Skills Directory
Claude Skills by agentskillexchange
github.com/agentskillexchangeUse Gemini MCP Tool to let MCP-capable coding agents delegate large file and codebase analysis to Gemini or Antigravity CLI without leaving the agent workflow.
Use GoModel as an OpenAI-compatible and Anthropic-compatible gateway for routing, observability, failover, and cost tracking across model providers.
Use BitRouter as an agentic LLM gateway that routes model, tool, and sub-agent calls with scoped keys, cost policy, failover, telemetry, MCP gateway support, and loop guards.
Integrate agent applications with RouterBase as an OpenAI-compatible API gateway, including SDK base URL configuration, streaming, tool calling, JSON mode, retries, and safe API key handling.
Build RouterBase media generation workflows for image, audio, speech, and video tasks, covering endpoint selection, request schemas, polling, retries, asset storage, moderation, and failure handling.
Design RouterBase model routing policies for AI agents, including primary model selection, fallback chains, latency budgets, cost controls, rollout checks, and provider-specific capability notes.
Use COG to onboard a markdown-based second brain with agent skills for braindumps, briefs, reviews, research, product work, and verifier-backed workflows.
Use dev-3.0 to turn coding-agent work into isolated Kanban tasks with git worktrees, tmux sessions, live previews, multi-agent launches, and review handoff.
Use Aut Sci Write to let an agent search scholarly sources, download papers, extract PDF evidence, sync Zotero citations, and produce review or presentation artifacts.
Use Bug Hunter to run scan-first adversarial code audits where Hunter, Skeptic, and Referee agents check repository bugs, security issues, and fix evidence before any approved edits.
Use Notebook Intelligence to add chat, inline edit, autocomplete, MCP tools, Claude Code mode, and coding-agent launchers directly inside JupyterLab.
Use Claude Sidebar when an operator wants Claude Code, Codex, or another agent CLI available as terminal tabs inside an Obsidian vault with file and folder context.
Use Microsandbox to create local microVM-backed sandboxes for isolated execution of untrusted agent-generated code and tool calls.
Put pctx between agents and tools so MCP servers and custom tools can run through a code-oriented execution layer instead of one-off tool calls.
Use ASO Skills to run repeatable App Store keyword research, metadata optimization, competitor analysis, and growth planning from an agent session.
Add Axiom's Apple OS skills, agents, and commands so coding assistants can diagnose Xcode builds, Swift issues, crashes, logs, UI flows, and performance traces.
Guides Markdown-capable coding agents through large changes with deep analysis, intent refinement, task decomposition, GitHub issue tracking, batch PRs, adaptive control, and review workflows.
Use Guardian CLI to orchestrate authorized penetration tests with AI planning, tool selection, evidence capture, triage, and reporting across common security scanners.
RAPTOR turns Claude Code into an evidence-first offensive and defensive security research workflow for mapping attack surfaces, validating scanner findings, analyzing binaries, generating patches, and tracking project findings.
Use Zeroshot when a coding issue or spec needs an executor agent and an independent verifier loop before the change is accepted.
Use Autoprompt when an operator wants a coding agent to turn one goal into a planned, delegated, reviewed, and verified execution loop across supported agent runtimes.
Use bioSkills to give an agent domain-specific bioinformatics procedures, tool choices, and guardrails for omics analysis workflows.
Use Automa when an operator needs repeatable browser workflows for form filling, scraping, screenshots, or scheduled web tasks through a browser-extension block builder.
Bind a research profile to a FAROS blueprint and execute an AutoResearch chain from idea generation through experiment scaffolding, paper drafting, and reviewer simulation.
Build and run browser agents that combine deterministic Playwright-style actions with natural-language AI steps, hosted sessions, vault-backed credentials, and structured outputs.
Install and invoke a Chinese-first academic skill bundle for paper writing, editable Word/PPT research documents, and scientific computing tasks in Claude Code or Codex.
Use Career-Ops to run a repeatable Claude Code powered job-search workflow: evaluate listings, tailor resumes, generate applications, and review outputs before sending anything.
Install SecOpsAgentKit when a Claude Code session needs repeatable security review skills for SAST, DAST, container scanning, secrets checks, policy review, and remediation planning.
Use baoyu-design as a portable agent skill for local UI mockups, prototypes, decks, and design-system workflows that produce inspectable HTML artifacts.
Use the Claude Trading Skills pack to run structured market-regime checks, portfolio reviews, swing-trade screens, trade journals, and performance retrospectives inside Claude workflows.
Use CodeWhale as a local terminal coding agent for repository edits, test repair, provider-switched sessions, approval-gated commands, MCP tools, skills, and hooks.
Use ComfyUI Skills for OpenClaw when an agent needs to import, parameterize, route, and run repeatable ComfyUI workflows through a controlled CLI skill layer instead of manipulating raw node graphs.
Uses GRACE skills and the optional grace CLI to guide coding agents through contract-first code changes backed by .grace artifacts, graph navigation, lint gates, verification entries, and review workflows.
Connect business data sources to Minds Platform so an agent can search, analyze, and automate recurring operational work with inspectable data grounding.
Turns repeatable AI work into versioned YAML pipelines that can call Claude Code, Codex, Gemini CLI, Kimi Code, API models, tools, files, worktrees, and MCP-exposed workflows from the terminal.
Use dsh-cc-tui to run DeepSeek Harness coding-agent sessions from a full-screen terminal with live activity, context meters, session rewind, presets, model switching, file mentions, and MCP access.
Use Reasonix when an operator wants a persistent terminal coding agent tuned for DeepSeek-style prefix caching, project memory, MCP-compatible plugins, and reviewable code-edit runs.
Orchestrate parallel CLI coding agents in isolated git worktrees with reproducible scheduling, gates, replay journals, and optional tamper-evident audit receipts.
Use Dapr sidecars and workflows to give AI agents durable execution, state, messaging, approvals, and recovery across languages and platforms.
Embed gocron in Go-based agents or operators to run recurring tasks, cron expressions, one-time jobs, singleton executions, concurrency limits, and distributed leader-elected schedules.
Schedule recurring, interval, calendar, and one-off Python agent jobs with persistent job stores so background workflows survive restarts.
Use Agenda when a custom Node.js agent needs persistent scheduled jobs, retries, locking, and background workers backed by MongoDB, PostgreSQL, or Redis instead of fragile in-process timers.
Use eCommerce-Skills to give compatible agents plain-text workflows for product research, listing optimization, review analysis, pricing, marketing, supply-chain checks, and growth planning for online sellers.
Use Generative Media Skills when an agent should turn a creative brief into repeatable image, video, audio, product-ad, social-pack, storyboard, or brand-asset workflows backed by MuAPI CLI commands.
Use Genie to turn a vague coding request into Claude Code brainstorm, wish, work, and review loops backed by markdown plans and local SQLite state.
Use Academic Research Skills to guide Claude Code through research planning, literature review, drafting, review, revision, citation checks, and publication preparation.
Use OPC as a Claude Code skill to select a task flow, dispatch specialist roles, enforce independent review, and gate builds, audits, and release checks.
Use Obscura as a lightweight headless browser runtime for agent scraping, page inspection, parallel extraction, and CDP-driven Playwright or Puppeteer workflows.
Use Lark Coding Agent Bridge to connect Feishu or Lark chat threads to a local Claude Code or Codex CLI session with streaming cards, per-chat continuity, workspace switching, file handling, and controlled slash commands.
Index local or self-hosted documents, search them with hybrid and multimodal retrieval, and answer agent questions through an MCP server with citations.