Instruccions per a IA

start-research

leeovery

"Start a research exploration using the technical-research skill. For early-stage ideas, feasibility checks, and broad exploration before formal discussion."

start-discussion

leeovery

"Start a technical discussion. Discovers research and existing discussions, offers multiple entry paths, and invokes the technical-discussion skill."

vaultcraft

MikolajSapek

"Turn scattered materials (lecture slides, lab scripts, project docs, meeting notes, research papers) into a richly visual, linked Obsidian knowledge vault. Use when the user wants to build, bootstrap, or extend an Obsidian study, work or research vault from raw inputs. Trigger on '/vaultcraft', 'build a vault', 'vaultcraft', or 'make an Obsidian vault from my materials'."

claude-cookbooks

2025Emma

Claude AI cookbooks - code examples, tutorials, and best practices for using Claude API. Use when learning Claude API integration, building Claude-powered applications, or exploring Claude capabilities.

my-skill Skill

2025Emma

Claude Skills Meta-Skill

2025Emma

skill-creation-guide

gleanwork

Auto-triggers when users discuss creating skills or ask about SKILL.md format. Triggers on phrases like "create a skill", "write a skill", "make a skill", "new skill", "SKILL.md format", "skill structure", "how do skills work", "skill best practices", or when the user wants to add custom behavior to Claude Code.

accelint-skill-manager

gohypergiant

Use when users say "create a skill", "make a new skill", "build a skill", "skill for X", "package this as a skill", or when refactoring/updating/auditing existing skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations.

stitch-design

nguyenthienthanh

Generate UI designs using Google Stitch AI with optimized prompts

trace-qa

MooseGoose0701

Analyze and answer questions about agent execution traces. Use this skill when the user asks about a trace, wants to debug a failed agent run, understand what an agent did, analyze token usage or efficiency, or asks "what happened in trace X". Triggers: trace analysis, trace debugging, trace QA, execution review, agent run review.

PowerPoint Suite

michelg10

Microsoft PowerPoint (.pptx) presentation creation, editing, and analysis.

hiring-recruitment

pluginagentmarketplace

Master hiring processes, interviewing, candidate assessment, and building strong engineering teams

emerging-tech

pluginagentmarketplace

Emerging technologies (prompt engineering, AI agents, red teaming) and leadership roles (product manager, engineering manager, DevRel).

agents-py

codeSTACKr

Build LiveKit Agent backends in Python. Use this skill when creating voice AI agents, voice assistants, or any realtime AI application using LiveKit's Python Agents SDK (livekit-agents). Covers AgentSession, Agent class, function tools, STT/LLM/TTS models, turn detection, and multi-agent workflows.

session-reset

webbertakken

Reset the session while preserving context. Commits changes, writes a PROMPT.md capturing current work state, tears down any active team if present, then guides the user through /clear and context restoration. Supports a new parameter (/session-reset new) to write only key institutional knowledge without current task/progress — for starting a different task while preserving learnings. Use when the context window is getting large, the session needs a fresh start, or when switching focus. Also use when user says "reset", "fresh start", "save and clear", or "write prompt".

sv-print

CcSimple

可视化打印设计器组件。基于 Svelte 构建，支持 Vue、React、Angular、jQuery 等框架引入。提供拖拽式模板设计、预览、打印、导出 PDF/图片功能，支持插件扩展元素（ECharts、二维码、Fabric等）。

xmtp-docs

xmtp

Query XMTP documentation for current SDK patterns, methods, and examples. Use when: (1) Looking up XMTP SDK methods or patterns, (2) Verifying current API signatures before coding, (3) Finding examples for XMTP features like streaming, consent, groups, or content types.

context-optimizer

webbertakken

Audit and optimise context window usage for AI coding tools (Claude Code, OpenCode, etc.). Estimates token breakdown, identifies waste (duplicate skills, overlapping rules, bloated instruction files, dirty git status, MCP server overhead), and provides actionable recommendations with projected savings. Use when the user says "context checkup", "reduce context", "check context", "context audit", "how big is my context", or when sessions feel sluggish.

session-start

webbertakken

Start team, run dev servers, and read PROMPT.md if present.

session-summary

ProjAnvil

会话总结技能，用于总结当前会话的上下文，包括已完成的任务、技术决策和下一步计划。使用此技能生成交接文档，以便在不丢失关键上下文的情况下开始新会话。

strategy-writer

rileyhilliard

Produces executive-quality strategic documents in The Economist/HBR style. Use when writing strategy memos, market analysis, business cases, customer research reports, or any document for Product, Design, and Business leaders. Customer-led, evidence-based, narrative-driven.

my-skill-name

sendaifun

A clear description of what this skill does and when to use it

gpt-pro-audit

hubeiqiao

"Use when the user asks to audit a plan, document, diff, website finding, or implementation proposal with the best available ChatGPT GPT-5.5 Pro (Extended Thinking) option through Chrome - automatically packages codebase/project context ChatGPT cannot see, runs multi-round review until accepted, verifies the response, and applies only accepted findings."

stitch-loop

jh941213

Stitch를 사용하여 자율적으로 멀티 페이지 웹사이트를 생성하는 반복 빌드 루프 패턴. "Stitch 루프", "웹사이트 생성", "멀티 페이지" 키워드에 활성화.