Tools & Automation

CLI tools, utilities, converters, workflow automation, and productivity helpers

skills in category: 47,597
pages available: 1,984

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse tools & automation skills

Showing 3,865–3,888 of 47,597 skills

Browser Setup DevtoolsAGuide users through browser automation setup using Chrome DevTools MCP only. Use when the user asks to set up browser automation, Chrome DevTools MCP, browser MCP, or runs the browser-setup command.toolsgoVotes: 0GitHub stars: 3
Excel ReportACreate an auditable Markdown report for any uploaded Microsoft Excel (.xlsx) or CSV files in an Openrind Shell sandbox.toolspythongoVotes: 0GitHub stars: 3
Video DownloadBDownloads videos from YouTube, TikTok, Douyin, Bilibili, Instagram, XiaoHongShu and 1000+ platforms. Primary: yt-dlp. Fallback: agent-browser + GreenVideo for Douyin/TikTok when yt-dlp fails. Use when user says "download video", "save video", "grab video", "watermark-free download", or pastes a video URL. Do NOT use for AI video generation or video editing.toolsgobashVotes: 0GitHub stars: 12
Renoise SetupASet up, update, or diagnose Renoise on any agent host. Use when the user asks to install, upgrade, configure, connect, log in, check dependencies, enable the Renoise CLI, or fix missing RENOISE_API_KEY, ffmpeg, jq, yt-dlp, ImageMagick, or agent-browser.toolsrustgoVotes: 0GitHub stars: 12
Macos CleanupBUse when the user wants to free disk space on macOS, find leftover files from uninstalled apps, audit what is installed, or figure out why their Mac is slow or full. Scans every install surface (Homebrew, npm, .pkg installers, curl installers, language toolchains, app support data), proves what is actually used before suggesting anything, then removes only what the user confirms.toolspythonrustVotes: 0GitHub stars: 2
Vgp Repo BootstrapABootstrap or repair the standard Very Good Plugins agent-facing project surface: AGENTS.md as canonical, CLAUDE.md as @AGENTS.md, MIGRATING.md when renaming, GitHub hygiene (SECURITY, PR/issue templates, CODEOWNERS, dependabot), and product vs MCP naming discipline. Use when spinning up a new VGP repo, forking an upstream project, renaming product/CLI/skill identifiers, or when a repo still treats CLAUDE.md as the only agent contract. Trigger phrases: new project scaffold, agents.md bootstrap...toolsgogitVotes: 0GitHub stars: 2
Skills DirectorySkills Directory 3 slots · $399/mo · one ad per page · sponsors can never buy grades.See placements
Dev BrowserASandboxed throwaway-Chromium scripting via the upstream `dev-browser` CLI. Use ONLY for unauthenticated QA in a clean browser profile. For anything touching the user's real Chrome — the active tab, signed-in pages, filling forms, clicking, screenshotting "this page" — use the `browser-hand` skill instead.toolsjavascriptjavaVotes: 0GitHub stars: 2
Browser HandADrive the user's already-open, logged-in Chrome — forms, clicks, screenshots, evaluate, authenticated admin UIs and real cookies/tabs. Prefer this whenever work needs the normal Chrome profile (Gmail, GitHub, OAuth-backed sites, open tabs). Do NOT use for disposable headless pages or plain HTTP fetches. Trigger phrases: signed-in Chrome, logged-in browser, real session, existing tabs, cookies, fill this form on my browser, screenshot my account, use my Chrome, authenticated site, without remo...toolsgobashVotes: 0GitHub stars: 2
Review To PrAShips work that is implemented but not yet reviewed. Verifies it, commits it locally, has a reviewer with a fresh context review the change (a /code-review subagent in Claude Code, a separate reviewer CLI in Codex, Grok CLI or Copilot CLI), applies the fixes, re-verifies, and opens or updates the PR, so no /clear or second session is needed. Trigger on "/review-to-pr [--level <l>] [--model <m>] [--reviewer claude|codex|grok|copilot]", "review and ship this", "code-review it then open the PR",...toolsshellcode-reviewVotes: 0GitHub stars: 2
Factory Mcp UninstallATake Factory's MCP server back out of a coding agent's configuration — find where it actually is, remove the entry, and leave everything else alone. Use when the user asks to disconnect Factory from their agent, remove the Factory MCP server, or invokes /factory-mcp-uninstall. Not for removing Factory itself (that is `factory-uninstall`).toolsrustgoVotes: 0GitHub stars: 2
Factory Mcp InstallAPoint a coding agent at Factory's MCP server so it can create tasks, start workflows and read runs — choosing between every project on this machine and one repository. Use when the user asks to add Factory to their agent, connect Factory over MCP, or invokes /factory-mcp-install. Not for installing Factory itself (that is `factory-setup`).toolsgoshellVotes: 0GitHub stars: 2
Update StatusAThis skill should be used when the user wants to change the status of a job already in the tracker (List.xlsx), especially after a company responds. Triggers on phrases like "[company] called me back", "[company] replied", "got an interview with [company]", "move [company] to in progress", "set [company] to in progress", "mark [company] as done/applied again", "undo rejection for [company]".toolspythongoVotes: 0GitHub stars: 9
Arxiv 2609 30054 Sciwalker Synthesizing Scientific Coding Problems With Operator Graphs And Execution FeedbackASciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback (arXiv: 2609.30054)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30192 Sage Mitigating Long Horizon Reasoning Biases Via Topological GuidanceASAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance (arXiv: 2609.30192)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30123 Hexis Compiling Skills Into Extended Finite State MachinesAHEXIS: Compiling Skills into Extended Finite State Machines (arXiv: 2609.30123)toolsVotes: 0GitHub stars: 3
Arxiv 2609 29973 Learning Better Reasoning For Generative Recommendation With Semantic IdsALearning Better Reasoning for Generative Recommendation with Semantic IDs (arXiv: 2609.29973)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30074 How Reproducible Are Evaluation Conclusions A Self Audit Of Llm Inferred Prompt StructureAHow Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure (arXiv: 2609.30074)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30266 Llm Agents Can Easily Tamper With Their Own TracesALLM Agents Can Easily Tamper With Their Own Traces (arXiv: 2609.30266)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30249 Rapid Robot Agentic Programming From DemonstrationsARAPID: Robot Agentic Programming from Demonstrations (arXiv: 2609.30249)toolsapiVotes: 0GitHub stars: 3
Arxiv 2609 30233 Coding Agents For Generalized Task And Motion Planning ProblemsACoding Agents for Generalized Task and Motion Planning Problems (arXiv: 2609.30233)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30226 Poem Predicting Rl Outcomes From Existing PoliciesAPoEM: Predicting RL Outcomes from Existing Policies (arXiv: 2609.30226)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30186 Jev Mobile Jev As An Executor For Mobile Gui AgentsAJev-Mobile: Jev as an Executor for Mobile GUI Agents (arXiv: 2609.30186)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30147 Grasp Generating Revising And Assessing For Strategic Planning With Agentic AiAGRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI (arXiv: 2609.30147)toolsVotes: 0GitHub stars: 3
Arxiv 2609 30137 Screen Before You Serve Simulation For Production Customer Experience Ai Agents At 140m ScaleAScreen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale (arXiv: 2609.30137)toolsVotes: 0GitHub stars: 3