InnerVault

Library

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

Results

  1. simmer

    Skills

    Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements

    Stale GitHub, 2389-research 16 ★MITUpdated 15 days ago

    git clone https://github.com/2389-research/simmer.git
  2. Sharps and red-bag pickup proposals for Dallas County offices, with named-office records

    Stale Official MCP Registry, com.forevenza.services Updated 11 days ago 1 note

  3. Run AI agents across machines without state drift: consensus protocol (propose/counter/accept/commit), dual-rail message bus, ACK discipline, self-healing sync. Formerly claude-consensus. Free, MIT.

    Indexed GitHub, tonydzi 7 ★MITUpdated yesterday

    git clone https://github.com/tonydzi/claw-consensus.git
  4. resp-warden-desk

    Agents & frameworks

    An eight-agent rule engine for on-chain risk analysis. Seven rules propose, one vetoes. Read-only, no keys, no execution.

    Indexed GitHub, ElysiumduskImmortal63439 50 ★Updated 3 days ago

    git clone https://github.com/ElysiumduskImmortal63439/resp-warden-desk.git
  5. Dearborn MI switch swap and repatch visits for MSPs; remote signoff; proposal by email

    Stale Official MCP Registry, com.forevenza.services Updated 8 days ago 1 note

  6. Self-improvement feedback loop for AI agent skills — analyzes past sessions, drafts structured improvement proposals, and gates auto-apply behind an evaluation framework. Host-agnostic (Hermes, Claude Code, and any HostAdapter).

    Stale GitHub, Carlo1911 6 ★MITUpdated 30 days ago

    git clone https://github.com/Carlo1911/skill-evolution.git
  7. --- name: sql-index-recommendation-reviewer description: Reviews a schema and slow SQL queries, proposes composite indexes in the right column order (equality, sort, range) with covering columns and tradeoffs, flags…

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

  8. A controlled AI workflow for Blender: every copilot edit is a supervised tool call—proposed, approved, executed in sequence, cancellable after the current step and undoable by name—inside a visual studio with a built-in MCP server. · blender-ai-copilot-flow · blender · blender 3d · blender addon · blender plugin · blender extension

    Indexed GitHub, tiobeharxi1987 510 ★MITUpdated yesterday

    git clone https://github.com/tiobeharxi1987/blender-ai-copilot-flow.git
  9. extract all information in this chat verbatim Capture every detail from start to finish, ensuring the notes read like a comprehensive plan or proposal, with a focus on the user's intentions and actions.

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

  10. Act as a senior research associate in academia. When I provide you with papers, ideas, or experimental results, your task is to help brainstorm ways to improve the results, propose innovative ideas to implement, and…

    Indexed prompts.chat (CC0 prompt collection), turhancan97 CC0-1.0

  11. Act as an expert technical blog writer specializing in AI, robotics, and related technical domains. When requested to write a blog post, always begin by proposing a detailed outline for the post based on the provided…

    Indexed prompts.chat (CC0 prompt collection), turhancan97 CC0-1.0

  12. Act as a software developer specializing in data analysis portals. You are responsible for developing and debugging the HTS Veri Analiz Portalı. Your task is to: - Identify bugs in the current system and propose…

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

  13. I want you to act like a music video designer, propose an innovative plot, legend-making, and shiny video scenes to be recorded, it would be great if you suggest a scenario and theme for a video for big clicks on…

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

  14. I need assistance crafting a convincing summary for my LinkedIn profile that would help me land a ${job_title} in ${industry}. I want to make sure that it accurately reflects my unique value proposition and catches the…

    Indexed prompts.chat (CC0 prompt collection), tejaswi4000@gmail.com CC0-1.0

  15. 한국어 원고 교정교열 Claude Code 스킬. 논문·연구계획서·보고서·공문서의 맞춤법·띄어쓰기·문장·용어 통일·인용을 문단 단위로 점검하고, 고친 이유를 교정교열표로 남깁니다. 한글(.hwpx)은 원본에 바로 반영합니다. | Korean proofreading skill for Claude Code: papers, research proposals, reports and government documents, with an edit log and in-place .hwpx revisions.

    Stale GitHub, parkjui92 6 ★MITUpdated 19 days ago

    git clone https://github.com/parkjui92/paper-proofread.git
  16. skills

    Skills

    43 Claude Code skills for making content that doesn't read like a machine made it — prose editing with an offline linter, prompt engineering for 40+ image/video/music models with optional one-command execution, and orchestrators from research to a published carousel, reel or proposal. Russian-first, English throughout.

    Stale GitHub, Mikefluff 26 ★MITUpdated 21 days ago

    git clone https://github.com/Mikefluff/skills.git
  17. Five Claude Code plugins, Python stdlib + git. ar-board: judge agent proposals one by one on a local board; the agent keeps your reasons. publish-check: scan a repo's history for personal data before it goes public. tidy-board: delete stale branches, worktrees, and stashes only on approval. Plus doc, handoff, and TODO tools, and a status line.

    Stale GitHub, dvwinck 33 ★MITUpdated 14 days ago

    git clone https://github.com/dvwinck/capybara-toolbox.git
  18. Policy Simulator API

    Public APIs

    Policy Simulator is a collection of endpoints for creating, running, and viewing a Replay. A Replay is a type of simulation that lets you see how your members' access to resources might change if you changed your IAM policy. During a Replay , Policy Simulator re-evaluates, or replays, past access attempts under both the current policy and your proposed policy, and compares those results to…

    Indexed APIs.guru OpenAPI Directory, Google Updated 3 years ago

  19. After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts…

    Indexed Agent skill collections on GitHub, anthropics Complete terms in LICENSE.txt1 note

    /plugin marketplace add anthropics/skills

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.