Agent Plugins Marketplace

Recently added

Plugins grouped by the day they were added to the directory, newest first.

Aug 30, 2026

  1. brex0stars

    Analyze Brex expenses, cards, limits, banking, bills, accounting, travel, and organization data, or safely update supported expense details through Brex's official hosted MCP server.

    Agent Plugins1 skill1 MCP server
  2. brand240stars

    Explore current Brand24 project summaries, important events, discussions, influencers, and mention sources through Brand24's official read-only hosted MCP server.

    Agent Plugins1 skill1 MCP server
  3. boltz-api-cli0stars

    Predict structures, screen molecules and proteins, and design binders.

    Agent Plugins8 skills
  4. biorender0stars

    Search BioRender templates and accessible figures, preview results, and create editable scientific figure drafts through BioRender's official hosted MCP server.

    Agent Plugins1 skill1 MCP server
  5. binance0stars

    Comprehensive Binance workflows for public market data, Spot, Futures, Options, Convert, Margin, Earn, Loans, Wallet, Fiat, P2P, and Onchain Pay.

    Agent Plugins4 skills
  6. bilibili-search0stars

    Skill for searching Bilibili videos and the daily ranking via the public web search endpoint — no login required for top-level results.

    Agent Plugins1 skill
  7. base440stars

    Build and deploy Base44 full-stack apps with CLI project management and JavaScript/TypeScript SDK development skills

    Agent Plugins5 skills
  8. attio0stars

    Search, read, create, and update Attio CRM records, lists, comments, notes, tasks, meetings, calls, emails, and reports through Attio's official hosted MCP server.

    Agent Plugins1 skill1 MCP server
  9. atlassian-rovo0stars

    Search and manage Jira, Confluence, Jira Service Management, Bitbucket, Compass, and Teamwork Graph through Atlassian's official Rovo MCP server and workflow skills.

    Agent Plugins6 skills1 MCP server
  10. asana0stars

    Read and manage Asana tasks, subtasks, comments, due dates, projects, portfolios, status updates, teams, users, and workspace priorities through Asana's official V2 MCP server.

    Agent Plugins3 skills1 MCP server
  11. apollo0stars

    Prospect for people and companies, enrich leads, load reviewed contacts into outreach sequences, and query sales analytics through Apollo.io's official skills and hosted MCP server.

    Agent Plugins4 skills1 MCP server
  12. amplitude0stars

    Analyze Amplitude charts, dashboards, experiments, session replays, feedback, accounts, reliability, AI agents, taxonomy, and instrumentation through Amplitude's official skills and hosted MCP server.

    Agent Plugins32 skills1 MCP server
  13. alpaca0stars

    Research stocks, options, crypto, fixed income, indices, news, and corporate actions through Alpaca's official market-data MCP, with separately authorized paper and live trading servers for account, order, position, portfolio, and watchlist workflows.

    Agent Plugins1 skill3 MCP servers
  14. alation0stars

    Search and browse trusted Alation catalog context, query data products, inspect BI lineage, configure agents and tools, automate workflows, and curate governed metadata through Alation's official Codex skills and CLI.

    Agent Plugins7 skills
  15. airtable0stars

    Airtable is the database and operations layer for your agents — whether running product, marketing, sales, ops, HR, or a custom business app. It combines structured data with multiplayer visual surfaces (grid, kanban, calendar, gallery, timeline) humans and agents share — plus sync integrations to Jira, Salesforce, Zendesk, Google Drive, and Databricks. Makes Codex fluent in Airtable: bases and schema, records, and collaboration UI. Bundles the official Airtable MCP server.

    Agent Plugins8 skills1 MCP server
  16. aiera0stars

    Search and analyze Aiera corporate events, transcripts, filings, company publications, equities, financials, broker research, Third Bridge content, and trusted web results through Aiera's official MCP server.

    Agent Plugins1 skill1 MCP server
  17. actively0stars

    Research and prioritize accounts using Actively's persistent Per-Account Agent intelligence, buying signals, prospect context, strategy, and next-best actions.

    Agent Plugins1 skill1 MCP server
  18. scientific-agent-skills0stars

    Ready-to-use scientific and research Agent Skills for biology, chemistry, medicine, and related workflows.

    Agent Plugins50 skills
  19. aeokit0stars

    Evidence-backed AEO audits, improvements, and observations.

    CodexClaude Code3 skills
  20. spreadsheets2stars

    Runtime-free basic Excel workflows using Artemis's normalized Office document service.

    Codex1 skill
  21. presentations2stars

    Runtime-free basic PowerPoint workflows using Artemis's normalized Office document service.

    Codex1 skill
  22. pdf2stars

    Runtime-free basic PDF workflows using Artemis's normalized Office document service.

    Codex1 skill
  23. documents2stars

    Runtime-free basic Word document workflows using Artemis's normalized Office document service.

    Codex1 skill
  24. watch2stars

    Unattended server & long-running task supervision — health checks, anomaly detection, auto-repair, multi-channel alerting. One YAML config per project, zero code changes to adopt.

    CodexClaude Code1 skill
  25. traceme2stars

    Local-first personal observability for Claude Code — token usage, cost, tool usage, daily reports, ActivityWatch integration

    Claude Code1 skill
  26. sharp-review2stars

    Post-feature sharp review — 3 parallel reviewers with schema enforcement, merge findings, sync task list

    CodexClaude Code1 skill
  27. rem2stars

    REM sleep for your Claude sessions — prune stale memory, crystallize learnings, maintain .claude/memory/ with timestamps and automatic eviction

    CodexClaude Code4 skills
  28. fabric2stars

    Multi-provider agent fabric — any agent (Claude / Codex / …) invoking, orchestrating, and handing off to models of any provider. One `call` primitive (task/review/agent/image modes) + fan_out + a minimal observe proxy that dissolves the Foundry-vs-tap conflict.

    CodexClaude Code2 skills1 MCP server
  29. evolve2stars

    Iterative TDD review→fix loop — critique, fan out fix agents, verify, gate hard calls to the human, keep tests green, commit per round

    CodexClaude Code
  30. cc-latex2stars

    LaTeX writing assistant — compile workflow, academic writing style, and word counting (texcount) for LaTeX documents

    CodexClaude Code2 skills
  31. cc-academia2stars

    Academic research toolchain — systematic literature review, manuscript peer review, and IEEE reviewer discovery, backed by a single deterministic Python library and an accumulating local scholarly database.

    CodexClaude Code4 skills1 MCP server
  32. zuke33stars

    Agent skills for Zuke, the code-first build automation system for Deno/TypeScript. Bundles zuke-setup (scaffold Zuke into a project) and zuke-write-build (author or edit a zuke.ts build).

    CodexClaude Code2 skills
  33. waa-independent-evaluation0stars

    Evidence-based independent evaluation with versioned output contracts and strict artifact-read-only boundaries.

    CodexClaude Code1 skill
  34. tandem19stars

    Edit and iterate on documents with any MCP-capable AI. Claude is the default and best-supported client today.

    Claude Code1 skill2 MCP servers
  35. slashwork-work2stars

    slashwork offloader. Interception is on by default: /work init authenticates (a bare /work with no token does the same), and from then on a PreToolUse hook routes self-contained subagent spawns to the offload network and returns the artifact in place, falling back to the local spawn on any miss. /work off pauses routing per project, /work on resumes it; a bare /work shows status and the dashboard.

    Claude Code1 skill
  36. slashwork-earn2stars

    slashwork earner. /earn init authenticates and scaffolds an earner agent folder with run settings (model, bypass_permissions, default_duration); a bare /earn runs the default duration, /earn <goal> holds the live task feed over SSE, claims offloaded subagent tasks the moment they land, runs each with the folder's configured agent, and a SubagentStop hook submits the artifact with token usage. Earn credits and a per-class score for accepted work.

    Claude Code1 skill
  37. livespec-orchestrator-beads-fabro0stars

    Beads/Dolt-backed implementation plugin for livespec. Exposes /livespec-orchestrator-beads-fabro:capture-impl-gaps, /livespec-orchestrator-beads-fabro:capture-spec-drift, /livespec-orchestrator-beads-fabro:capture-work-item, /livespec-orchestrator-beads-fabro:detect-impl-gaps, /livespec-orchestrator-beads-fabro:implement, /livespec-orchestrator-beads-fabro:list-plans, /livespec-orchestrator-beads-fabro:list-work-items, /livespec-orchestrator-beads-fabro:needs-attention, /livespec-orchestrator-beads-fabro:next, /livespec-orchestrator-beads-fabro:drive, /livespec-orchestrator-beads-fabro:plan.

    Claude Code
  38. livespec-orchestrator-beads-fabro0stars

    Beads/Dolt-backed implementation plugin for livespec. Exposes /livespec-orchestrator-beads-fabro:capture-impl-gaps, /livespec-orchestrator-beads-fabro:capture-spec-drift, /livespec-orchestrator-beads-fabro:capture-work-item, /livespec-orchestrator-beads-fabro:detect-impl-gaps, /livespec-orchestrator-beads-fabro:implement, /livespec-orchestrator-beads-fabro:list-plans, /livespec-orchestrator-beads-fabro:list-work-items, /livespec-orchestrator-beads-fabro:needs-attention, /livespec-orchestrator-beads-fabro:next, /livespec-orchestrator-beads-fabro:drive, /livespec-orchestrator-beads-fabro:plan.

    Codex12 skills
  39. project-workflow2stars

    Spec-driven project workflow for Codex and Claude Code with project initialization, feature specs, reviews, delivery gates, and spec lifecycle management.

    Codex9 skills
  40. project-workflow2stars

    Spec-driven feature development blueprint for AI-assisted coding (Claude Code-native). Skills: /project-init, /project-personalize, /feature-init, /spec-quality-check, /spec-revise, /feature-done, /feature-archive, /spec-reconcile, /agents-md-revise. Agents: agents-md-reviewer, spec-reviewer, spec-quality-reviewer, tech-researcher, codebase-explorer, decision-completeness-auditor.

    Claude Code9 skills
  41. xtctx0stars

    Local cross-tool handoff for AI coding agents. Read this project's transcripts from the other assistants you use.

    CodexClaude CodeAgent Plugins1 skill1 MCP server
  42. engram7kstars

    Persistent memory for AI coding agents. Survives across sessions and compactions.

    Codex
  43. engram7kstars

    Persistent memory for AI coding agents. Survives across sessions and compactions.

    Claude Code
  44. mefisto0stars

    Harness opinionado de Claude Code para construir aplicaciones serverless en Azure con Event Driven Architecture, Event Sourcing (Marten + Wolverine), Postgres y .NET 10. Incluye pipelines TDD, IaC, tooling, scaffolding y agentes/skills especializados.

    Claude Code2 skills1 MCP server
  45. brothermode0stars

    Turn an idea into a verified result with a guided start, honest forecasts, clear status, and a checked delivery. Verified on Claude Code; the plugin install is proven end to end by scripts/release-smoke-install.sh, and the tagged git clone remains the immutable option for auditors.

    Claude Code19 skills
  46. writer0stars

    Rewrites a Russian draft — a post, a chapter, a note — so it reads alive: finds the buried detail, restores scenes, kills dead verbs, fixes rhythm, keeps the author's voice. Tuned for LiveJournal and vc.ru.

    Claude Code1 skill
  47. skill-smith0stars

    Engineering discipline for Claude Code configuration: pick the right mechanism before writing anything, take the frontmatter from the live docs instead of memory, match the wording to the failure it fixes, and ship only after a static validator and a fresh-context trigger check.

    Claude Code1 skill
  48. second-opinion0stars

    Check a risky hypothesis against an independent LLM — DeepSeek, Gemini, GPT, Grok, or any model on OpenRouter — through one OpenAI-compatible script.

    Claude Code1 skill
  49. image-gen0stars

    Prompt to PNG on disk through OpenRouter — seedream, gpt-image, qwen-image — plus rembg background removal, with the prompting lore that makes the frames usable.

    Claude Code1 skill
  50. feature-pipeline0stars

    Route a feature through four stages — spec plus acceptance checklist, an outside opinion, implementation in another agentic harness (Grok Build or DeepSeek), and an independent verification — while the main context only orchestrates and never writes the code itself.

    Claude Code1 skill