45 skills found · Page 1 of 2
openclaw / coding-agentDelegate coding tasks to Codex, Claude Code, or Pi agents via background process
openclaw / model-usageUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
anthropics / frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
anthropics / Writing Hookify RulesThis skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
anthropics / Agent DevelopmentThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
anthropics / Command DevelopmentThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
anthropics / Hook DevelopmentThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
anthropics / MCP IntegrationThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
anthropics / Plugin SettingsThis skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
anthropics / Plugin StructureThis skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
harrymunro / nelsonCoordinate agent teams in Claude Code using a Royal Navy inspired command structure and operating procedures. It provides structured sailing orders, battle plans, action stations, and a captain's log to manage complex tasks; from single-session work through to multi-agent squadrons.
ForteScarlet / codex-kkpA Claude Code Plugin that enables seamless integration with Codex AI Agent for code analysis, implementation, and collaboration tasks.
massimodeluisa / recursive-decomposition-skillClaude Code skill for handling long-context tasks through recursive decomposition
Rorogogogo / claude-cracks-the-whipClaude Code is the boss. Other AI agents are the workforce. Whip goes crack. A skill for dispatching tasks to AI coding agents (Codex, Gemini, Kimi, etc.)
Viniciuscarvalho / Feature-markerAI-powered feature development orchestrator — PRD → Tech Spec → Tasks → Implementation → Tests → PR — with checkpoint/resume, 5 execution modes, and auto-detection for GitHub/GitLab/Azure DevOps. Claude Code skill.
Ask-Ditto / ditto-product-research-skillClaude Code skill for running customer research, pricing tests, and product validation using Ditto's synthetic persona platform (300K+ AI personas, 92% overlap with real focus groups). Works with Claude Code and OpenAI Codex.
Ask-Ditto / ditto-political-pollingClaude Code skill: Run state-specific voter research, campaign messaging tests, and candidate perception studies using Ditto's 300K+ synthetic personas. For campaign managers and political consultants.
go-restream / aliyun-askThis is a specialized skill designed for Claude Code to query Alibaba Cloud resources using natural language. It supports retrieving information across various services such as ECS, RDS, VPC, SLB, OSS, and more.这是一个专为 Claude Code 设计的阿里云资源查询技能skill，通过自然语言查询阿里云资源信息，包括 ECS、RDS、VPC、SLB、OSS 等多种服务。
majiayu000 / planzManage hierarchical project plans in SQLite. Tree-based structure with phases and tasks. Multiple output formats (text, JSON, XML, markdown).
Keeeeeeeks / etudesYou have ideas but nothing shipped. Etudes fixes that. It interviews you about your project and how you work, detects your avoidance patterns (overplanning, idea-hopping, perfectionism), then generates a 5-day sprint with concrete daily tasks calibrated to your actual time and energy. Coaches you through check-ins, catches procrastination in real-time, and keeps you focused on the next checkbox until you ship. Triggers on: sprint, etudes, coaching, accountability, shipping, stuck, blocked, overwhelmed, procrastinating, too many projects.
Vedant9500 / frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
sacredvoid / ceo-assistantUse when working on any startup or business task - idea validation, financial modeling, pitch decks, market research, competitive analysis, fundraising, board updates, OKRs, hiring plans, go-to-market strategy, decision-making, or any CEO/founder operational need
0x-wzw / docker-sandboxDocker-based execution sandbox for secure agent task isolation. Adapted from DeerFlow's containerized execution model.
MessiasLima / jules-skillUse this skill whenever Jules (Google's async AI coding agent) is mentioned or implied. Triggers include: starting a new Jules coding task (\"kick off\", \"create a session\"), checking Jules session status or progress, reading a message Jules left, approving or rejecting a Jules plan, replying to Jules mid-task, and scanning for sessions in states like AWAITING_PLAN_APPROVAL or AWAITING_USER_FEEDBACK. Also triggers on bare Jules session IDs (long numeric strings) or any request to monitor, manage, or respond to Jules activity across repos.
Viniciuscarvalho / maestroIntelligent skill knowledge gateway. Routes tasks to the right knowledge without loading all skills into context. MUST be consulted before any coding task — call the search_skills MCP tool to retrieve relevant expertise from 100+ indexed skills covering Swift, SwiftUI, concurrency, testing, architecture, performance, and security.
dvald / chainlink-agents-hackathon-skillsVerifyMe Oracle workflow: scan a Moltbook submolt for claims, extract verifiable statements, gather evidence via web_search, run CRE consensus with 3 LLMs, and post verified results. Use when operator asks about verifying claims, scanning verify-me, running the oracle, or checking verification status.
natedemoss / token-surgeonThis skill should be used when the user wants to analyze, audit, optimize, or reduce tokens in a prompt, system prompt, or instruction set. Triggers on phrases like "analyze this prompt", "optimize my prompt", "too many tokens", "trim this prompt", "audit my system prompt", "token-surgeon", or when the user pastes a prompt and asks for feedback on efficiency.
0x-wzw / heartbeat-refinementRefined heartbeat scheduling with cleaner intervals, atomic task checkout, and goal ancestry tracking. Adapted from Paperclip's heartbeat principle.
kbarbel640-del / tick-md--- name: tick-md description: Multi-agent task coordination via Git-backed Markdown. Claim tasks, prevent collisions, track history with automatic commits. homepage: https://tick.md metadata: openc
damoli1103 / claude-code-project-bootstrapUse when setting up a new project for Claude Code development, creating a GitHub repo, adding hooks and guardrails to an existing project, or when the user asks about protecting files, blocking commands, enforcing builds before commits, or setting up git workflow automation with Claude Code.
