conversational context, progress, decisions, and project…

    Indexed prompts.chat (CC0 prompt collection), joembolinas CC0-1.0

  2. botica

    Skills

    Recipes and standards for projects: deterministic rules, templates, and design decisions for AI coding agents (opencode, Claude Code, Codex).

    Stale GitHub, collectiveai-team 9 ★Custom licence (see repository)Updated 15 days ago

    git clone https://github.com/collectiveai-team/botica.git
  3. --- name: sprint-prioritizer description: "Use this agent when planning 6-day development cycles, prioritizing features, managing product roadmaps, or making trade-off decisions. This agent specializes in maximizing…

    Indexed prompts.chat (CC0 prompt collection), ersinyilmaz CC0-1.0

  4. claude-mem-lite

    MCP servers

    Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.

    Indexed GitHub, sdsrss 68 ★MITUpdated 5 days ago

    git clone https://github.com/sdsrss/claude-mem-lite.git
  5. { "role": "Senior product researcher who turns raw customer interview transcripts into evidence-backed, decision-ready insights", "task": "Read one customer interview transcript (or detailed notes) and extract…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  6. agentic-career-search

    MCP servers

    Agentic job-discovery backend: 119 ATS & job-board adapters (Greenhouse, Lever, Workday, JSON-LD), explainable scoring with decision traces, cancellable runs, a JobSpy-style search API with CSV/JSONL export and Atom feeds, and a read-only MCP server for Claude, Cursor and VS Code.

    Indexed GitHub, Francis1998 101 ★Updated 4 days ago

    git clone https://github.com/Francis1998/agentic-career-search.git
  7. An open-source MCP server that turns LLMs into condition monitoring assistants for reliability engineers. It gives your AI assistant evidence-based vibration diagnostics: machine fault detection, severity assessment and diagnostic reports, for faster predictive maintenance decisions. Also available as a Claude Code plugin.

    Indexed GitHub, LGDiMaggio 114 ★MITUpdated 2 days ago

    git clone https://github.com/LGDiMaggio/predictive-maintenance-mcp.git
  8. Role: Principal AI Project Manager, Senior Prompt Engineer, and Multi-Agent Workflow Orchestrator. Context: Continue the existing project. Inspect and follow all current project rules, architecture decisions…

    Indexed prompts.chat (CC0 prompt collection), mhe931 CC0-1.0

  9. methodsmith

    Skills

    Rigorous methods for statistics, machine learning and meta-analysis, from question to paper. A plugin for Claude Code and Codex: you make the scientific decisions, it plans, runs and reviews the work.

    Stale GitHub, sajor2000 5 ★MITUpdated 20 days ago

    git clone https://github.com/sajor2000/methodsmith.git
  10. You are a product-minded senior software engineer and pragmatic PM. Help me brainstorm useful, technically grounded ideas for the following: Topic / problem: {{Product / decision / topic / problem}} Context: ${context}…

    Indexed prompts.chat (CC0 prompt collection), Hmm100-star CC0-1.0

  11. Hand-off

    Prompts

    Produce a handoff summary of all decisions made in this session, formatted so I can paste it into a new chat to continue with the next steps pending to execute.

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

  12. --- name: lagrange-lens-blue-wolf description: Symmetry-Driven Decision Architecture - A resonance-guided thinking partner that stabilizes complex ideas into clear next steps. --- Your role is to act as a…

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

  13. Stateful research workflow infrastructure for AI agents: preserves experiments, failures, decisions, and evidence across sessions, from daily lab work to publication (upstream Academic Research Skills by Cheng-I Wu).

    Stale GitHub, zi-yue-1129 9 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/zi-yue-1129/research-lab-skills.git
  14. briefback

    Skills

    A coding-agent workflow with Grill at its core: challenge assumptions and settle decisions before coding. Just describe your task and AgentFlow automatically guides the work from research to reviewable code. Lightweight spec-driven development with planning, TDD, review and handoff for Claude Code, Codex and Cursor.

    Stale GitHub, reforma-ai 10 ★MITUpdated 6 days ago

    git clone https://github.com/reforma-ai/briefback.git
  15. skills

    Skills

    Professional skills for any work and software factory, nasty bugs, hard decisions and reliable software delivery with Claude Code, Codex and other AI agents.

    Stale GitHub, simonasrazm 5 ★MITUpdated 30 days ago

    git clone https://github.com/simonasrazm/skills.git
  16. Agent skill to clean up AI-generated code: audit, refactor and guard vibe-coded codebases with Claude Code, Cursor or Codex. A human approves every decision.

    Indexed GitHub, fictormarcel2 5 ★MITUpdated 6 days ago

    git clone https://github.com/fictormarcel2/untangle-everything.git
  17. I want you to act as a Chief Executive Officer for a hypothetical company. You will be responsible for making strategic decisions, managing the company's financial performance, and representing the company to external…

    Indexed prompts.chat (CC0 prompt collection), jjjjamess CC0-1.0

  18. You are a senior design systems engineer conducting a forensic audit of an existing codebase. Your task is to extract every design decision embedded in the code — explicit or implicit. ## Project Context -…

    Indexed prompts.chat (CC0 prompt collection), gokbeyinac CC0-1.0

  19. You are a senior strategy consultant (McKinsey-style, hypothesis-driven). Your task is to convert a raw business idea into a decision-ready business blueprint. Work top-down. Be structured, concise, and analytical…

    Indexed prompts.chat (CC0 prompt collection), mmanisaligil CC0-1.0

  20. You are a senior market entry consultant (Big 4 + strategy firm mindset). Your task is to design a market entry strategy that is realistic, structured, and decision-oriented. --- ### 0. Entry Hypothesis - Why this…

    Indexed prompts.chat (CC0 prompt collection), mmanisaligil CC0-1.0

  21. An opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, durable handoffs.

    Stale GitHub, dbc-oduffy 5 ★Custom licence (see repository)Updated 10 days ago

    git clone https://github.com/dbc-oduffy/coordinator-claude.git
  22. role: Practical, calm kitchen remodel planner who helps homeowners turn a kitchen renovation idea into a realistic timeline and budget plan, covering phases, decisions and their deadlines, lead times, a contingency…

    Indexed prompts.chat (CC0 prompt collection), f CC0-1.0

  23. Aphorism Book

    Prompts

    I want you to act as an aphorism book. You will provide me with wise advice, inspiring quotes and meaningful sayings that can help guide my day-to-day decisions. Additionally, if necessary, you could suggest practical…

    Indexed prompts.chat (CC0 prompt collection), devisasari CC0-1.0

  24. agent-afk

    MCP servers

    The coding agent you don’t have to watch. Start a task and walk away. AFK builds the feature, verifies its own work, and texts you when it’s done. You come back to a receipt of every step, every decision, and what’s waiting on you. If it’s unsure, it stops and asks instead of guessing.

    Indexed GitHub, griffinwork40 63 ★Apache-2.0Updated yesterday

    git clone https://github.com/griffinwork40/agent-afk.git

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.