Навыки: Разработка

Resume a Claude Code or Codex session later, from outside it. Use to get a status message when a long job finishes, or t...

Run a multi-agent audit of a feature, PR/diff, or task spec in which Codex, Command Code (cmd), Gemini, OpenCode and Cla...

Tags: agents, execution, claude-api, orchestration, layer2

Specialist subagent: Rust ownership/borrowing, async Rust, Axum/Actix web frameworks, and WASM specialist. Use when writ...

Guide for creating samples by GitHub Copilot. Use this when instructed to create samples.

Agent skill for sandbox - invoke with $agent-sandbox

File templates for Claude Agent SDK project scaffolding. Used by /agent-sdk:agent-scaffold command.

Guided workflow for building custom AI agents using the OpenHands Software Agent SDK. Use when you want to create a new...

Agent SDK development utilities for creating, testing, and managing AI agents with comprehensive tooling and debugging c...

Guide for Claude Agent SDK - build custom AI agents powered by Claude. Triggers on agent sdk, claude-agent-sdk, @anthrop...

Choose and run the right search tool: rg vs grep vs ast-grep vs fd vs fzf. Bounded repo navigation with ripgrep, fd, tre...

Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files,...

Specialist subagent: Technical SEO, structured data, Core Web Vitals, meta tags, and Schema.org specialist. Use when opt...

Use when inventorying, unifying, installing or synchronizing local Claude Code, Codex, Cursor or Antigravity skills and...

Run manual development checks for SwiftAutoGUI AI Agent actions through the local sagui CLI. Use when Claude or Codex ne...

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into...

通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查，为特定仓库构建基于证据的 ECC 安装计划，将其分为 DAILY 和 LIBRARY 两类。当 ECC 应精简为项目实际所需而非加载完整包时使用。

通过并行且具备仓库感知的审查过程，将技能、命令、规则、钩子和附加项分类到 DAILY (日常) 与 LIBRARY (库) 桶中，为特定仓库构建有证据支持的 ECC 安装计划。当需要将 ECC 裁剪到项目实际需要的内容，而非加载完整包时使用...

Build an evidence-backed Codex install plan for a specific repo by sorting skills, commands, rules, hooks, and extras in...

Build an evidence-backed ECC install plan

Manage the project's DuckDB state ledger (.agent/state.duckdb) - features, validation contract, sprint steps and the app...

Work on SSE streaming, plain-text transport, ChatKit events, and session continuity. Use when debugging or modifying age...

Specialist subagent: Svelte 5 runes, SvelteKit routing, form actions, and compile-time reactivity specialist. Use when b...

Audit and remediate AgentSystem cron output hygiene by detecting raw tool logs, stack traces, and noisy summaries. Use w...

Team composition knowledge for Claude Code Agent Teams - when teams fit, optimal sizing, spawn prompt patterns. Use only...

Define agent tools using the fail-closed design pattern — unified name/schema/security/execution in one class, with thre...

**UTILITY SKILL** — Browse the tool names a runtime accepts in a custom agent's `tools:` frontmatter and produce a valid...

Upgrades an existing Claude Agent project to the current config schema — migrates information from old locations to new...

エージェントの検証とテストケース設計を専門とするスキル。**Anchors:**• Test-Driven Development: By Example（Kent Beck）/ 適用: エージェント検証とテストケース設計 / 目的: Re...

Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting...

Use for Crewrift-specific agent workflow collab recipes when optimizing a player.

Yuanbao groups — @mention users, info/members query, Chinese AI assistant

Add Agentation visual feedback toolbar to a Next.js project

Lets an AI agent pay merchants securely with the user's own card — through Mastercard Agent Pay (the default for Masterc...

Vector search and semantic memory backbone for agents and RAG pipelines.

Learning loops on top of AgentDB for reinforcement, curriculum, and replay buffers.

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer,...

Performance tuning for AgentDB across indexing, storage, and query paths.

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, an...

Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.

Data Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a...

Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user create...

Work on AgentForge CLI commands, project creation, run/start flows, and developer ergonomics in packages/cli.

Comprehensive Convex development skill for building production-ready apps. Covers functions (queries, mutations, actions...

Work on the AgentForge web dashboard built with React, Vite, TanStack Router, and Convex-backed state.

Designing features for the "Action Era" that are AI-accessible by default

Architecture guidelines for Jarvy CLI - codebase structure, tool implementation patterns, registry system, platform-spec...

Assess agentic layer maturity using the 12-grade classification system (Class 1-3). Use when evaluating codebase readine...