Claude Skills by agentskillexchange

Run a self-hosted bridge so an operator can start, resume, approve, and review Codex or Claude Code sessions from a phone or tablet.

Give MCP clients hosted browser tools for scraping, crawling, structured extraction, search, and computer-use browser automation.

Use GO Feature Flag as an OpenFeature-compatible control plane for rollout rules, targeting, experiments, remote config, and launch verification.

Run Claude Code, Cursor CLI, Codex, and OpenCode sessions from a web or mobile UI when an operator needs remote access, project switching, terminal access, and browser-assisted agent work.

Connect MCP-compatible agents to Unity Editor so they can inspect scenes, manage assets, edit scripts, run tests, and automate game-development tasks.

Connect Terminator MCP to an agent so it can inspect and automate real Windows desktop and browser workflows with pixels, DOM, and accessibility context.

Use OCRFlux when agents need local PDF or image parsing into Markdown/JSONL with layout-aware OCR, table handling, and cross-page paragraph or table merging.

Use a local or private multimodal model to convert PDFs, Office files, scans, screenshots, charts, formulas, and diagrams into Markdown for agent search and reasoning.

Convert PDFs, scans, office files, images, and URLs into clean Markdown, structured JSON, CSV, or HTML before an agent ingests or reviews the content.

Run Docext locally or with a chosen model backend to turn PDFs and document images into structured Markdown for RAG, extraction, and review workflows.

Route identity, negotiation, delegated permissions, x402 payments, escrow, execution, and dispute review through one Claude Code skill for agent commerce deals.

Use CompozyOS as a local-first control plane for durable agent sessions, loops, approvals, shared memory, and web/CLI/API/MCP control surfaces.

Install Ruflo when an operator needs Claude Code or Codex agents to coordinate swarms, memory, hooks, and MCP tools across a bounded project workflow.

Define and supervise multi-agent coding rigs with declarative city configuration, runtime providers, work routing, formulas, waits, mail, and health patrols.

Run AionUi as a local cowork surface for coordinating built-in agents, Codex, Claude Code, OpenClaw, Gemini CLI, and other CLI agents across supervised files, tools, approvals, teams, and scheduled automation.

Run Claude Code, Codex, Cursor, OpenCode, Pi, and custom agents behind one governed orchestration layer with shared sessions, policies, and sandbox options.

Use Ouijit to manage parallel CLI coding-agent tasks with per-task git worktrees, integrated terminals, lifecycle hooks, and sandboxed sessions.

Run Codex, Claude Code, OpenCode, Pi, and similar coding agents side by side in isolated worktrees, then compare, annotate, and merge the best result.

Let Claude Code, Codex, Gemini CLI, Copilot CLI, and other terminal agents exchange messages through a shared local SQLite channel.

Use Termio's `termio sessions` CLI to list, watch, spawn, send to, read, and close sibling coding-agent sessions in one macOS project.

Use MetaGPT to turn a product requirement into coordinated product, architecture, project, and engineering agent outputs that an operator can review and iterate.

Use hcom to launch, message, watch, fork, and coordinate multiple terminal coding agents across Claude Code, Codex, Gemini, OpenCode, Cursor, and similar CLIs.

Run and monitor multiple coding agents from one terminal workspace, keeping panes, status, detach/reattach, and handoff context visible for operator review.

Use CCB to run Codex, Claude, Gemini, Cursor, OpenCode, and other CLI agents in a visible project workspace with configured panes, shared memory, role packs, and human takeover.

Use SandBase Multi-Source Search to fact-check claims across independent web and academic sources, record disagreements, score confidence, and validate a structured evidence ledger offline.

Provides Codex plugin skills for reviewed talking-head video editing: cut mistakes from source video and subtitles, finish a captioned deliverable, report bugs with confirmation, and check trusted plugin updates.

Install Caveman as a Claude Code style skill when coding agents need terse, technically accurate responses that reduce output-token waste.

Searches and enriches US property, owner, people, and company data through the DealMachine CLI and hosted MCP server for prospecting, lead generation, comparable-sales research, and targeted sales and marketing exports.

Run Axon as a local OpenTelemetry endpoint and dashboard for inspecting LangChain and instrumented agent traces without sending run data to a cloud service.

Use delegate-skills to discover implementer CLIs, create approved delegation lanes, dispatch bounded coding tasks, and review the returned diff before landing commits yourself.

Use Elves to hand a bounded development or research plan to a separate Claude Code or Codex worker while preserving run files, worktree safety, review gates, and human merge authority.

Build and run voice-first conversational agents by configuring telephony, ASR, LLM, and TTS providers behind a deployable orchestration service.

Use Unstract when an operator needs agents or automation pipelines to turn recurring PDFs, scans, and document batches into structured JSON through prompt-defined extraction workflows.

Define agents, model configs, and MCP tool servers as Kubernetes resources so cloud operators can run controlled infrastructure workflows in-cluster.

Use Agents Best Practices when an agent should produce concrete harness designs, permission models, memory plans, eval gates, or production-readiness audits.

Use Loop Engineering to scaffold, audit, and operate repeatable coding-agent loops with explicit state, budget, readiness, and tool-specific patterns.

Run a presentation-design workflow that turns a confirmed brief into editable PPTX output, rendered PNG previews, and revision loops before delivery.

Install Power BI and Microsoft Fabric plugins so Claude Code can author, validate, and review PBIP, TMDL, DAX, reports, semantic models, and related project files.

Use LinkedIn Skills when an agent needs to draft posts, comments, replies, audits, profile rewrites, or content plans while preserving explicit approval before publishing.

Use STORM to research a topic, build a multi-perspective outline, and generate a cited long-form draft for human review.

Use Rmux to create and automate cross-platform terminal sessions for agent CLIs, with tmux-compatible commands, typed SDKs, web sharing, and Claude Code teammate mode.

Use comfyui-mcp to let an MCP-capable agent author, run, debug, and manage ComfyUI image, video, audio, model, and custom-node workflows from natural-language instructions.

Add a JavaScript GUI agent to a web app so users or agents can complete UI tasks through natural-language commands without a headless browser.

Drop a multi-agent protocol pack into a project so coding assistants must satisfy reviewer, memory, and supply-chain gates before code-changing work completes.

Use Probity when Claude Code, Codex, or GitHub Copilot CLI should be blocked from unsafe file writes or shell commands before they happen.

Use Ring to load curated engineering skills and specialist agents for TDD, systematic debugging, code review, product planning, and technical writing across supported agent hosts.

Codify complex GitHub review rules, evaluate pull requests, and expose approval status as a required check.

Install cc10x as a Claude Code loop engine that routes complex work through specialist agents, reusable skills, durable workflow artifacts, and fail-closed review gates.

Run repeatable EvalScope benchmark suites for LLM, VLM, RAG, and agent workflows, then inspect traces and reports before changing models or prompts.

Run prompt experiments, testset evaluations, and observability reviews for production LLM workflows before regressions reach users.