A measurement-first decision discipline for choosing HOW to build something. Before pouring effort into one approach, operationalize a measurable fitness, sketch a few candidate…
Multi-agent code review using Agent Teams. Summons up to 8 built-in Ashes (plus custom Ash from talisman.yml), each with their own dedicated context window.
Answer questions about Claude Code CLI, Claude Agent SDK, and Claude API (Anthropic API). Use when the user asks about Claude Code features, settings, hooks, MCP, slash commands,…
Claude Code learning — configure and optimize Claude Code settings, tips, and workflows. Triggers: learn, setup, claude code, optimize, 학습, 설정, 최적화.
Interactively create a new Jira issue (and optional sub-tasks with dependency links) from conversation context.
Resolve a specific GitHub PR review comment. Supports review thread comments (line-level) and issue comments (PR-level from bots).
Multi-agent work execution using Agent Teams. Parses a plan into tasks, summons swarm workers that claim and complete tasks independently, and runs quality gates before completion.
Сводка непрочитанных сообщений по чатам Telegram. Использует MCP-сервер claudegram. Запускать при просьбах «что у меня в тг», «дайджест непрочитанных», «что я пропустил».
Показать последние сообщения из конкретного Telegram-чата через MCP-сервер claudegram. Запускать при «покажи переписку с X», «история чата X», «что писали в чате Y».
Ответить на конкретное сообщение в Telegram-чате через MCP-сервер claudegram. Только пользователь явно вызывает.
Поиск по сообщениям Telegram (глобально или в одном чате) через MCP-сервер claudegram. Запускать при просьбах «найди в тг», «искать в чате X», «поищи переписку про Y».
Отправить сообщение в Telegram-чат через MCP-сервер claudegram. Только пользователь явно вызывает — Claude сам не запускает.
Этот скилл MUST быть вызван когда есть design.md и нужно разбить доработку на атомарные задачи (2-5 мин) с точными путями файлов и критериями проверки в tasks.md.
Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best…
Agent-based modeling skill for simulating complex adaptive systems with heterogeneous interacting agents
Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes independent work, supervises execution, tracks progress in…
Multi-agent deliberation for Claude Code - orchestrate AI coding assistants (Claude, Codex, Gemini) for council, debate, and consensus workflows
Use after code review - implement ALL findings; any finding not fixed MUST have tracking issue created; no finding disappears without trace — from troykelly/codex-skills
Use atrib as your literal substrate for memory, reasoning, and getting smarter over time, not as instrumentation that observes you from the outside.
Use when starting any work session - establishes autonomous operation mode, overriding token limits and time pressure to work until goal is achieved — from general/ai-tooling
Use when user requests autonomous operation across multiple issues. Orchestrates parallel workers using Task tool, monitors with TaskOutput, handles SLEEP/WAKE cycles, an — from…
Open source biomedical Model Context Protocol (MCP) toolkit for connecting LLMs to biomedical data sources (PubMed, ClinicalTrials, Genomics).
AI-powered bone marrow morphology analysis, cell classification, and hematologic disorder diagnosis using deep learning on aspirate and biopsy images.
Use before any code changes - hard gate ensuring work never happens on main branch, with proper feature branch creation from correct base — from general/ai-tooling
Continuous learning system that monitors all user requests and interactions to identify learning opportunities.
Guide for creating and validating Claude Code plugin.json files. Use when creating plugins, validating plugin schemas, or troubleshooting plugin configuration.
Use after implementing features - 7-criteria code review with MANDATORY artifact posting to GitHub issue; blocks PR creation until complete — from general/ai-tooling
Use when encountering merge conflicts - handle conflicts cleanly, verify resolution, and maintain code integrity
Automatically assigns GitHub issues to appropriate GitHub Copilot agents based on issue type, labels, and content.
Use when a review finding cannot be fixed in current PR - creates properly documented tracking issue with full context, linked to parent, following full issue-driven-deve — from…
Prompt optimization for LLMs. Trigger when the user wants to improve a prompt, add examples, or structure instructions.
Use for development environment setup - create and maintain init scripts, run smoke tests, ensure consistent environment across sessions
Use when encountering failures - assess severity, preserve evidence, execute rollback decision tree, and verify post-recovery state
Use when user-facing features change. Ensures features documentation is updated. Pauses work if documentation has drifted, triggering documentation-audit skill.
[Trigger] When PPT workflow needs SVG slide layout and aesthetic optimization via Gemini. [Output] Structured optimization suggestions with scores and concrete layout/style…
Guide for implementing Google Gemini API image generation - create high-quality images from text prompts using gemini-2.5-flash-image model.
Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image…
Use when discovering, exploring, or retrieving gluestack-ui components via MCP tools. Provides access to component source code, variants, demos, and metadata.
Build document Q&A with Gemini File Search - fully managed RAG with automatic chunking, embeddings, and citations. Upload 100+ file formats, query with natural language.
Triage and batch-implement Claude-tagged Things todos as PRs for the claude config repo. Use when the user wants to work on their Claude Code improvement backlog, process Things…
Install skills, agents, and teams from agent-almanac into any supported agentic framework using the CLI.
Use when an issue is too large for a single task - breaks into linked sub-issues with full documentation, ensuring manageable work units
Use for any development work - the master 13-step coding process that orchestrates all other skills, ensuring GitHub issue tracking, proper branching, TDD, code review, a — from…
Use throughout all work - ensures GitHub issues are updated continuously as work happens, not batched at the end
Use before starting ANY work - hard gate ensuring a GitHub issue exists, creating one if needed through user questioning — from general/ai-tooling
LangChain 框架学习笔记 - 快速查找概念、代码示例和最佳实践。包含 Core components、Middleware、Advanced usage、Multi-agent patterns、RAG retrieval、Long-term memory 等主题。当用户询问…
Human interface agent that translates ecosystem activity into clear, actionable communication. Creates status briefings, decision requests, celebration reports, concern alerts,…
Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.
CLAUDE.md 및 CLAUDE.local.md 파일을 관리하는 스킬. 프로젝트 컨텍스트를 최적의 상태로 유지한다.
Integrate and use codex-cli MCP server effectively with Claude Code. Use when executing shell commands, running builds, or performing file operations through the codex-cli MCP…
Run multiple Ralph loops concurrently for independent tasks. Manages parallel agent execution with proper isolation and result aggregation.
Read-only multi-agent ship queue dashboard. Shows what each agent is shipping, what's in flight, what version slots are claimed, and what /ship would pick next.
Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking
RAG 시스템 품질 평가 및 개선을 위한 스킬입니다. RAGAS 기반 LLM-as-Judge 평가, 사용자 페르소나 시뮬레이션, 합성 데이터 생성, 평가 결과 저장 및 분석 기능을 제공합니다.
Cross-encoder reranking and MMR diversity filtering for improved retrieval quality
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE,…
Use when choosing between supervisor, swarm, or pipeline coordination for multi-agent workflows, when two agents produce conflicting findings and deduplication is needed, when…
Stochastic multi-agent consensus. Spawns N agents with identical prompts to independently analyze a problem.
Backing skill for the /ultra:run and /ultra:resume slash commands — multi-agent swarm with adversarial validation, structured debates, devil's advocate, and anti-AI-slop checks.
Criar especificações detalhadas. Ativa com "escrever spec", "definir requisitos", "design detalhado".