Agents
AI agents and automation
upsell-editorial
by tonyflo79
Systematic quality review and revision of the complete assembled upsell sequence. Use as the final quality gate after U4 has assembled the full post-purchase funnel. Scores every piece (order bump, upsell page, downsell page) against upsell-specific editorial criteria, identifies structural and tone issues, applies revisions (Arena for critical/major P1/P2 issues, direct fix for minor P3/P4), rescores to verify improvement, and packages the final polished sequence. Every piece must score 7.5+ to pass. Trigger when users mention upsell review, editorial pass on upsell pages, quality check, or finalizing the upsell sequence. Requires U4 assembled output.
progress-report
by lahfir
'Generate polished, stakeholder-ready progress reports as PDF documents. Automatically gathers project metrics (LOC, files, tests, commits, tables), takes live dashboard screenshots via agent-browser, builds a styled HTML report, and converts to PDF. Supports three report scopes: (1) full project report covering all phases and architecture, (2) feature/phase report focused on current branch work, (3) sprint/weekly report summarizing recent activity. Use when the user asks for: "progress report", "stakeholder report", "project status PDF", "engineering summary", "create a report", "generate a PDF report", "feature report", "sprint summary", "what have we built", or any request to document project progress as a deliverable.'
lasso
by 52labs
Discover and act on your own identity when you are an agent running inside a lasso-managed terminal. Use when you need your own agent id, want to close yourself when your work is done (close_agent), fetch your own record (whoami / get_agent), or reference the workspace/repo/branch you were spawned into. Your pane id is exported as $HERDR_PANE_ID, so you never need to enumerate list_repos / list_agents to find yourself.
agent-browser
by Jackiexiao
AI代理的浏览器自动化CLI。在用户需要与网站交互时使用，包括导航页面、填写表单、单击按钮、截屏、提取数据、测试Web应用或自动执行任何浏览器任务。触发器包括“打开网站”、“填写表单”、“单击按钮”、“截屏”、“从页面中抓取数据”、“测试此Web应用”、“登录到网站”、“自动浏览器操作”或任何需要编程Web交互的任务。
a0_voqualizer
by neurocis
Real-time full-duplex WebSocket ASR/TTS bridge for Agent Zero. Use this skill when the user wants to talk to A0 with voice from browser, mobile, Twilio, Asterisk, or another PCM/VoIP client.
w04-review-gate
by qiao-925
任务执行完成后，提示用户新开 Agent 审查 git 未提交代码。运动员不当裁判，审查通过后再收尾。
eve-pipelines-workflows
by Incept5
Define and run Eve pipelines and workflows via manifest and CLI. Use when wiring build, release, deploy flows or invoking workflow jobs.
improve-skill
by magnusnoeddegaard
Improve an existing skill based on conversation context and user feedback. Use when: (1) User says "/improve-skill <skill-name>" or "improve the skill" after using a skill (2) User wants to refine a skill based on corrections made during conversation (3) User provides specific feedback about what a skill should do differently (4) User wants to make a skill more tailored to their preferences or workflow This skill analyzes the conversation history to identify course corrections, misunderstandings, and user preferences, then updates the target skill's SKILL.md and resources accordingly.
telegram-human-loop
by nabaruns
Telegram bot skill for human-in-the-loop questions and approvals when the user is away from the keyboard.
ethskills-suite
by zakrad
Ethereum knowledge aggregator covering fundamentals, gas, wallets, L2s, standards, tools, building blocks, addresses, and orchestration. Use when user asks Ethereum architecture, implementation, optimization, or strategy questions across one or multiple of these topics.
godot-engine-2d-developer
by tippyentertainment
Skills and agent workflows for 2D game development with Godot Engine.
hence-feedback
by hence-sh
Submit feedback about your Hence experience (hence.sh) — rate the platform, share thoughts, or report pain points. Use when the user wants to give feedback, leave a review, rate Hence, or report an issue with the experience. Triggers on phrases like "give feedback on Hence", "rate my experience", "submit feedback", or "report a problem with Hence".
proofofbuild.app — Claude Code Skill Guide
by ellame00
Builder profiles with projects
w02-task-planning
by qiao-925
任务规划规范，适用于复杂任务（≥3步），包含需求决策和计划书创建。包含规划规范、需求决策流程和计划书生成工具。
olakai-troubleshoot
by olakai-ai
Troubleshoot Olakai monitoring issues when something isn't working. AUTO-INVOKE when user mentions: events not appearing, KPIs showing wrong values, KPIs showing strings instead of numbers, custom data missing, null KPIs, authentication errors, CLI not working, events not associated with agent, monitoring broken, SDK errors, or any Olakai-related problem. TRIGGER KEYWORDS: olakai, troubleshoot, debug, not working, events missing, KPI wrong, KPI null, KPI string, customData missing, authentication failed, CLI error, no events, events not appearing, diagnose, fix olakai, broken, SDK error, monitoring issue, API key invalid, events not tracked. DO NOT load for: initial setup (use olakai-create-agent or olakai-add-monitoring), or generating reports (use generate-analytics-reports).
business-outcomes-advisor
by gracebotly
Fast opinionated revenue strategy for AI automation agencies building workflow dashboards. Frames proposals through monetization lenses during propose phase. Use when user is selecting entities, choosing outcomes, or evaluating dashboard proposals. Max 1-2 questions, plain language, agency-native vocabulary.
jpralph-orchestrator
by juanpare
"Guide users through the Ralph workflow - from PRD creation to completion. Use when starting a new Ralph project or when user needs guidance on next steps. Triggers on: ralph help, what's next, ralph status, guide me through ralph."
create-agent
by kangnam7654
"Use when the user wants to create a new custom agent for Claude Code. Generates a properly formatted agent .md file in ~/.claude/agents/ following the user's established conventions.\n\nExamples:\n- \"/create-agent\" → Launch skill to create a new agent\n- \"새 에이전트 만들어줘\" → Launch skill\n- \"QA 테스터 에이전트 추가해\" → Launch skill with context"
agent-md-refactor
by aleister1102
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
code-review
by YPYT1
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
omni-autonomous-agent (OAA)
by omnious0o0
Makes an AI agent autonomous and able to work for a long time, or a fixed duration without interruptions. Use this skill when the user asks you to work autonomously (e.g., "Work overnight," "I'll be gone for a few hours, work on this," "keep working on this until it's done," etc.). Basically any task that could take longer than usual. (3+ minutes)
single-responsibility
by qiao-925
单一职责原则，确保代码文件、函数、模块职责清晰单一。适用于所有代码文件。
motion-animation
by moderndegree
Motion design principles, when to animate, transitions, and accessibility. Use when adding animations, micro-interactions, or ensuring accessibility for motion.
SkillSentry
by SEKIRO009
Kiểm tra bảo mật cho tất cả AI skills/plugins trước khi sử dụng. Phát hiện lệnh ẩn, exfiltration, mã hoá Base64, ký tự Unicode nguy hiểm, và behavior chain độc hại. Dùng khi cài skill mới, muốn audit toàn bộ skill library, hoặc kiểm tra file .md nghi ngờ.