Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

agents-architect-skill

Estrellas0

Forks0

Actualizado14 de abril de 2026 a las 19:07

Author a single skill from a short brief. Use to add a skill to an existing plugin or iterate on a skill's description/body.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

Ibrahim-3d

Ibrahim-3d/agents-architect

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

Explorador de archivos

9 archivos

SKILL.md

readonly

name	agents-architect:skill
description	Author a single skill from a short brief. Use to add a skill to an existing plugin or iterate on a skill's description/body.
argument-hint	<skill-name> "<one-line purpose>" [--plugin <path>] [--siblings <a,b,c>]
allowed-tools	["Read","Write","Task","AskUserQuestion"]

Fast path to a single, well-triggered skill without running full /agents-architect:new.

<execution_context> @${CLAUDE_PLUGIN_ROOT}/agents-architect/templates/skill.template.md </execution_context>

Arguments: $ARGUMENTS — name, purpose, optional plugin path and sibling skills for disambiguation. 1. Parse args. If plugin path omitted, default to current working directory. 2. `AskUserQuestion` to fill gaps: target trigger phrases (10-30), examples of prompts that should fire it, examples that should NOT. 3. Spawn `agents-architect-skill-author` with the filled brief. It writes `skills//SKILL.md`, `reference.md` (if needed), `evals/`. 4. Report back the produced files + trigger surface. Paths of produced files + 5-line summary.

Más de este repositorio

mismo repositorio

agent-authoring

Ibrahim-3d/agents-architect

Write or refactor Claude Code sub-agent definitions (files in agents/*.md). Use when the user asks to "create a subagent", "add an agent for X", "build a specialist agent", "make a research agent", "write an agent file", "agent YAML", "delegate to a subagent", "design a multi-agent workflow", or when a task needs a fresh context window, restricted tools, or isolation. Covers frontmatter (tools/model/effort/maxTurns/isolation), delegation patterns, read-only constraints, and orchestrator↔specialist contracts.

2026-04-140

command-authoring

Ibrahim-3d/agents-architect

Write or refactor Claude Code slash commands (files in commands/<ns>/<cmd>.md). Use when the user asks to "create a slash command", "add /<name>", "write a command file", "make a /command", "turn this workflow into a command", "argument hints", "allowed-tools", or when packaging a repeatable workflow as a one-keystroke invocation. Covers frontmatter, $ARGUMENTS parsing, @-imports for context files, and orchestration patterns.

2026-04-140

context-management

Ibrahim-3d/agents-architect

Design and optimize context windows for agentic workflows. Use when the user asks to "manage context", "optimize context", "compact context", "context budget", "CLAUDE.md", "memory hierarchy", "context degradation", "agent is forgetting", "agent hallucinating after many turns", "long conversation", "hit token limit", "prune context", "memory tiers", or when a multi-turn workflow shows quality decay. Covers CLAUDE.md authoring, tiered memory, scratchpads, /compact strategies, read-depth rules, and subagent delegation for context relief.

2026-04-140

domain-research

Ibrahim-3d/agents-architect

Research a domain end-to-end before scaffolding an agentic system for it. Use when the user asks to "research [domain]", "learn about [field]", "what are the best practices for X", "survey the tools for Y", "what MCPs exist for Z", "before we build the agent, understand [topic]", or when kicking off a new /agents-architect:new for an unfamiliar domain. Covers methodology: taxonomy → tools → MCPs → idioms → anti-patterns → eval cases. Produces DOMAIN.md.

2026-04-140

mcp-integration

Ibrahim-3d/agents-architect

Select, scaffold, or integrate Model Context Protocol (MCP) servers with a Claude Code plugin. Use when the user asks to "add an MCP", "which MCP for X", "connect to [service]", "find a server for [API/tool]", "wrap [tool] as an MCP", ".mcp.json", "MCP server config", or when a domain needs external tools Claude doesn't have (Blender, Figma, ClickUp, arxiv, a CAD program, etc.). Covers MCP discovery via registry, config schema, env/userConfig wiring, and fallback to CLI when no MCP exists.

2026-04-140

plugin-packaging

Ibrahim-3d/agents-architect

Package a collection of skills/agents/commands/hooks as a distributable Claude Code plugin. Use when the user asks to "package this as a plugin", "create a plugin.json", "build a marketplace entry", "make this installable", "publish my plugin", "plugin manifest", "validate my plugin", or when bundling work for others to install via /plugin marketplace add. Covers plugin.json schema, marketplace.json, CLAUDE_PLUGIN_ROOT, userConfig, and validation.

2026-04-140

name	agents-architect:skill
description	Author a single skill from a short brief. Use to add a skill to an existing plugin or iterate on a skill's description/body.
argument-hint	<skill-name> "<one-line purpose>" [--plugin <path>] [--siblings <a,b,c>]
allowed-tools	["Read","Write","Task","AskUserQuestion"]

Fast path to a single, well-triggered skill without running full /agents-architect:new.

<execution_context> @${CLAUDE_PLUGIN_ROOT}/agents-architect/templates/skill.template.md </execution_context>