Instruccions per a IA

Disseny d’instruccions i plantilles per a models d’IA

Skills: 1369–1392 de 4972
dylanfeltus

creative-direction

dylanfeltus

Image prompt templates, model selection guidance, and anti-generic patterns for generating visual assets. Use when the user needs AI-generated images for landing pages, marketing, or products. Covers hero images, feature illustrations, OG cards, icons, and backgrounds.

Anàlisi estàtica i format 180 fa 8 mesos
GhostScientist

your-skill-name

GhostScientist

A clear description of what this skill does and when Claude should use it. Include trigger phrases like "when asked to...", "use when...", or specific keywords that should activate this skill.

Processament de dades 5 fa 10 mesos
sabahattinkalkan

prompt-engineering

sabahattinkalkan

Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. Use when creating prompts, optimizing existing prompts, or improving AI instructions.

Automatització 31 fa 9 mesos
alirezarezvani

claude-md-enhancer

alirezarezvani

Analyzes, generates, and enhances CLAUDE.md files for any project type using best practices, modular architecture support, and tech stack customization. Use when setting up new projects, improving existing CLAUDE.md files, or establishing AI-assisted development standards.

Generació de codi 893 fa 11 mesos
colonelpanic8

journaling

colonelpanic8

Use when user wants to journal, reflect, write a journal entry, or process thoughts. Also use when user mentions wanting to talk through what's on their mind.

Operacions amb fitxers 221 fa 8 mesos
NeverSight

extract-transcripts

NeverSight

Extract readable transcripts from Claude Code and Codex CLI session JSONL files

Autenticació 218 fa 9 mesos
NeverSight

openai-image-gen

NeverSight

Generate images using OpenAI's DALL-E 3 API. Use when needing to create graphics, icons, backgrounds, or any visual assets. Requires OPENAI_API_KEY in environment.

Generació de codi 218 fa 9 mesos
NeverSight

claude-code-hooks

NeverSight

"Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging."

Eines de línia d’ordres 218 fa 9 mesos
massgen

model-registry-maintainer

massgen

Guide for maintaining the MassGen model and backend registry. This skill should be used when adding new models, updating model information (release dates, pricing, context windows), or ensuring the registry stays current with provider releases. Covers both the capabilities registry and the pricing/token manager.

Generació de codi 1,1 k fa 11 mesos
p-wegner

skill-author

p-wegner

Scaffold, validate, and install new OpenCode agent skills — handles directory creation, YAML frontmatter, naming rules, tool/permission wiring, and placement in the correct discovery paths. Use when asked to "create a skill", "write a skill", "scaffold a SKILL.md", "make a new agent skill", "add a skill to this repo", or any request to author reusable agent behavior.

Generació de codi 9 fa 2 mesos
Montimage

skill-creator

Montimage

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Generació de codi 9 fa 8 mesos
wangyendt

pywayne-llm-chat-window

wangyendt

PyQt5-based GUI chat window for LLM conversations with streaming responses and stop functionality. Use when working with pywayne.llm.chat_window module to create desktop chat applications with customizable window configuration, system message management, and real-time streaming display.

Desenvolupament d’API 9 fa 8 mesos
gwenwindflower

chezmoi

gwenwindflower

Manage dotfiles with chezmoi - a cross-platform dotfile manager using a source-state model. Use when: (1) Working with chezmoi configuration, setup, or repo structure, (2) Managing files, templates, or scripts (Go template syntax, run_once_/run_onchange_ scripts, .chezmoidata), (3) Handling file attributes (symlinks, permissions, encryption, external sources), (4) Troubleshooting chezmoi operations or understanding application order.

Generació de codi 9 fa 8 mesos
p-wegner

--help

p-wegner

--help

Instruccions per a IA 9 fa 5 mesos
accomplish-ai

skill-creator

accomplish-ai

Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends the AI's capabilities with specialized knowledge, workflows, or tool integrations.

Generació de codi 10,8 k fa 8 mesos
smallnest

skill-creator

smallnest

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Generació de codi 309 fa 10 mesos
QwenLM

image-generation

QwenLM

Image generation skill based on Alibaba Cloud DashScope, supporting the creation of high-quality hand-drawn or standard images from user descriptions.

Eines de línia d’ordres 143 fa 9 mesos
beshkenadze

your-skill-name

beshkenadze

Brief description of what this Skill does and when to use it. This field is critical for Claude to discover when to invoke your skill.

Generació de codi 4 fa 10 mesos
wundercorp

honcho

wundercorp

Configure and troubleshoot Honcho memory for Loki.

Finances 26 fa 1 mes
wundercorp

creative-ideation

wundercorp

"Generate ideas via named methods from creative practice."

Àmbit acadèmic 26 fa 1 mes
oldwinter

ai-evaluation-evals

oldwinter

Create AI evaluation plans with benchmarks, rubrics, and error analysis workflows.

Generació de codi 10 fa 7 mesos
oldwinter

humanizer-zh

oldwinter

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。

Operacions amb fitxers 10 fa 7 mesos
oldwinter

fundraising-strategy

oldwinter

Plan early-stage fundraising strategy, investor pipeline, and process execution.

Operacions amb fitxers 10 fa 8 mesos
oldwinter

building-with-llms

oldwinter

"Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). Use for building with LLMs, GPT/Claude apps, prompt engineering, RAG, and tool-using agents."

Agents 10 fa 9 mesos