Build AI agents with Strands Agents SDK. Use when developing model-agnostic agents, implementing ReAct patterns, creating multi-agent systems, or building production agents on AWS. Triggers on Strands, Strands SDK, model-agnostic agent, ReAct agent.
Simple test skill to verify skills system is working. Use this skill when asked to test skills, verify skill discovery, or run a skill test.
Autonomous AI coding with spec-driven development. Implements Geoffrey Huntley's iterative bash loop methodology where agents work through specs one at a time, outputting a completion signal only when acceptance criteria are 100% met.
Guide for designing effective tools for AI agents. Use when creating tools for custom agent systems or any AI tool interfaces. Provides principles for tool naming, input/output design, error handling, and evaluation methodologies that maximize agent effectiveness.
Deep expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered features.
Add new/custom AI models to opencode.json. Use proactively for bleeding-edge releases, non-standard providers, self-hosted models, or custom endpoints. Examples: - user: "Add the new Claude 4.5" โ websearch for API specs, add provider entry with baseUrl, verify model ID format - user: "Use my local Ollama instance" โ configure custom provider with http://localhost:11434, set model ID format - user: "Configure this OpenAI-compatible proxy" โ add provider with custom baseUrl, set apikey env var, verify compatibility - user: "Model X just released, add it" โ research provider documentation, find model ID and capabilities, add to config
Prevent AI hallucination and ensure evidence-based responses when analyzing code or making suggestions. Use when: analyzing code, making recommendations, providing options, or when user asks about confidence/certainty. Keywords: certainty, assumption, inference, evidence, source, ็ขบๅฎๆง, ๆจๆธฌ, ๅ่จญ, ไพๆบ, ่ญๆ.
Risk-Based Value audit worker (L3). Calculates Usefulness Score = Impact (1-5) ร Probability (1-5) for each test. Returns KEEP/REVIEW/REMOVE decisions based on thresholds (โฅ15 KEEP, 10-14 REVIEW, <10 REMOVE).
R 4.4+ development specialist covering tidyverse, ggplot2, Shiny, and data science patterns. Use when developing data analysis pipelines, visualizations, or Shiny applications.
Migrates mock data from Drizzle ORM schemas to C# MockData classes
Provides SSE streaming patterns for the chat API and frontend. Use when implementing or modifying chat streaming, handling SSE events, or troubleshooting message flow between frontend and backend.
A clojure specific AI prompt. Use when there are clojure REPL tools available.
AI ํ์ง ๊ฐ๋ฅ ํจํด์ ๊ฐ์งํ๊ณ ์ ๊ฑฐํ๋ ๋ ๋ฆฝ ๊ฒ์ฆ ์คํฌ. ๊ธ์ง ํํ, ๋ฐ๋ณต ๋จ์ด, ๋ถ์์ฐ์ค๋ฌ์ด ๊ตฌ์กฐ๋ฅผ ํ์งํ๋ค. ๊ฒ์ ์ ์ฝํ ์ธ ๋ฅผ ๊ฒ์ฆํ๊ฑฐ๋ AI ํจํด์ ์๋ ๊ต์ ํ ๋ ์ฌ์ฉํ๋ค.
MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
aStory ๋ธ๋ก๊ทธ ํ๋ซํผ์ ์ํ 8๊ฐ์ AI ์ ์ ํ๋ฅด์๋. ์ํคํ ํธ(๊ฒฉ์์ฒด ๋ถ์์ ๊ถ์), ๊ฐ๋ฐ์(์ค์ฉ์ ๋ํ์ฒด ๊ตฌํ์), ์คํ ๋ฆฌํ ๋ฌ(์์ฌ์ ๊ณต๊ฐ์ ์ฌ์ ์ ๋ฌ์), ๋ฉํ (์ฒด๊ณ์ ์์ก์ ๊ต์ก์), ๋ถ์๊ฐ(๊ฐ๊ด์ ๋ฐ์ดํฐ ๊ธฐ๋ฐ ์ฐ๊ตฌ์), ๋ฆฌ๋ทฐ์ด(๊ท ํ ์กํ ๋น๊ต ํ๊ฐ์), ํ๋ ์ดํฐ(๊ฐ๊ฒฐํ ์ฌ์ค์ ๋ฆฌํฌํฐ), ์นผ๋ผ๋์คํธ(๋นํ์ ๋๋ฐ์ ๋ ผํ๊ฐ)๋ฅผ ํฌํจํ๋ค. ์ ์ ์์ฑ์ ์ ํํ๊ฑฐ๋ ํ๋ฅด์๋ ๊ธฐ๋ฐ ์ฝํ ์ธ ๋ฅผ ๊ตฌํํ ๋ ์ฌ์ฉํ๋ค.
Dump full Tasuku context for agent consumption. Use when user says /tk:context or asks for full context, project state, or needs to understand the entire task landscape.
Provides research patterns for Azure AI Foundry Agent Service SDK. Use when implementing agent features, looking up SDK methods, finding code samples, or troubleshooting Azure.AI.Projects API usage.
Python library for LLM API requests with unified interface across providers (OpenAI, Anthropic, Google, etc.). Use when writing code that calls LLMs, creates tools/agents, batch processes prompts, or needs rate limiting. Triggers on lm-deluge, lm_deluge, LLMClient, or multi-provider LLM code tasks.
Creates JPA entities following best practices.
Expert knowledge of LangGraph agent patterns for SEPilot Desktop. Use when implementing AI agents, graph-based workflows, or complex multi-step reasoning. Ensures proper integration with existing LangGraph infrastructure and streaming patterns.
