160 boosters for "claude-skill" — open source, verified from GitHub, ready to install
Return the following mode definition verbatim to the team lead. Do not summarize or interpret — the lead needs the full specification. You are the team lead. You manage the team with patience — you do not hurry teammates along, and you do not overcommunicate. You are the only person on the team who
A review finding is stuck. Structure its resolution in three steps. Identify and state aloud: After the reviewer responds:
The user stated an outcome in their own words. Read it for ONE structural pattern — a specific instance named as the way to reach a broader end the user's outcome also states — which can silently collapse the team onto that one point and orphan the alternatives. Fire ONLY when BOTH are present: (1)
Suggest additional team members based on the user's outcomes and selected mode. The lead and facilitator are always included. Keep teams to 3-5 members total. Up to 8 for complex multi-domain work. All members except the lead are read-only. Present your suggestion.
Return the following governance specification verbatim to the team lead. Do not summarize or interpret — the lead needs the full specification. The briefing templates below are the exclusive source of truth for team member context. Do not add sections beyond what the templates specify — no "Your Fir
"description": "Launch agent teams for any kind of work — coding, writing, diagnosis, and more", "name": "Dheer Gupta", "email": "noreply@dheer.co"
Return the following mode definition verbatim to the team lead. Do not summarize or interpret — the lead needs the full specification. You are the team lead. You manage the team with patience — you do not hurry teammates along, and you do not overcommunicate. You coordinate the team, relay user feed
The team can't find existing standards. Help them build a rubric. Ask: what does the output look like when it's right? Get specific, measurable answers. File sizes, response times, value ranges, visual correctness, behavioral expectations. If the user or team can't quantify it, ask what they'd check
Evaluate the user's ambient context artifacts for compatibility with swarm's governance rules. You are a read-only diagnostic — never modify any files. 1. CLAUDE.md files. Read the project's (working directory root). If exists, read that too. Also check (global config) — it loads into every sessi
This file is the control plane. It decides the mode, loads only the references that mode needs, and runs the shared start and finish steps. Methodology lives in The experience this skill must deliver:
"name": "forward-deployed-selling", "description": "Operating doctrine for AI-era enterprise sales. Use when an agent works on accounts, deals, outreach, coaching, or pipeline — any revenue-affecting decision.", "name": "Angel Armendariz",
"name": "mindmap-markmap-viewer", "description": "Turn Markdown outlines, notes, docs, or plans into an interactive mind map — a single self-contained HTML file that opens offline anywhere (markmap.js, white-on-dark, zoom/expand/export toolbar, context-preserving search).", "name": "Jaderson Vargas"
Use AskUserQuestion to ask the buyer: Tell the user the version was updated, then re-read the EVALUATION.md file from the updated directory and proceed with the skill. After the preamble, read the full evaluation methodology:
The definitive SEO and Generative Engine Optimization agent. LLM-agnostic — works on any platform that reads . Merges Google's official SEO guidance, 2026 GEO research, and practitioner best practices into one universal framework. Every finding comes with a
Operate the user's real Safari browser on macOS via AppleScript () and . This provides full access to the user's actual browser session — including login state, cookies, and open tabs — without any extensions or additional software. Before first use, verify two settings are enabled. Run this check a
Format markdown articles with bm.md styling and publish directly to WeChat Official Account drafts via the official API. 1. Read markdown file (typically from article directory) 2. Upload local images to WeChat CDN via API
仅适用于中文学术论文(学位论文、期刊投稿、学术报告)。不适用于: 知网AIGC检测器不是抓"AI写的",而是抓5种语言模式。理解这5种模式比记规则更重要: 用户贴一段红色显著文本进来,按以下步骤处理:
你精通 LaTeX/TikZ 绘图和 draw.io XML 生成,擅长将论文中的系统架构、协议流程、技术方案、技术路线图转化为高质量配图。 执行任务时不要陷入惯性——不是所有图都该用 TikZ,不是所有架构都该自下而上,不是遇到编译错误就反复微调同一行代码。带着目标进入,边画边判断,遇到问题就诊断根因,发现方向错了就换方案——全程围绕「这张图要传达什么信息」做决策。 ① 定义成功标准:这张图要传达什么信息?读者看到后应该理解什么?几个模块、几层关系、什么样的视觉层次?这是后续所有判断的锚点。
The captain's log for your codebase. Every decision, discovery, and change logged as you ship code. Use GitHub as a complete knowledge graph where every brainstorm, commit, review, and decision is traceable. This skill orchestrates existing skills and references; it defines when and how to invoke th
引导用户完成一次结构化需求访谈,收集配套素材,最终打包生成一份可直接使用的完整Skill文件包。 1. 用户不需要懂Skill格式——他们只需要回答问题,你来负责转化 2. 每轮问完先小结确认——不要一口气把12个问题全抛出来
Transform podcast audio into cinematic visual content using Seedance 2.0 on Higgsfield. This skill produces video prompts that replace static audiograms with storytelling-driven visual experiences built entirely from constructed imagery. The hook is the opening frame that stops the scroll. It must c
A complete system for crafting Seedance 2.0 prompts on Higgsfield that feature AI avatars, digital personas, virtual presenters, and synthetic characters as the primary subject. This skill covers everything from photorealistic digital humans to stylized 3D characters, including hook patterns, enviro
Videos with 80%+ completion get 2-3x algorithmic reach. Your hook determines everything. Layer these elements for maximum impact: 1. Base Layer — Ambient bed (room tone, wind, hum) or silence
The first two seconds determine whether a viewer stops scrolling. These patterns open with immediate visual authority. Luxury camera work operates within a narrow, controlled vocabulary. No exceptions. The most used luxury camera move. Camera travels toward subject at 0.1x–0.3x of normal speed. Tota