Prompts
Prompt engineering and templates
latex-table
by brycewang-stanford
LaTeX回归表格生成Skill。辅助生成符合AER/QJE等顶刊格式的三线表，包括标准误聚类标注、显著性星标、固定效应标注。触发词：LaTeX表格/回归表/三线表/table制作/latex table
scrum-master
by aj-geddes
Sprint planning and agile workflow specialist. Breaks epics into user stories, estimates complexity using story points, plans sprint iterations, and tracks velocity. Trigger keywords: sprint planning, user story, story points, velocity, backlog, sprint, epic breakdown, estimation, burndown, agile planning.
humanizer-ru
by Vladimir-Human
"Use when: нужно очеловечить (humanize) сгенерированный ИИ текст на русском. Убирает 25 машинных паттернов, делает язык живым и естественным."
ai-llm-engineering
by Microck
Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.
humanize-chinese
by brycewang-stanford
Detect and humanize AI-generated Chinese text. 20+ rule detection categories plus statistical features (sentence-length CV, short-sentence fraction, comma density, perplexity, GLTR, DivEye) plus scene-aware LR fusion (rule × 0.2 + LR × 0.8) trained on three scenes: general / academic / longform 长文本 (≥1500 字)。Unified CLI: ./humanize {detect,rewrite,academic,style,compare}. 8 style transforms (casual/zhihu/xiaohongshu/wechat/academic/literary/weibo/novel)。 Multi-paragraph rewriting (paragraph length CV、跨段 trigram 重复) plus best-of-N humanize (默认 N=10 取最低 LR)。165 replacement patterns + CiLin 同义词词林 38873 with collision blacklist。 Academic paper AIGC reduction for CNKI/VIP/Wanfang (知网/维普/万方 AIGC 检测降重)。 Pure Python, no dependencies, offline。v5.0.0 — HC3 fused 准确率 95%、学术 hero 100→35 (-65)、 工作汇报 96→13 (-83)、长篇博客 96→41 (-55)。 Use when user says: "去AI味", "降AIGC", "人性化文本", "humanize chinese", "AI检测", "AIGC降重", "去除AI痕迹", "文本改写", "论文降重", "知网检测", "维普检测", "AI写作检测", "让文字更自然", "detect AI text", "humanize text", "reduce AIGC score", "make text human-like", "去ai化", "改成人话", "去机器味", "降低AI率", "过AIGC检测", "长文本改写", "小说改写"
hook-developer
by parcadei
Complete Claude Code hooks reference - input/output schemas, registration, testing patterns
agentic-workflow
by parcadei
Agentic Workflow Pattern
agent-base-template-generator
by ruvnet
Agent skill for base-template-generator - invoke with $agent-base-template-generator
understand
by Egonex-AI
Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships
knowledge-absorber
by YuJunZhiXue
深度解析链接、文档或代码，生成“全能导师级”的教学笔记（零基础直达精通）。具备“真理锚定”校验能力，自动识别幻觉与过时信息。
turn-into-app
by BuilderIO
Turn visible project context, a proven thread, skill, or workflow into a runnable Agent-Native app with simple buttons, visible agent steps, preview, and deployment handoff. Use when a user invokes /turn-into-app or asks to make a workflow into an app, including from Claude or ChatGPT on the web, including when the source is a spreadsheet link or upload.
multi-frontier-desktop
by BuilderIO
Run or extend the Desktop Code Agents Multi-Frontier workflow. Use when coordinating Codex and Claude Code subscriptions, collaboration phases, checkpoints, recovery, usage meters, or helper admission.
writing-agent-instructions
by BuilderIO
How to write great agent instructions for an agent-native app or template: AGENTS.md, skills, and tool/action descriptions. Use when authoring or reviewing AGENTS.md, writing a SKILL.md, wording action descriptions, or deciding what belongs in instructions vs skills vs memory.
council
by warpdotdev
Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.
seo-geo
by AgriciDaniel
Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. Generative Engine Optimization (GEO) analysis including brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization. Use when user says "AI Overviews", "SGE", "GEO", "AI search", "LLM optimization", "Perplexity", "AI citations", "ChatGPT search", or "AI visibility".
an
by BuilderIO
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.
agent-page
by BuilderIO
The full-page Agent surface (/agent) with Context, Files, Connections, Automations, and Access tabs. Use when mounting the Agent page in a template, adding an app-specific tab, surfacing context transparency, MCP servers, A2A agents, recurring jobs, or external-client connect flows in the UI.
delegate-to-agent
by BuilderIO
How to delegate all AI work to the agent chat. Use when delegating AI work from UI or scripts to the agent, when a user asks for agent behavior or LLM-powered features, when tempted to add inline LLM calls, or when sending messages to the agent from application code.
turn-into-app
by BuilderIO
Turn visible project context, a proven thread, skill, or workflow into a runnable Agent-Native app with simple buttons, visible agent steps, preview, and deployment handoff. Use when a user invokes /turn-into-app or asks to make a workflow into an app, including from Claude or ChatGPT on the web, including when the source is a spreadsheet link or upload.
GEO Optimizer — AI Context Files
by auriti-web-design
GEO Optimizer by Juan Camilo Auriti â https://github.com/auriti-web-design/geo-optimizer-skill
ralph-lisa-loop
by basecamp
Automated plan-implement loop with expert review. Claude implements, Codex reviews, the human steers. A single rope-length knob (0-5) controls interruption frequency. Closure requires zero open findings and zero unresolved disputes at any rope level. Use for any planning, development, or implementation task that benefits from structured review. The default workflow for building anything non-trivial.
claude-code-plugins
by melodic-software
"Validate the bug-report output configuration and explain how to change it through Claude Code's plugin configuration prompt. Use when: 'set up bug-report', 'configure bug-report', 'bug-report setup', 'where do bug reports land', or you want --file reports committed alongside code. Actions: check (read-only verification, default and only action — this plugin's entire configuration is native userConfig, so there is nothing an apply could write)."
adversarial-review
by basicmachines-co
Cross-vendor adversarial code review of the current branch. Two different model families (Claude + Codex/GPT) review the diff independently, then try to refute each other's findings; survivors are reported by confidence. Runs from either Claude Code or Codex. Use when the user asks for an adversarial review, a cross-model / second-opinion review, or wants high-confidence findings before merging. Report-only — never auto-applies fixes.
libtv-video-production
by PomeloR611
用 LibTV CLI（Seedance 2.0 视频 + nebula/seedream 图）把分镜做成短片（2D 绘本或写实皆可）——涵盖九宫格故事板→clean 去标注→image2video 单镜生成→ffmpeg 本地剪辑(转场+配乐+旁白)全流程，附 prompt 铁律模板库（角色/比例/零文字/场景锁定/负面词反召唤）与高频踩坑速查（多狗/角色漂移/格号穿帮/审核三连拒/长镜头漂移）。当用户要用 liblib.tv / libtv / Seedance 把参考图或脚本做成视频短片、或维护此类制作工程时触发。