Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
build-error-analyzer
openharmonyinsight
This skill should be used when the user asks to "分析构建错误", "analyze build errors", "查看编译错误", "检查构建日志", "诊断链接错误", "fix build errors", "resolve compilation errors", "分析 last_error.log", "extract build error", "分析SDK的编译错误", "分析 SDK 编译错误", "analyze SDK build errors", "check SDK errors", "诊断 sdk 编译错误", or mentions analyzing build failures, compilation errors, linker errors, undefined symbols, SDK compilation errors, or needs to fix build issues. Focuses on reading last_error.log from out/<product>/ directory (or out/sdk/ for SDK builds) and providing specific fix recommendations based on error patterns and historical cases.
cangjie-lang
ystyle
Cangjie programming language code generation and analysis expert. Use this when users need to write or analyze Cangjie code.
prompt-engineer
dy9759
Comprehensive LLM prompt engineering and optimization workflow that orchestrates expert analysis, advanced techniques, and multi-domain optimization using the integrated toolset. Handles everything from basic prompt improvement to complex multi-agent prompt orchestration.
llms-generative-ai
pluginagentmarketplace
LLMs, prompt engineering, RAG systems, LangChain, and AI application development
project-setup
JeongHeonK
C#/.NET 프로젝트를 Claude Code용으로 초기화. CLAUDE.md 생성 + 컨텍스트 hook 설치 (Bash/PowerShell). Use when setting up new C# projects for Claude Code, migrating existing projects, or updating context hooks.
claw-compactor
aeromomo
Claw Compactor — 6-layer token compression skill for OpenClaw agents. Cuts workspace token spend by 50–97% using deterministic rule-engines plus Engram: a real-time, LLM-driven Observational Memory system. Run at session start for automatic savings reporting.
ai-sdk-core
ma1orek
Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds. Use when: implementing AI SDK v5/v6, migrating versions, troubleshooting AI_APICallError, Workers startup issues, Output API errors, Gemini caching issues, Anthropic tool errors, MCP tools, or stream resumption failures.
agent-md-refactor
ma1orek
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
agenta-langchain-integration
vamseeachanta
'Sub-skill of agenta: Langchain Integration.'
prompt-engineering-4-system-prompt-design
vamseeachanta
'Sub-skill of prompt-engineering: 4. System Prompt Design.'
prompt-engineering-example-1-multi-stage-document-processor
vamseeachanta
'Sub-skill of prompt-engineering: Example 1: Multi-Stage Document Processor
ai-prompting-available-skills
vamseeachanta
'Sub-skill of ai-prompting: Available Skills.'
prompt-engineering-constraints
vamseeachanta
'Sub-skill of prompt-engineering: Constraints.'
agenta-2-ab-testing-prompts
vamseeachanta
'Sub-skill of agenta: 2. A/B Testing Prompts.'
solo-factory
fortunto2
Install the full Solo Factory toolkit — 23 startup skills + solograph MCP server for code intelligence, KB search, and web search. Use when user says "install solo factory", "set up solo", "install all solo skills", "startup toolkit", or "solo factory setup". This is the one-command entry point for the entire startup pipeline.
prompt-engineering-background
vamseeachanta
'Sub-skill of prompt-engineering: Background.'
prompt-engineering-1-zero-shot-prompting
vamseeachanta
'Sub-skill of prompt-engineering: 1. Zero-Shot Prompting (+1).'
agenta-1-prompt-versioning-and-management
vamseeachanta
'Sub-skill of agenta: 1. Prompt Versioning and Management.'
agent-usage-optimizer-baseline-route-defaults
vamseeachanta
'Sub-skill of agent-usage-optimizer: Baseline Route Mapping (quota-agnostic
agenta-3-evaluation-metrics-and-testing
vamseeachanta
'Sub-skill of agenta: 3. Evaluation Metrics and Testing.'
langchain-3-conversation-memory
vamseeachanta
'Sub-skill of langchain: 3. Conversation Memory.'
ai-prompting-choose-langchain-when
vamseeachanta
'Sub-skill of ai-prompting: Choose langchain when: (+4).'
create-subagents
glittercowboy
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
dspy-dspy-philosophy
vamseeachanta
'Sub-skill of dspy: DSPy Philosophy.'