Claude Skills by agentskillexchange

Use Nanobrowser when an operator needs a local Chrome or Edge browser agent to run multi-step web tasks with their own LLM keys and visible browser state.

Use Pi when an operator needs a local coding-agent CLI with explicit sandboxing, provider setup, and reviewable session artifacts.

Give coding agents isolated browser spaces that can use real logged-in state while the operator keeps normal tabs separate and reviewable.

Use LongHorizon-Harness to keep Claude Code, Codex, DeepSeek Harness, or custom agent backends working through long GUI and CLI tasks with verified state, role separation, checkpoints, and recovery loops.

Collect public discussion, coordinate specialist agents, and generate an evidence-backed public opinion report from one conversational analysis request.

Use OpenClaude when a repository task needs one terminal-first coding-agent workflow that can switch across cloud, local, Codex OAuth, MCP, slash commands, file tools, and background sessions.

Use jcode as a local coding-agent harness for long-running, multi-session repository work with custom provider and memory configuration.

Use Kilo Code as an open-source coding agent across VS Code, JetBrains, CLI, cloud runs, and trusted CI workflows with custom agents, MCP tooling, model switching, and review/debug modes.

Use UI-TARS Desktop when an operator needs a local or remote GUI agent to drive desktop, browser, and computer-use tasks with multimodal model support.

Deploy OpenChatBI when an agent needs to turn business questions into SQL, charts, anomaly analysis, and explainable BI results.

Use Qwen Code as a repeatable terminal coding agent: install the CLI, authenticate a provider, run interactive or delegated coding sessions, and connect skills, MCP servers, subagents, and sandboxed workflows when the operator needs an open-source agent runtime.

Install opencode-power-pack so OpenCode can run Claude Code-style review, security, feature-development, frontend-design, MCP-building, skill-authoring, and project-memory workflows from one maintained plugin.

Install an OpenCode orchestration plugin that routes codebase work across specialist agents, background tasks, model presets, bundled skills, and live terminal multiplexers.

Use ADHD to fan out isolated reasoning branches for open-ended coding-agent decisions, then score, prune, and deepen the strongest options.

Install a maintained skill pack for weekly planning, retrospectives, task routing, department setup, and founder-ops workflows across Claude Code and Codex.

Install a multi-skill operator pack for decisions, research, second-brain work, content rotation, financial cadence, project management, and skill authoring.

Use AgentSys to install and run structured coding-agent pipelines for task discovery, delivery preparation, drift checks, review, release, and shipping.

Use Text Extract API when an agent needs to turn PDFs, Office files, or images into Markdown or structured JSON with local OCR, optional Ollama models, PII removal, and queued batch processing.

Install a .NET skill and agent pack for C#, ASP.NET Core, Aspire, EF Core, Akka.NET, testing, performance, and quality-gate workflows.

Use FuXi when an operator wants a terminal coding agent to edit code, run commands, drive tools, and verify changes with cost-aware routing across LLM providers.

Ingest a bounded document set into Verba, configure retrieval and model providers, then review grounded chatbot answers before handing context to an agent workflow.

Install a maintained marketing skill library so agents can run scoped SEO/GEO, email, paid ads, influencer, launch, social, and brand narrative workflows with shared quality gates.

Use hax as a lightweight terminal-native coding agent for local-model, provider-backed, or Unix-composed code workflows where low overhead and inspectable transcripts matter.

Use Khoj to connect private knowledge and web sources, create a custom agent, and schedule recurring research or notification workflows.

Use Sidekiq Scheduler to run recurring Ruby/Sidekiq agent jobs for refreshes, evaluations, reports, maintenance, and queue-driven automations with cron-style schedules.

Use IronClaw Reborn as a secure local agent runtime for model-routed CLI, REPL, and WebUI sessions with explicit state, policy, storage, and secret boundaries.

Use Codeman to supervise persistent Claude Code, Codex, OpenCode, and Gemini CLI sessions through a self-hosted web dashboard with live terminals and API controls.

Use tldw_server when an agent workflow needs to ingest video, audio, documents, and web pages into a local research layer with RAG, evals, OpenAI-compatible APIs, and MCP access.

Coordinate multiple coding agents in one local-first workspace with shared memory, tools, files, browser access, and MCP-backed integrations.

Use Social Media Research Skills when an agent needs to find outlier posts, mine comments, compare competitors, inspect ad libraries, and turn public social data into cited marketing research artifacts.

Use OSpec to turn a coding request into a repo-persisted spec workflow with initialization, change advancement, verification evidence, and archival.

Turn rough coding intent into durable specs, task graphs, fresh-context worker runs, adversarial reviews, PR bodies, and evidence receipts.

Use MoAI-ADK to install Claude Code agents and skills for spec-first implementation, TDD, DDD, and quality-gated development.

Use Ouroboros when a coding agent should turn a vague request into a replayable spec, execute it across supported runtimes, and pass explicit evaluation gates.

Use Council of High Intelligence when an agent should convene a structured panel, force disagreement, and return a decision with dissent, kill criteria, and next actions.

Install StyleSeed skills so coding agents choose a design grammar, build UI with project-local rules, score the result, and verify rendered screens before handoff.

Install Suede Creator Skills when an agent needs repeatable Codex, Claude Code, or MCP-backed workflows for orchestration, code review, ship gates, AI evals, design, copy, SEO, app packaging, creator rights, and recovery audits.

Give an MCP-capable agent a local Playwright browser with human takeover, reusable auth profiles, approvals, audit trails, and repeatable browser workflow evidence.

Start a bounded Suna or Kortix agent session, let it use browser, files, tools, and connectors, then review the session output before delivery.

Use Empryo when a coding agent should map symbols, blast radius, and dependencies before making AST-backed edits across a repository.

Use the Fable Method skill bundle to classify work, gather evidence, act narrowly, verify by observation, and judge agent outputs against repeatable eval-backed rules.

Use Evalite when a TypeScript team needs repeatable Vitest-style eval runs for LLM apps before prompt, model, or workflow changes ship.

Use Pneuma Skills when Claude Code, Codex, or Kimi should build slides, documents, diagrams, videos, dashboards, or custom modes in real files while a human reviews and edits through a live visual workspace.

Use Cronicle to schedule, run, monitor, and manually trigger recurring agent maintenance jobs across one or more worker servers from a web UI and REST API.

Build and run Python agents that execute tasks against an explicit workspace, with tools, MCP connections, and prebuilt agent packages available when needed.

Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbase_discover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the user already has one.

Use Metaharness to score a repository, generate a branded agent harness with CLI, MCP, memory, and safety defaults, then package it for repeatable team use.

Use Milvus to create vector collections, ingest embeddings, and serve filtered similarity search for RAG and agent retrieval workloads.

Run OWASP dep-scan before adopting dependencies, containers, or generated code so agents get a reviewable vulnerability, license, SBOM, and risk report.

Use SkillSpector to scan Claude Code, Codex, Gemini, MCP, and other agent skills for vulnerabilities, malicious patterns, prompt injection, data exfiltration, and supply-chain risk before installation.