Навыки: Разработка

Scaffold MCP server projects and baseline tool contract checks. Use for defining tool schemas, generating starter server...

在 Claude Code 上构建持久化多智能体操作系统——涵盖内核架构、专业 Agent、斜杠命令、文件记忆、定时自动化及无外部数据库的状态管理

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash comm...

Build persistent multi-agent operating systems on OpenAI Codex. Covers kernel architecture, specialist agents, slash com...

Build persistent multi-agent operating systems

Design and operate multi-agent orchestration patterns (ReAct loops, evaluator-optimizer, orchestrator-workers, tool rout...

Design, implement, or harden an AI website-building agent that turns natural-language requests into scoped code changes...

Collaborative programming framework for production-ready development. Use when starting features, writing code, handling...

Test-driven development for behaviour a unit test cannot reach, by writing the expectation against the running app befor...

Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the walle...

Route broad or ambiguous AgentKit SEO work to the right module while keeping context scoped. Use when a request spans mu...

Optimize CV and resume content for recruiter readability and parser-safe ATS handling without making unsupported claims...

Optimize GitHub profile and repository discoverability, clarity, and trust signals using documented search, metadata, an...

Optimize LinkedIn profile structure and discoverability for headline, about, featured, experience, skills, and AI-readab...

Optimize personal website and web portfolio discoverability, crawlability, metadata, structured data, content usefulness...

Optimize X and Twitter profile positioning, pinned post strategy, posting structure, and discoverability using conservat...

Use when the user types /agentlas-build, /agentlas build, or /hep-build to design, build, and package a single agent or...

Use when an agent folder must pass the Agentlas Cloud 2-stage security scan (static rules + BYOK LLM judgment) before pr...

Use when an agent needs AgentMail CLI email inboxes.

Build with the AgentMail TypeScript or Python SDK for inbox, message, thread, draft, attachment, domain, allow/block lis...

Email inbox for AI agents. Check messages, send emails, and communicate via your own @agentmail.to address.

Generate a single canonical AGENTS.md context file plus minimal CLI-specific shim files that @-import it for coding agen...

Use when the user types /agento <command> [args]: routes an Agento command to its skills/agento/commands/<name>.md and r...

Imported skill agents from langchain

Imported from AGENTS.md

Test a Frontline agent end-to-end from the terminal using frontline agents chat (Overview/Playground channel). Use when...

Split a bloated AGENTS.md / CLAUDE.md / README into a small always-loaded kernel plus task-routed wiki topics, loaded on...

Generate or maintain a minimal high-signal AGENTS.md for coding agents. Use whenever a repo needs agent instructions, an...

Owns instruction files: AGENTS.md, CLAUDE.md, personal and repo rules. Use when writing, pruning, auditing them, sharing...

Build stateful Agents on Cloudflare Workers with current, source-verified SDK APIs. Covers durable state, RPC, chat, sch...

Redesign the assigned repository or repositories for agent understanding, control, and cumulative learning. Use when ask...

Stores and retrieves per-user, per-project preferences for AI skills via a unified JSON-backed CLI. Loaded by consumer s...

SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format +...

Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, t...

Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" S...

Enhancement-overlay SOP for adding sparse (BM25 / keyword) retrieval alongside dense (embedding) retrieval. Activate whe...

Re-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an ingestion pipe...

Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is...

Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agen...

ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / Prog...

Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any...

Pick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitiv...

Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins,...

Tool skill — the *first move* in any LM-debugging session: dump the actual rendered prompt the framework sent to the mod...

Build a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code chan...

A 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace...

Decision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dsp...

See what your AI agent is doing, from anywhere. The agent keeps writing — logs, code, generated outputs, screenshots, ar...