Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
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.
agent-md-refactor
dirnbauer
Refactor bloated agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) to follow progressive disclosure principles - keeping essentials at root and organizing the rest into linked, categorized files. Use when agent instruction files are too long, contain contradictions, or need restructuring.
prompt-engineering
martinholovsky
"Expert skill for prompt engineering and task routing/orchestration. Covers secure prompt construction, injection prevention, multi-step task orchestration, and LLM output validation for JARVIS AI assistant."
llm-integration
martinholovsky
"Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific vulnerabilities including prompt injection, model theft, and denial of service attacks."
model-quantization
martinholovsky
"Expert skill for AI model quantization and optimization. Covers 4-bit/8-bit quantization, GGUF conversion, memory optimization, and quality-performance tradeoffs for deploying LLMs in resource-constrained JARVIS environments."
cloud-api-integration
martinholovsky
"Expert skill for integrating cloud AI APIs (Claude, GPT-4, Gemini). Covers secure API key management, prompt injection prevention, rate limiting, cost optimization, and protection against data exfiltration attacks."
saas-pipeline
ThomasPraun
"Use when starting a new SaaS project, checking project status, advancing to the next phase, viewing the project dashboard, or when the user mentions 'pipeline', 'saas-pipeline', 'next phase', 'project status', 'dashboard', 'idea to launch'. Orchestrates 28 skills across 8 phases: idea, business, product, architecture, design, implementation, deployment, marketing."
llama
G1Joshi
Meta Llama open-source LLM family. Use for local AI.
product-background-generation
tara-shopos
Generate professional studio or lifestyle backgrounds for product photography that match product aesthetics, brand positioning, and target audience. Use when creating product shoots, fashion photography, or e-commerce visuals requiring contextual backgrounds.
security-review
thoreinstein
Perform enterprise security review of the codebase
web-artifacts-builder
icartsh
현대적인 프런트엔드 웹 기술(React, Tailwind CSS, shadcn/ui)을 사용하여 정교한 다중 컴포넌트 claude.ai용 HTML artifact를 제작하기 위한 툴킷입니다. 상태 관리, 라우팅 또는 shadcn/ui 컴포넌트가 필요한 복잡한 artifact에 사용하세요. 단순한 단일 파일 HTML/JSX artifact용이 아닙니다.
mlflow
G1Joshi
MLflow ML lifecycle management. Use for ML experiment tracking.
dalle
G1Joshi
DALL-E OpenAI image generation. Use for image creation.
agent-tower-plugin
BayramAnnakov
Multi-agent deliberation for Claude Code - orchestrate AI coding assistants (Claude, Codex, Gemini) for council, debate, and consensus workflows
langchain
G1Joshi
LangChain LLM application framework with chains and agents. Use for LLM orchestration.
wicked-garden-classify
mikeparcewski
v11 LLM-based work-shape classifier. Replaces the regex archetype detector with the model's own reasoning. Reads the user's prompt, picks the right archetype(s) from the catalog, identifies signals (blast_radius, novelty, reversibility, etc.), and persists to SessionState so subsequent turns steer correctly. Use when: the prompt_submit hook emitted a <wg classify-due /> directive, OR explicitly invoked at session start, OR when re-classifying after the user changes scope mid-session.
agent-prompt-infrastructure
BANG404
Use when changing agent prompt assembly, skill discovery, skill routing metadata, agent-facing documentation validation, memory or role injection, or prompt observability contracts.
claude-handoff
TurboSnails
为 Claude Code 创建交接摘要。
skill-creator
rangerrick337
"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."
wicked-garden-qe-ai-feature-test-engineer
mikeparcewski
Tier-2 specialist — testing LLM-backed features. Prompt-injection probes (direct / indirect / payload-smuggling / multi-turn), jailbreak library (DAN, grandma, token-smuggling, base64), refusal-rate regression, hallucination drift against a caller-provided golden set, output-drift monitors (JSON-schema, token length, citation fidelity). Use when: LLM feature under test, prompt-injection review, jailbreak sweep, refusal-rate check, hallucination regression, RAG citation audit, "does this AI feature still behave after the prompt change". NOT THIS WHEN: post-deploy LLM cost/latency monitoring (use wicked-garden-qe-production-quality-engineer); classical model-accuracy metrics (use wicked-garden-qe-data-quality-tester); security bugs in the surrounding app (use wicked-garden-qe-security-test-engineer) — AI-specific attack surface stays here. Cross-ref: design-time agent-safety review is wicked-garden-agentic-safety-reviewer; THIS skill EXECUTES the probes with evidence.
wicked-garden-jam-council
mikeparcewski
"Runs structured multi-model council evaluations using external LLM CLIs. Use when: multi-model evaluation, council verdict on defined options, high-stakes decision needing genuinely independent model perspectives — handed off by the wicked-garden-jam skill's council sub-action."
godmode
Russ534
"Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN."
cross-platform-context-sync
Russ534
Use when one user talks via multiple channels.
wicked-garden-agentic-performance-analyst
mikeparcewski
Token optimization, latency budgets, cost analysis, caching strategy, and parallelization assessment for agentic systems. Use when: performance optimization of an AI agent system, cost analysis or token-budget review, latency profiling, cache-strategy assessment, parallelization opportunities, or as a parallel worker in a heavyweight wicked-garden-agentic review.