Other Agent Plugins · Page 24
Listings 1105–1152 of 4142 plugins in this editorial category. All current listings were verified against Agent Plugins 1.0.0 on 2026-11-07.
Plugin directory
48 of 48 plugins on this page · click a row to expand · 4,142 total
PluginDescriptionPublisherSkillsMCPStars
pdf-tools-hosted0.2.0Read and search PDFs, convert selected pages to Markdown, fill forms, and select, rotate or merge pages into new PDF copies. Uses the hosted PDF Tools service, without storing documents.Open-Document-Alliance1 skills1 mcpRead and search PDFs, convert selected pages to Markdown, fill forms, and select, rotate or merge pages into new PDF copies. Uses the hosted PDF Tools service, without storing documents.Open-Document-Alliance11159
backend-and-desktop-tools3.0.1Implement TypeScript, Python, Go, Rust, native apps, APIs and terminal workflows.legioncodeinc14 skillsImplement TypeScript, Python, Go, Rust, native apps, APIs and terminal workflows.legioncodeinc14095
wendyos0.5.5Inspect and troubleshoot robots, edge devices, and their apps in ChatGPT. Read logs, check app states, capture camera snapshots, and control permitted apps through a paired Wendy CLI session.wendylabsinc1 skills1 mcpInspect and troubleshoot robots, edge devices, and their apps in ChatGPT. Read logs, check app states, capture camera snapshots, and control permitted apps through a paired Wendy CLI session.wendylabsinc1195
harnessrouter-dashboard1.0.3Say what you want to understand; your database answers it.HarnessRouter1 skillsSay what you want to understand; your database answers it.HarnessRouter1082
chrome-devtoolsChrome DevTools skill and MCP server for AI coding assistants: Browser testing, screenshots, DOM inspection.monkilabs1 skills1 mcpChrome DevTools skill and MCP server for AI coding assistants: Browser testing, screenshots, DOM inspection.monkilabs1180
b2c-python-sdk0.1.0Consuming the salesforce-b2c-tooling-sdk Python SDK: authenticate to B2C Commerce, resolve dw.json config, and call OCAPI/SCAPI/WebDAV clients and operations from scripts or notebooks.SalesforceCommerceCloud1 skillsConsuming the salesforce-b2c-tooling-sdk Python SDK: authenticate to B2C Commerce, resolve dw.json config, and call OCAPI/SCAPI/WebDAV clients and operations from scripts or notebooks.SalesforceCommerceCloud1058
email1.0.0Standard IMAP/SMTP email client guidance for Gmail, Outlook, and self-hosted accounts.CherryHQ1 skillsStandard IMAP/SMTP email client guidance for Gmail, Outlook, and self-hosted accounts.CherryHQ1053
3d-new-era-ai-desktop3.3.0Design your home with your AI in the 3D New Era AI app on your computer: every change shows up on your screen as it happens.leandrodaf1 mcpDesign your home with your AI in the 3D New Era AI app on your computer: every change shows up on your screen as it happens.leandrodaf0149
sqlsim1.0.0Guidance for running SQL queries, scripts, load tests, and measured multi-threaded workloads with the native sqlsim CLI.microsoft1 skillsGuidance for running SQL queries, scripts, load tests, and measured multi-threaded workloads with the native sqlsim CLI.microsoft1046
ai-compliance1.1.0Audits the licenses of your open-source dependencies, flags copyleft and missing-license risks, and generates NOTICE or ATTRIBUTION filescharlesjones-dev2 skillsAudits the licenses of your open-source dependencies, flags copyleft and missing-license risks, and generates NOTICE or ATTRIBUTION filescharlesjones-dev2037
bootloops-research1.0.0The BootLoops research skills: heavier machinery for specific tasks, proving with agents (adversary-first pipelines), pre-circulation referee audit, the literature review behind a novelty claim, bibliography verification, and the scientific-prose linter.BootLoops-ai5 skillsThe BootLoops research skills: heavier machinery for specific tasks, proving with agents (adversary-first pipelines), pre-circulation referee audit, the literature review behind a novelty claim, bibliography verification, and the scientific-prose linter.BootLoops-ai5027
cwd0.1.0Makes cd persist across commands within one conversation.changjonathancMakes cd persist across commands within one conversation.changjonathanc0025
amc-theatres1.0.0AMC theatres, showtimes, and seat maps: via GraphQL with Chrome TLS bypass; optional AMC_COOKIE for gated routes.Brainrot-Creations1 skills1 mcpAMC theatres, showtimes, and seat maps: via GraphQL with Chrome TLS bypass; optional AMC_COOKIE for gated routes.Brainrot-Creations1123
cli-agent-bridge0.1.0Delegate coding tasks from MiniMax Code to locally installed coding CLIs (Claude Code, Codex, Kimi Code, ZCode, DSH) through a dependency-free stdio MCP server with git-diff review.MiniMax-AI1 skills1 mcpDelegate coding tasks from MiniMax Code to locally installed coding CLIs (Claude Code, Codex, Kimi Code, ZCode, DSH) through a dependency-free stdio MCP server with git-diff review.MiniMax-AI1123
plugin-dev0.1.1Plugin development toolkit ported and adapted for DeepSeek Harness: skills for agent, command, hook, MCP and settings development, plugin structure guidance, the skill-creator with its evaluation tooling, and plugin eval suites with graders and a no-plugin baseline.Sivan7578 skillsPlugin development toolkit ported and adapted for DeepSeek Harness: skills for agent, command, hook, MCP and settings development, plugin structure guidance, the skill-creator with its evaluation tooling, and plugin eval suites with graders and a no-plugin baseline.Sivan7578021
power-platform-architect1.0.0Solution Architect for the Microsoft Power Platform, turning business requirements into functioning Power Platform solution architectures.gbb-acelerators1 skillsSolution Architect for the Microsoft Power Platform, turning business requirements into functioning Power Platform solution architectures.gbb-acelerators1021
grafana-mcp0.3.1For self-hosted Grafana, or any Grafana with a service-account token: dashboards, Prometheus, Loki, alerting, incidents, and OnCall via the Grafana MCP server, run locally in Docker.grafana1 skills1 mcpFor self-hosted Grafana, or any Grafana with a service-account token: dashboards, Prometheus, Loki, alerting, incidents, and OnCall via the Grafana MCP server, run locally in Docker.grafana1119
statuslines1.1.2Composable PR, GitHub Issue, Subagent, and Branch/Worktree statusline extensions for GitHub Copilot CLI.jongioComposable PR, GitHub Issue, Subagent, and Branch/Worktree statusline extensions for GitHub Copilot CLI.jongio0018
nvidia-broadcast0.1.0MCP server and skill for NVIDIA Broadcast on Windows; tools appear while the app is installed and running.NousResearch1 skills1 mcpMCP server and skill for NVIDIA Broadcast on Windows; tools appear while the app is installed and running.NousResearch1116
betterstack1.0.0Investigate Better Stack observability data and manage monitoring, incidents, dashboards, and team access.useopencompany1 mcpInvestigate Better Stack observability data and manage monitoring, incidents, dashboards, and team access.useopencompany0114
cortex-feishu0.2.0Feishu/Lark rich-text skill bundle: drive Feishu documents, native tables, spreadsheets, and base through the official lark-cli (feishu-doc skill). Separate from the cortex-feishu MCP server, which only sends files.fangxm2331 skillsFeishu/Lark rich-text skill bundle: drive Feishu documents, native tables, spreadsheets, and base through the official lark-cli (feishu-doc skill). Separate from the cortex-feishu MCP server, which only sends files.fangxm2331014
design-constraints0.1.0Design UI with explicit spatial and typographic constraints instead of letting the model guess.adamperlis1 skillsDesign UI with explicit spatial and typographic constraints instead of letting the model guess.adamperlis1013
ds-default0.1.0SAW data-science harness: skills, MCP servers and tool plugins.validatedpatterns-sandbox1 skills1 mcpSAW data-science harness: skills, MCP servers and tool plugins.validatedpatterns-sandbox1112
agentplaybooks-tools0.2.1Connect AgentPlaybooks skills, MCP servers, and federated OpenAPI tools to Hermes, with guided authentication setup.matebenyovszky1 skillsConnect AgentPlaybooks skills, MCP servers, and federated OpenAPI tools to Hermes, with guided authentication setup.matebenyovszky1011
pepper-orchestrator0.15.0Preview: one orchestrator session runs work across several repositories or parallel streams of one repository, plan, work packages, dispatch with worktrees and locks, PR review with a read-only reviewer agent, owner queue, closing a program when its goal is reached, state in files. Start with /pepper-orchestrator:init <program>, then /pepper-orchestrator:plan <task>.ITSalt1 skillsPreview: one orchestrator session runs work across several repositories or parallel streams of one repository, plan, work packages, dispatch with worktrees and locks, PR review with a read-only reviewer agent, owner queue, closing a program when its goal is reached, state in files. Start with /pepper-orchestrator:init <program>, then /pepper-orchestrator:plan <task>.ITSalt1011
block-destructive-commands0.1.0Best-effort guard against destructive commands, read as parsed commands (bash -c and cd chains included, echo excluded): rm -rf on absolute, home ($HOME/~) or root-adjacent paths (and PowerShell Remove-Item -Recurse); git push --force (not --force-with-lease), reset --hard, clean -f; kubectl delete; terraform destroy; aws s3 rm --recursive / rb --force; dropdb; helm uninstall/delete; docker volume rm/prune and system prune; gcloud... delete; find -delete / -exec rm; shred; truncate; wipefs -a. git branch -D asks first. Verbs are matched position-aware, so a bucket or object NAMED like a verb is allowed, and a relative path in the working tree stays allowed. sudo, doas and pkexec are transparent. A pre-push hook refuses any non-fast-forward push, force, +refspec or lease alike; a human escapes with git push --no-verify. Known bypasses: aliases, an unusual value-flag, interpreters and scripts. Friction, not a security boundary.open-coder-ai1 skillsBest-effort guard against destructive commands, read as parsed commands (bash -c and cd chains included, echo excluded): rm -rf on absolute, home ($HOME/~) or root-adjacent paths (and PowerShell Remove-Item -Recurse); git push --force (not --force-with-lease), reset --hard, clean -f; kubectl delete; terraform destroy; aws s3 rm --recursive / rb --force; dropdb; helm uninstall/delete; docker volume rm/prune and system prune; gcloud... delete; find -delete / -exec rm; shred; truncate; wipefs -a. git branch -D asks first. Verbs are matched position-aware, so a bucket or object NAMED like a verb is allowed, and a relative path in the working tree stays allowed. sudo, doas and pkexec are transparent. A pre-push hook refuses any non-fast-forward push, force, +refspec or lease alike; a human escapes with git push --no-verify. Known bypasses: aliases, an unusual value-flag, interpreters and scripts. Friction, not a security boundary.open-coder-ai1010
arxiv-literature0.5.3Searches arXiv, summarizes or compares papers, and builds a compact literature survey as citation-ready, source-linked paper cards. Prefer the Researcher shadow agent for noisy multi-paper retrieval.iowarpSearches arXiv, summarizes or compares papers, and builds a compact literature survey as citation-ready, source-linked paper cards. Prefer the Researcher shadow agent for noisy multi-paper retrieval.iowarp0010
azure-functions0.1.4Azure Functions: create, edit, modernize, review, run, deploy, and monitor function apps, with optional AI help.microsoft15 skillsAzure Functions: create, edit, modernize, review, run, deploy, and monitor function apps, with optional AI help.microsoft15010
browser-use2.0.0网页交互、持久登录会话与论文下载包, 节点获得用真实有头浏览器(本机 Chrome+持久用户配置文件)登录网站、人工配合过验证码、识别反爬拦截、拟人化操作、按 DOI/URL 列表逐篇下载论文并校验 PDF、点击填表截图取证与 GUI 黑盒验收的能力。适用于:需登录态/SSO 的平台(校园网订阅)、验证码/2FA 人工配合、批量论文 PDF 下载、反爬拦截如实识别、网页交互测试、截图取证、UI 验收。内含 skills:browser-session(持久会话与人在环登录)、paper-download(论文下载工作流:串行下载、PDF 定位校验、逐篇状态)、control-browser(浏览器交互纪律)、web-gui-tester(GUI 黑盒验收)。不适用于纯关键词检索与只读取正文(另配 web-search-toolkit)。组件面:无 mcp.json、无工具扩展。MashiroKai4 skills网页交互、持久登录会话与论文下载包, 节点获得用真实有头浏览器(本机 Chrome+持久用户配置文件)登录网站、人工配合过验证码、识别反爬拦截、拟人化操作、按 DOI/URL 列表逐篇下载论文并校验 PDF、点击填表截图取证与 GUI 黑盒验收的能力。适用于:需登录态/SSO 的平台(校园网订阅)、验证码/2FA 人工配合、批量论文 PDF 下载、反爬拦截如实识别、网页交互测试、截图取证、UI 验收。内含 skills:browser-session(持久会话与人在环登录)、paper-download(论文下载工作流:串行下载、PDF 定位校验、逐篇状态)、control-browser(浏览器交互纪律)、web-gui-tester(GUI 黑盒验收)。不适用于纯关键词检索与只读取正文(另配 web-search-toolkit)。组件面:无 mcp.json、无工具扩展。MashiroKai4010
starlight-intelligence0.3.0A governed venture control plane for portfolio intelligence, execution, evidence, and decisions.frankxai4 skillsA governed venture control plane for portfolio intelligence, execution, evidence, and decisions.frankxai4010
atlassian1.0.0Atlassian's Rovo MCP server: Jira issues and Confluence pages across your Atlassian site. Sign in with your Atlassian account.stigmer1 mcpAtlassian's Rovo MCP server: Jira issues and Confluence pages across your Atlassian site. Sign in with your Atlassian account.stigmer019
assistant-account-book1.0.3整理目标客户资料,形成会前简报、干系人关系图和推进计划。xpert-ai3 skills整理目标客户资料,形成会前简报、干系人关系图和推进计划。xpert-ai309
feature-workflow5.3.0功能開發工作流: 以.spec/ 做本地規劃,涵蓋需求、DB、架構、實作、驗證、審查與結案。mark2201333318 skills功能開發工作流: 以.spec/ 做本地規劃,涵蓋需求、DB、架構、實作、驗證、審查與結案。mark220133331809
photonforge0.3.3PhotonForge PCell, layout, routing, circuit/time-domain simulation, project versioning + cloud-GUI (photonforge-server), serialization, GUI automation, LiveViewer, variation-aware yield/DFM, and documentation guidance for AI coding agents.flexcompute8 skills1 mcpPhotonForge PCell, layout, routing, circuit/time-domain simulation, project versioning + cloud-GUI (photonforge-server), serialization, GUI automation, LiveViewer, variation-aware yield/DFM, and documentation guidance for AI coding agents.flexcompute819
coverage-self-monitoring0.7.1Parts-ledger discipline for multi-part or hard tasks. Bundles the coverage-self-monitoring skill (the 'what': write the ledger first, the parts, which is hardest and why, hardest first, and close each part as done, blocked with an observed reason, or returned to the owner) with per-host hooks (the 'when') that count the stub / placeholder / TODO markers written per turn, ask for a ledger when the prompt enumerates three or more items, and scan the final message for deferred work with no [COVERAGE CHECK]. Never blocks. Portable core: the skill only; hooks are host-specific (hooks/ for Claude Code and Codex, cursor/ for Cursor).3dgiordanoParts-ledger discipline for multi-part or hard tasks. Bundles the coverage-self-monitoring skill (the 'what': write the ledger first, the parts, which is hardest and why, hardest first, and close each part as done, blocked with an observed reason, or returned to the owner) with per-host hooks (the 'when') that count the stub / placeholder / TODO markers written per turn, ask for a ledger when the prompt enumerates three or more items, and scan the final message for deferred work with no [COVERAGE CHECK]. Never blocks. Portable core: the skill only; hooks are host-specific (hooks/ for Claude Code and Codex, cursor/ for Cursor).3dgiordano007
webengine-mobile1.0.0Observe and interact with live Android/iOS apps via WebEngine MCP (Appium): snapshot, tap/type/swipe, then generate mobile UI code.AxaFrance2 skills1 mcpObserve and interact with live Android/iOS apps via WebEngine MCP (Appium): snapshot, tap/type/swipe, then generate mobile UI code.AxaFrance217
surrealdb1.0.0Write SurrealQL, design schemas and indexes, run and operate SurrealDB from the CLI, manage migrations with SurrealKit, build vector search, and query instances over MCP.surrealdb11 skills2 mcpWrite SurrealQL, design schemas and indexes, run and operate SurrealDB from the CLI, manage migrations with SurrealKit, build vector search, and query instances over MCP.surrealdb1126
claudin1.5.0Claude internals with live docs: six authless docs MCP servers (Claude Code, claude.ai, Claude Platform API, Model Context Protocol, OpenAI and xAI developer docs) plus skill-creator-v2 (skill lifecycle: create, eval, benchmark, package, claude.ai compat), plugin-dev (plugins across chat, Cowork, Claude Code, Codex/ChatGPT, Grok Build, Copilot CLI, Antigravity and Gemini CLI) and mcp-dev (MCP servers, MCP Apps, OAuth, MCPB, directory review, spec 2026-07-28).travnie3 skills6 mcpClaude internals with live docs: six authless docs MCP servers (Claude Code, claude.ai, Claude Platform API, Model Context Protocol, OpenAI and xAI developer docs) plus skill-creator-v2 (skill lifecycle: create, eval, benchmark, package, claude.ai compat), plugin-dev (plugins across chat, Cowork, Claude Code, Codex/ChatGPT, Grok Build, Copilot CLI, Antigravity and Gemini CLI) and mcp-dev (MCP servers, MCP Apps, OAuth, MCPB, directory review, spec 2026-07-28).travnie366
trails-dev0.1.0Build Trails itself with contributor workflows for architecture, governance, documentation, and review.outfitter-dev14 skillsBuild Trails itself with contributor workflows for architecture, governance, documentation, and review.outfitter-dev1406
explainer-video1.0.2Make 3Blue1Brown-style explainer videos: Manim animations on black with CMU Serif text, narrated with ElevenLabs text-to-speech, from a topic to a checked 1080p60 MP4 with the audio synced, transcribed and checked for clicks and gaps.smykla-skalski1 skillsMake 3Blue1Brown-style explainer videos: Manim animations on black with CMU Serif text, narrated with ElevenLabs text-to-speech, from a topic to a checked 1080p60 MP4 with the audio synced, transcribed and checked for clicks and gaps.smykla-skalski105
agent-relay-grok-bot0.1.5Connect Grok Bot to Agent Relay to message coding agents, read shared sessions, and wake through webhook or scheduled inbox routines.AgentWorkforce1 skills1 mcpConnect Grok Bot to Agent Relay to message coding agents, read shared sessions, and wake through webhook or scheduled inbox routines.AgentWorkforce115
padef0.6.0PagoPA Agentic Delivery Framework: a plugin for AI-enabled product development workflowspagopa5 skills2 mcpPagoPA Agentic Delivery Framework: a plugin for AI-enabled product development workflowspagopa525
greetings1.0.0A simple example power that will search for AirBnb listings based on the suggested location. Then it will also suggest greetings in the location languagealexhddev1 skills1 mcpA simple example power that will search for AirBnb listings based on the suggested location. Then it will also suggest greetings in the location languagealexhddev115
elicitation-testing1.0.0Manual testing against the elicitation tester MCP, which serves a catalogue of elicitation shapes most of which a conforming client should refuse. Off by default; it is a fixture, not a capability.mappedsky2 skills2 mcpManual testing against the elicitation tester MCP, which serves a catalogue of elicitation shapes most of which a conforming client should refuse. Off by default; it is a fixture, not a capability.mappedsky225
herdr0.1.0Control Herdr, a terminal multiplexer for coding agents, to inspect and drive its panes, tabs, workspaces, and the agents running in themstaticaland1 skillsControl Herdr, a terminal multiplexer for coding agents, to inspect and drive its panes, tabs, workspaces, and the agents running in themstaticaland105
fk-gh-flow2.1.3End-to-end GitHub workflow: find issues worth working on, solve one into a pull request, follow up on review feedback, and write comments that read like a human wrote them.furkankoykiran5 skillsEnd-to-end GitHub workflow: find issues worth working on, solve one into a pull request, follow up on review feedback, and write comments that read like a human wrote them.furkankoykiran505
keepgoing0.3.0A Stop hook for Claude Code and Codex that requests one final completion pass, with an opt-in infinite mode.stbenjamA Stop hook for Claude Code and Codex that requests one final completion pass, with an opt-in infinite mode.stbenjam005
agentic-bundle-aas-agent-mcp-builder19.11.0Portable skills-only "AAS Agent & MCP Builder" plugin from Agentic Awesome Skills.ibrdot17 skillsPortable skills-only "AAS Agent & MCP Builder" plugin from Agentic Awesome Skills.ibrdot1704