Claude Skills by agentskillexchange

Use Code Context Engine to index a repository and expose token-efficient code search to Claude Code, Codex, Cursor, Gemini CLI, Copilot, OpenCode, and other MCP-capable agents.

Give coding agents a local MCP code intelligence graph for fast architecture, symbol, route, impact, and call-path queries across large repositories.

Use Socraticode to give coding agents a local codebase-intelligence layer for semantic search, dependency graphs, impact analysis, and call-flow investigation.

Use Chubbyskills when an agent needs installable skills for collecting Chinese social, video, podcast, and article content into Markdown and Obsidian-style knowledge bases.

Use Bull Board to add a protected dashboard for Bull and BullMQ queues so operators can inspect, retry, pause, clean, and debug background agent jobs.

Connect PDF Reader MCP when an agent needs source-backed PDF extraction with page evidence, visual crops, OCR provenance, tables, trust reports, and reviewable citations.

Add a Claude Code team scaffold with defined roles, stage gates, mandatory skills, blocking hooks, and Definition of Done checklists for app delivery.

Add a large source-backed cybersecurity skills library to Claude Code, Codex CLI, Cursor, Gemini CLI, and other agents so security investigations follow structured analyst playbooks.

Use claude-code-skills-zh to install Chinese-language Claude Code skills for repeatable code review, README writing, API testing, refactoring, dependency auditing, and performance profiling workflows.

Use superpowers-zh to install Chinese-localized coding-agent methods, China-specific development skills, and cross-tool setup for Claude Code, Codex, Cursor, Gemini CLI, OpenClaw, and related assistants.

Use headcount to install focused Claude Code department plugins and invoke repeatable specialist workflows across business, engineering, security, finance, product, and operations work.

Add Claude Forge's agents, slash commands, skills, and hooks to Claude Code when a coding task needs repeatable planning, review, and adversarial verification loops.

Add Codex commands, skills, hooks, diagnostics, and sub-agent roles for deep repository initialization, planning, execution, and evidence-backed completion.

Use GitHub Next's CI Doctor workflow to watch GitHub Actions runs, pull failure logs, trace recurring patterns, and open investigation issues with concrete next steps. This is for agents acting as CI failure investigators, not for listing GitHub Agentic Workflows as a product.

Connect agents to Monoscope so they can query logs, traces, metrics, monitors, and issues through stable JSON CLI output or MCP tools for incident triage.

Paid x402 HTTP-402 endpoints on Base mainnet that let agents pay-per-call in USDC for web search, AI analysis, crypto and stock market data, SEC filings, company intelligence, news, sentiment scoring, and a macro dashboard. 25 endpoints priced $0.001-$0.15/call, returning JSON. The proxy fronts local LLM inference and public data APIs so an agent can fetch grounded market, filings, and news data without API keys, charging micropayments via the x402 facilitator protocol.

Diagnose why a local Node, Python, Go, or Docker project will not start by checking runtimes, dependencies, ports, environment-key presence, permissions, and required services before changing application code.

Install and maintain a shared .agent layer so coding agents can carry memory, skills, protocols, dashboards, and bounded loop contracts across multiple agent harnesses.

Use Haft when an agent needs source-backed decision framing, comparison, authorization records, and stale-evidence checks across supported coding-agent hosts.

Ponytail gives coding agents a portable minimal-implementation ruleset, plugin hooks, and review commands so they reuse existing code, native platform features, and standard library behavior before writing new abstractions.

Initialize Git-native project memory that Claude Code, Codex, Cursor, Gemini CLI, and compatible coding agents can recall deterministically.

Connect Bdash's SQL workspace to MCP clients so an agent can list configured data sources and write SQL into the active query editor for supervised analysis.

Use Open Agent Hub to install, link, and enable reusable skills, agent roles, and slash commands across Claude Code, Codex, Cursor, Gemini, Trae, and related assistants.

Give Claude Code, Codex, or OpenCode live access to Google Search Console and GA4 data through RefreshAgent. Provides authenticated GSC queries, keyword positions, sitemap status, cannibalization detection, and analytics without manual GCP OAuth setup.

An ASE skill built around the official Mailgun JavaScript SDK for sending email and managing Mailgun API workflows from Node.js. It fits agent tasks that need transactional messaging, domain-aware email operations, event handling, and direct integration with the Mailgun platform.

Use Okf Skills to have Claude Code produce, validate, migrate, and visualize Open Knowledge Format bundles with provenance, trust, staleness, and CI checks.

Use mex when coding agents need a versioned project wiki, code graph, routed context, and drift checks instead of rediscovering a repo every session.

Use CAPA to declare coding-agent skills, rules, tools, MCP servers, sub-agents, and plugins once in capabilities.yaml, then install native provider files across Cursor, Claude Code, Codex, Windsurf, Copilot, Gemini CLI, and related agents.

Use the Baidu Netdisk storage skill to upload, download, transfer, share, search, move, copy, rename, and list cloud files from natural-language agent sessions.

Use Claude Code Tools when an operator needs installable CLI utilities, hooks, skills, and plugins for session management, tmux control, context handling, local safety checks, and cross-agent productivity workflows.

Use Agentfiles when an operator wants to browse, create, edit, install, and audit skills, commands, agents, rules, memories, and coding-session artifacts across multiple AI coding tools from Obsidian.

Use Skills Manager when an operator needs one auditable library for installing, inspecting, tagging, syncing, backing up, and deploying agent skills across many coding tools.

Run Claude Code, Codex CLI, Gemini CLI, Cursor Agent, Copilot CLI, Cline CLI, OpenCode, Kimi CLI, and related coding assistants from one worktree-aware terminal manager.

Use Agent of Empires to launch, monitor, sandbox, resume, and review multiple coding-agent sessions from a TUI or web dashboard.

Run a reviewable resume-to-job-description matching workflow that produces ATS-style gaps, keyword suggestions, and human-checkable resume improvements.

Route model calls through Helicone, inspect costs, latency, traces, prompts, and evaluations, then review changes before they ship.

Install Claude Code hooks that stream session, tool, subagent, and workflow events into a local dashboard for live observability and review.

Use TrendRadar when an operator needs a self-hosted trend monitor that filters multi-platform feeds, summarizes signals with AI, sends alerts, and exposes trend analysis through MCP.

Run a local read-only terminal dashboard for Claude Code, Codex CLI, and OpenCode sessions to watch tokens, context, rate limits, child processes, and orphan ports.

Use ClawMetry when an operator needs a local dashboard for agent sessions, token spend, tool calls, alerts, and governance across multiple runtimes.

Collect local telemetry from Claude Code, Codex, Cursor, OpenClaw, OpenCode, and related coding agents, then inspect token usage, tool calls, sessions, and traces from one local dashboard or OpenTelemetry pipeline.

Review a PR or diff through three independent focused lenses (correctness, security, test coverage), then deduplicate and validate findings before persisting. Catches more real bugs than a single general review pass while producing less noise.

Use Eigent when an operator needs a local desktop agent workforce that can coordinate developer, browser, document, multimodal, model-provider, and MCP-backed work in one controlled environment.

Run gptme as a terminal-first autonomous agent that can edit files, execute commands, browse the web, and keep local project context.

Let agents ingest sources, update Obsidian notes, reconcile contradictions, search vault context, and maintain a living knowledge base through documented commands.

Run Bifrost as an OpenAI-compatible gateway so agents can route model calls across providers with failover, load balancing, caching, and governance.

Give Emacs users one workflow layer for Codex, Claude Code, Gemini CLI, Cursor CLI, opencode, and other coding-agent backends.

Use Mission Control Jobs when an operator needs a Rails-mounted dashboard to inspect Active Job queues, review failed jobs, and retry or discard jobs with supervision.

Use Rasa to design, test, and operate custom conversational assistants for support, service, and voice workflows.

Use Coze Loop to evaluate, debug, and improve agent prompts and workflows across development iterations.