Prompts
Prompt engineering and templates
compare-standards
by keenranger
Compare implementation against internal standards. Use when comparing thresholds, checking compliance, or says /compare-standards.
investment-news
by Alnlll
为 A股投资者打造的本地「投资资讯看板」。从 100+ 源抓 12 大赛道(一一对应 A股板块:半导体/AI/机器人/新能源车…)新闻,用用户自己的大模型(Claude 订阅或 API)提炼中文「今日要点」+翻译,浏览器看板呈现。当用户想搭建/启动/更新投资资讯看板、或想看某赛道(A股板块)近期全球领先信号时使用。纯 Python 标准库,零 key,数据不出本机。
project-workspace
by guycoful
"מארגן פרויקט מפוזר לתיקיית workspace ייעודית עם שלד קבצי ניהול מלא (CLAUDE.md, SESSION_BRIEF.md, AGENTS.md, access.md, sessions-index.md), מנייד קבצים קיימים באמצעות סקריפט אוטונומי, ורושם טריגרים לקריאה אוטומטית בסשנים הבאים. הפעלה: 'תיצור תיקיית פרויקט', 'workspace לפרויקט', 'תפריד את הפרויקט', 'תנייד לתיקייה', 'תבודד פרויקט X', 'extract project', 'הפרויקט מפוזר', 'רוצה תיקייה נפרדת', 'תארגן את פרויקט X', 'תיצור workspace ל-X', 'הפרויקט צריך בית משלו', 'תרכז את הקבצים של X'."
promptl
by latitude-dev
PromptL syntax guide for writing prompts in the Latitude platform. This skill should be used when writing, reviewing, or editing PromptL prompts. Triggers on tasks involving creating prompts, configuring LLM parameters, using variables, conditionals, loops, chains, tools, agents, or any prompt engineering in Latitude.
angular-access-modifiers
by araujomartin
Recommended usage of access modifiers in Angular components: public readonly for API (inputs/outputs), protected readonly for template state, private readonly for internal logic. Trigger: When defining component properties in Angular.
autonomous-loop
by NCMcClure
Create task-specific autonomous agentic coding loop skills using the Ralph Wiggum methodology. Use when building harnesses for Claude Code to run autonomously for extended periods, implementing iterative development loops, creating self-healing agent pipelines, or designing systems where AI agents persist through context window boundaries. Triggers include requests for "autonomous coding", "agentic loops", "Ralph Wiggum", "self-running agents", "iterative AI development", "continuous coding loops", or "headless Claude Code".
plan-master
by ryoshimm
.claude/plans/<feature>/plan.md に実装計画書を作成する。コード実装は行わない。
reload
by gyumaruya
Restart the current Claude Code session from within tmux. Writes a handoff file, launches a restart script in a new tmux window, which stops the current Claude and resumes with --resume. Triggers: /reload, "reload", "restart", "reboot", "再起動"
Project Init Skill
by yousufjoyian
Use session-save to maintain context
3p
by WhaleCastle
Three-party review workflow — Claude plans/builds, Codex and Antigravity independently review, Claude verifies and iterates until unanimous approval or round-cap exit. Use when invoked via /3p <task> or when the user explicitly asks to run a task "through 3p" or "with 3p review." Per-task only — not a session-wide mode.
doc-coauthoring
by arielperez82
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
aeo-cost-governor
by ivzc07
Track token usage and enforce budget limits. Optional skill for cost-conscious projects.
wechat-article
by freeany
"Convert Markdown articles to WeChat Official Account compatible HTML format. Use when users need to convert Markdown files to WeChat articles, apply themed styling for WeChat formatting, generate inline CSS HTML compatible with WeChat editor, process technical articles with code blocks and tables for WeChat, or apply professional WeChat-style layouts with headers and footers."
multi-agent-thinker
by CodingHeader
This skill is the "Heavy Lifting Engine" for complex problem solving.
agent-creator
by slurpyb
Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks requiring consistent high-quality performance with deeply embedded domain knowledge.
tech-planner
by jkappers
Use when (1) evaluating technical feasibility of a feature spec, (2) making technology or framework choices, (3) defining system architecture for a new feature, (4) documenting architectural decisions as ADRs, (5) analyzing integration points and data flow for a proposed change.
flow-node-creator
by fleek-fitness
"A skill that creates 'conversation flow' nodes for vox.ai voice agents. It converts call-center/OB/CS scripts (free text) into a flow-node format with name + content + transition conditions. Use this skill whenever users ask to transform call scripts, consultation scenarios, OB scripts, CS manuals, call flows, consultation flows, or conversation-flow nodes into step-based prompts/nodes/flows. It is also triggered by requests such as 'split this script into steps,' 'turn this into flow nodes,' or 'organize this with transition conditions.'"
claude-code-dev
by maxoreric
Claude Code Plugin 开发专家。当用户要创建 Plugin、Skill、Subagent、Slash command、Hook 时触发。也用于解答 Claude Code 开发相关问题。触发词：创建 plugin、写 skill、写 agent、创建 hook、写 command、插件开发。
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。
stepanov-generic-programming
by copyleftdev
Write C++ code following Alexander Stepanov's generic programming principles. Emphasizes algorithms over data structures, concepts as requirements, and mathematical rigor in interface design. Use when designing reusable algorithms or data structures that must work across types.
baoyu-image-gen
by siatwangmin
AI image generation with OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and parallel generation (recommended 4 concurrent subagents). Use when user asks to generate, create, or draw images.
acommons
by Phlegonlabs
AI coding tool usage analytics. Tracks token usage across Claude Code, Codex CLI, OpenCode, Gemini CLI, and external tools. Use when user wants to view AI usage stats, sync usage data, or set up automatic usage tracking.
doc-coauthoring
by zhuxining
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
clinic-content-system
by gwanggyo-barun
광교바른내과 통합 환자 교육 콘텐츠 생성 스킬 (HTML + PDF). 세 가지 콘텐츠 타입을 단일 디자인 시스템·단일 빌드 파이프라인으로 생산한다: (1) 16:9 멀티슬라이드 환자 교육 덱, (2) A4 세로 1장 진료실 핸드아웃, (3) A4 세로 1장 검사 결과 인포그래픽. 공통 인프라: Navy #003366 + Steel Blue #5B9BD5, Pretendard Variable, Python qrcode SVG 자동 QR 생성, OG meta 7개 head 등록. 사용자가 "환자 교육 슬라이드/PDF", "유인물 만들어줘", "주의사항 PDF", "비치용 안내문", "검사 결과지 인포그래픽", "결과지 시각화", "종합검진 결과지", "건강검진 결과", "검진 결과지", "위/대장 내시경 + 초음파 + 혈액검사 종합", "경동맥/갑상선/상복부 초음파 결과", "심전도/골밀도 포함 검진 결과", "텍스트/PDF/캡쳐로 검사결과지 생성", "환자한테 보낼 자료", "카톡으로 보낼 자료" 등을 만들어 달라고 할 때 트리거된다. 특히 lab-reports/health-checkup 모드는 환자별로 시행 검사가 다른 종합 건강검진 결과지를 1~3페이지 HTML/PDF로 만든다. 기존 patient-education-pptx, patient-handout-pdf, lab-report-infographic 세 스킬의 HTML 통합 후속 버전이며, PPTX가 명시적으로 요구되지 않는 한 이 스킬을 우선 사용한다.