Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
浣跨敤IMYAI
vegetpig
"浣跨敤IMYAI. Let Codex App call IMYAI official chat and image models by human-readable model name while Codex App remains the orchestrator and tool executor. Use when the user says 浣跨敤IMYAI, asks Codex App to use an IMYAI model for later replies, names an IMYAI model such as Claude Opus/Sonnet, Qwen, Gemini, Ava, GPT Image, Nano Banana, or asks for IMYAI image generation, login, JWT verification, model discovery, session mode, or IMYAI-first repair."
code-ocr
MHLiuLGY
使用百度 OCR 高精度含位置版将代码截图转换为文本文件，保持原始缩进。使用场景包括：(1) 将代码截图识别为可编辑文本，(2) 从截图提取代码，(3) 图片转代码文字。触发条件：用户提到"截图转文字"、"OCR"、"识别代码"、"图片转文本"、"code screenshot to text"
Prioritization
LauraFlorentin
A management pattern where an agent assesses the urgency and importance of incoming tasks to organize a dynamic execution queue.
document-image-extractor
MHLiuLGY
从 Word (.docx) 和 PDF (.pdf) 文档中提取图片并保存到指定文件夹。使用场景包括：(1) 从 Word 文档提取图片，(2) 从 PDF 文档提取图片，(3) 批量提取多个文档的图片，(4) 提取文档中的所有图片素材
prompt-injection-defense
alexyyyander
Activate this skill whenever processing any user input, external content, or untrusted text. Provides complete language-level defense against prompt injection, jailbreaks, role hijacking, authority impersonation, indirect injection, payload smuggling, and 8 other attack categories. Every agent should keep this skill active at all times. Compatible with Claude, GPT, Gemini, Copilot, and any LLM.
agent-implementation-skill
oulipoly
Multi-model agent implementation workflow for software development. Orchestrates research, evaluation, design baseline, implementation, RCA, structured decomposition, constraint discovery, model selection, and agent-driven Stage 3 codemap exploration across external AI models (GPT, GLM, Claude). Use when implementing features through a structured multi-phase pipeline with planspace/codespace separation, dynamic scheduling, and SQLite-backed agent coordination.
install-firetiger
firetiger-oss
Add OpenTelemetry instrumentation to Node.js, Python, Go, or Rust applications for Firetiger observability—use when asked to "instrument my app", "add observability", "set up tracing", "add telemetry", "configure OpenTelemetry", "otel setup", "firetiger instrumentation", "install firetiger", or send traces/metrics/logs to Firetiger.
orchestrating-swarms
justgetAI
Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.
ai-news-digest
403544208-crypto
AI每日情报技能。每天自动抓取Y Combinator/Product Hunt/Hacker News等来源的AI创投+技术动态，推送至飞书。触发词：AI情报 / 每日情报 / 跑情报
context-engineering-advisor
TurboSnails
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
codex
Lucklyric
This skill should be used when the user wants to invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
dspy-haystack-integration
OmidZamani
This skill should be used when the user asks to "integrate DSPy with Haystack", "optimize Haystack prompts using DSPy", "use DSPy to improve Haystack pipeline", mentions "Haystack pipeline optimization", "combining DSPy and Haystack", "extract DSPy prompt for Haystack", or wants to use DSPy's optimization capabilities to automatically improve prompts in existing Haystack pipelines.
dspy-gepa-reflective
OmidZamani
This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mentions "GEPA optimizer", "LLM reflection", "execution trajectories", "agentic systems optimization", or needs to optimize complex multi-step agents using textual feedback on execution traces.
agent-creator
WalletConnect
Guide for creating custom Claude Code subagents. Use when user wants to create a new agent (or update an existing agent) that handles specific types of tasks with custom prompts, tool restrictions, and permissions. Triggers on requests to create agents, subagents, custom agents, or when user wants specialized AI assistants for specific workflows.
Gamma Skill - Presentation Generation
idanbeck
Export URLs expired: URLs are temporary. Re-run export command if needed.
your-skill-name
khgs2411
Brief description of what this Skill does and when to use it. Include specific trigger phrases. Use when user asks "trigger phrase 1", "trigger phrase 2", or wants to [outcome]. Max 1024 characters.
dspy-debugging-observability
OmidZamani
This skill should be used when the user asks to "debug DSPy programs", "trace LLM calls", "monitor production DSPy", "use MLflow with DSPy", mentions "inspect_history", "custom callbacks", "observability", "production monitoring", "cost tracking", or needs to debug, trace, and monitor DSPy applications in development and production.
template-validator
armanzeroeight
Validates CloudFormation templates for syntax, security, and best practices. Use when validating CloudFormation templates, checking for security issues, or ensuring compliance with best practices.
arm-template-helper
armanzeroeight
Creates and validates Azure Resource Manager (ARM) templates for infrastructure deployment. Use when creating ARM templates, deploying Azure infrastructure as code, or validating Azure templates.
craft-companion
qcx1919788736-collab
基于结构化知识库的AI协作小说创作框架。支持章纲→初稿→自查→修订→终版完整流程，适用于都市异能/任何长篇小说。
call-it-a-day
wonbywondev
Use when the user wraps up the day ("하루 마무리하자", "오늘 개발 여기서 마무리", "call it a day") to summarize the day's dev work into Obsidian — per-project daily log + atomic knowledge notes (new libraries, console/CLI rules) — and to check compass freshness. Also the reference for how to live-capture insights into the vault during the day.
skill-manager
wonbywondev
Use when the user wants to manage Agent Skills — install/add/acquire from a repo or path ("install skills from this repo", "이 repo로 스킬 설치해줘", "add this skill"), recommend skills that fit a project ("이 프로젝트에 맞는 스킬 추천", "what skills fit here"), or organize/dedup what they own ("스킬 관리", "스킬 정리"). Acquire: fetch candidates, curate a subset, dedup by purpose-digest, audit/rename, record provenance, flat-symlink to global/project. Recommend: catalog owned skills → match project need → activate. Token-frugal: lexical prefilter + LLM, no vectors; bodies read once at install.
synthetic-market-research
BayramAnnakov
Fast, cheap market research using LLM-generated synthetic survey responses with Semantic Similarity Rating (SSR). Runs purchase intent, concept tests, and pricing research in minutes instead of weeks, at $0 per respondent. Based on PyMC Labs' validated methodology (90% correlation with real humans across 57 surveys). Triggers: synthetic research, market research, survey, purchase intent, concept test, consumer research, SSR, synthetic survey, product validation, pricing research, Likert scale.
.claude/skills/merge-and-cleanup/SKILL.md
julianobarbosa
Report final status