InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Self-hosted AI orchestrator for ticket-driven coding and automated code review in isolated containers.

    Stale GitHub, savoirfairelinux 9 ★GPL-3.0Updated 32 days ago

    git clone https://github.com/savoirfairelinux/virtual-engineer.git
  2. consensus-mcp

    MCP servers

    Official Consensus MCP server. Semantic search over 400M+ research papers, including all of PubMed, for Claude, ChatGPT, Cursor and any MCP client.

    Stale GitHub, Consensus-NLP 31 ★MITUpdated 11 days ago

    git clone https://github.com/Consensus-NLP/consensus-mcp.git
  3. skill-doctor

    Skills

    🩺 A bilingual meta-skill for Claude Code: health-check your other skills and review agent-workflow architecture - runtime reality, ownership, scaffolding, recovery. Diagnose-only. Built on Matt Pocock's method.

    Stale GitHub, isalicema 7 ★MITUpdated 11 days ago

    git clone https://github.com/isalicema/skill-doctor.git
  4. Unified enterprise & software architecture Claude Code skill: C4+Structurizr, ArchiMate, TOGAF ADM, arc42+ADR. Diagram, document, review, and model the enterprise.

    Stale GitHub, gauravs19 16 ★MITUpdated 35 days ago

    git clone https://github.com/gauravs19/enterprise-architecture-skill.git
  5. ReviewGate

    MCP servers

    Code review against your team standards, before the pull request: generator finds, judge confirms

    Stale Official MCP Registry, dev.reviewgate Updated 2 months ago 1 note

    https://github.com/ReviewGate/reviewgate/releases/download/v2.0.6/reviewgate-2.0.6-darwin-arm64.mcpb
  6. An Orca best practice built around Matt Pocock's engineering skills. His chain stays: grill-with-docs, to-spec, to-tickets, then implement or implement-spec, closing with code-review. Orca supervises each step in its own worktree, with gates and merge. Not affiliated with or endorsed by Matt Pocock.

    Stale GitHub, whutlichao 9 ★MITUpdated 11 days ago

    git clone https://github.com/whutlichao/orchestra-auto.git
  7. a design skill for claude code, cursor and codex: art direction, reference analysis and browser QA for your frontend

    Stale GitHub, wrg32786 5 ★MITUpdated 12 days ago

    git clone https://github.com/wrg32786/aigent-design-system.git
  8. Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

    Stale Agent skill collections on GitHub, vercel-labs 1 note

    npx skills add vercel-labs/agent-skills
  9. pinboard

    Skills

    Keep coding-agent work coherent across tasks, interruptions, and review.

    Stale GitHub, valsteen 5 ★MITUpdated 15 days ago

    git clone https://github.com/valsteen/pinboard.git
  10. nightshift

    Agents & frameworks

    Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results a clear view of what’s done, in progress, parked, or blocked—without scrolling a marathon chat.

    Stale GitHub, orwa-mahmoud 175 ★MITUpdated 7 days ago

    git clone https://github.com/orwa-mahmoud/nightshift.git
  11. wicked-garden

    Skills

    The skills your coding agent can't build alone: done re-checked from evidence, graph-aware refactor, 40 QE specialists, review panels from other models.

    Stale GitHub, mikeparcewski 9 ★MITUpdated 4 days ago

    git clone https://github.com/mikeparcewski/wicked-garden.git
  12. lattice

    Agents & frameworks

    Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.

    Indexed GitHub, techygarg 213 ★MITUpdated 2 days ago

    git clone https://github.com/techygarg/lattice.git
  13. skills

    Skills

    23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex desktop edition tuned for Astra. Source for clickai.dev.

    Stale GitHub, timharris707 44 ★MITUpdated 13 days ago

    git clone https://github.com/timharris707/skills.git
  14. Agent skill for writing and reviewing SwiftUI code on macOS — runtime-level understanding of observation, concurrency, view identity, and platform integration

    Stale GitHub, kageroumado 13 ★MITUpdated 30 days ago

    git clone https://github.com/kageroumado/swiftui-macos-skill.git
  15. skills

    Skills

    Univer Skill enables AI tools to work directly with spreadsheets, Excel workbooks, and CSV files. Powered by Univer CLI, it brings Git-style diffs, reviews, approvals, and rollbacks to spreadsheet workflows — making human-AI collaboration structured, reviewable, and safe.

    Stale GitHub, dream-num 77 ★Apache-2.0Updated 33 days ago

    git clone https://github.com/dream-num/skills.git
  16. ui-ticket-mcp

    MCP servers

    Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP.

    Stale Official MCP Registry, io.github.0ics-srls Updated 10 days ago 1 note

    ui-ticket-mcp@1.6.2
  17. agent-flow

    Skills

    Guardrails for AI coding agents: run Claude Code, Codex, Gemini CLI, Cursor or Copilot unattended and come back to a reviewed pull request. Implement, review and QA agents, a guard on protected paths, and a tamper-evident audit log.

    Stale GitHub, Drix10 12 ★MITUpdated 5 days ago

    git clone https://github.com/Drix10/agent-flow.git
  18. UI Design to Code

    MCP servers

    Design-to-code artifact pipeline for UI screenshots, Figma node data, and visual review.

    Stale Official MCP Registry, io.github.Kinglions Updated 4 months ago 1 note

    ui-design-to-code-mcp@0.1.12
  19. Agent skills distilled from real-world usage — codex-implementation-loop: delegate coding to Codex, keep review/gate/ship judgment in Claude's hands

    Stale GitHub, olddonkey 17 ★MITUpdated 32 days ago

    git clone https://github.com/olddonkey/olddonkey-skills.git
  20. A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.

    Stale GitHub, russelleNVy 953 ★MITUpdated 5 months ago

    git clone https://github.com/russelleNVy/three-man-team.git
  21. trace-mcp

    MCP servers

    Code graph MCP: 81 languages, 91 frameworks, 72.7% fewer PR-review tokens, comprehension at parity

    Indexed Official MCP Registry, io.github.nikolai-vysotskyi 204 ★Updated yesterday 1 note

    trace-mcp@3.44.1
  22. cetus

    Agents & frameworks

    One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.

    Indexed GitHub, william-jin-cmu 151 ★MITUpdated today

    git clone https://github.com/william-jin-cmu/cetus.git
  23. storybloq

    MCP servers

    Project memory and workflows for Claude Code and Codex. Keep stories, plans, handovers, and review evidence in your repo. Resume across sessions and follow progress in the Mac app.

    Stale GitHub, Storybloq 788 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/Storybloq/storybloq.git
  24. tlbx

    Agents & frameworks

    Open-source Agentic Development Environment (ADE) for Codex, Claude Code and other agents. Run on your own Windows, macOS or Linux machines; steer sessions, review changes and test apps from any browser.

    Indexed GitHub, tlbx-ai 119 ★AGPL-3.0Updated yesterday

    git clone https://github.com/tlbx-ai/tlbx.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.