Prompts
Prompt engineering and templates
wicked-garden-qe-ai-feature-test-engineer
by 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
by 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
by Russ534
"Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN."
cross-platform-context-sync
by Russ534
Use when one user talks via multiple channels.
wicked-garden-agentic-performance-analyst
by 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.
浣跨敤IMYAI
by 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
by 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
by LauraFlorentin
A management pattern where an agent assesses the urgency and importance of incoming tasks to organize a dynamic execution queue.
document-image-extractor
by 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
by 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
by 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
by 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
by 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
by 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
by TurboSnails
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
codex
by 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
by 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
by 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
by 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.
Wyze Camera Skill
by idanbeck
#wyze #cameras #security #smart-home
Gamma Skill - Presentation Generation
by idanbeck
Export URLs expired: URLs are temporary. Re-run export command if needed.
playwright-skill
by idanbeck
Browser automation for web tasks. Use when the user needs to automate browser interactions, take screenshots, extract data from websites, fill forms, or perform web scraping. Supports persistent sessions for logged-in state.
linkedin-skill
by idanbeck
Post, comment, and react on LinkedIn profiles and company pages. Use when the user asks to post on LinkedIn, check their LinkedIn posts, add comments, react to posts, or manage their LinkedIn presence. Supports multiple accounts.
your-skill-name
by 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.