adaptive-team-consult — for Claude Code adaptive-team-consult, adaptive-dev-team, community, for Claude Code, ide skills, (create from template if missing) 3, database, llm-expert, architect, TeamCreate

v1.0.0

Acerca de este Skill

Escenario recomendado: Ideal for AI agents that need adaptive team consult. Resumen localizado: A self-healing Claude Code agent team for structured software development.

Características

Adaptive Team Consult
Step 0: PM Recovery / Grounding
PM reads, in order:
.claude/rules/adaptive-team-rules.md
.claude/adaptive-team-state/current-session.md (create from template if missing)

# Temas principales

lwstory lwstory
[1]
[0]
Actualizado: 4/24/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Escenario recomendado: Ideal for AI agents that need adaptive team consult. Resumen localizado: A self-healing Claude Code agent team for structured software development.

¿Por qué usar esta habilidad?

Recomendacion: adaptive-team-consult helps agents adaptive team consult. A self-healing Claude Code agent team for structured software development.

Mejor para

Escenario recomendado: Ideal for AI agents that need adaptive team consult.

Casos de uso accionables for adaptive-team-consult

Caso de uso: Applying Adaptive Team Consult
Caso de uso: Applying Step 0: PM Recovery / Grounding
Caso de uso: Applying PM reads, in order:

! Seguridad y limitaciones

  • Limitacion: Default minimum: architect. Spawn only those the signal warrants — do not invite everyone by habit.
  • Limitacion: If a team exists, join it — do not recreate. Otherwise TeamCreate with a descriptive name. Update current-session.md.
  • Limitacion: Spawn only those the signal warrants — do not invite everyone by habit

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Demo Labs

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ y pasos de instalación

These questions and steps mirror the structured data on this page for better search understanding.

? Preguntas frecuentes

¿Qué es adaptive-team-consult?

Escenario recomendado: Ideal for AI agents that need adaptive team consult. Resumen localizado: A self-healing Claude Code agent team for structured software development.

¿Cómo instalo adaptive-team-consult?

Ejecuta el comando: npx killer-skills add lwstory/adaptive-dev-team/adaptive-team-consult. Funciona con Cursor, Windsurf, VS Code, Claude Code y más de 19 IDE adicionales.

¿Cuáles son los casos de uso de adaptive-team-consult?

Los casos de uso principales incluyen: Caso de uso: Applying Adaptive Team Consult, Caso de uso: Applying Step 0: PM Recovery / Grounding, Caso de uso: Applying PM reads, in order:.

¿Qué IDE son compatibles con adaptive-team-consult?

Esta skill es compatible con Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Usa la CLI de Killer-Skills para una instalación unificada.

¿Tiene limitaciones adaptive-team-consult?

Limitacion: Default minimum: architect. Spawn only those the signal warrants — do not invite everyone by habit.. Limitacion: If a team exists, join it — do not recreate. Otherwise TeamCreate with a descriptive name. Update current-session.md.. Limitacion: Spawn only those the signal warrants — do not invite everyone by habit.

Cómo instalar este skill

  1. 1. Abre tu terminal

    Abre la terminal o línea de comandos en el directorio de tu proyecto.

  2. 2. Ejecuta el comando de instalación

    Ejecuta: npx killer-skills add lwstory/adaptive-dev-team/adaptive-team-consult. La CLI detectará tu IDE o agente automáticamente y configurará la skill.

  3. 3. Empieza a usar el skill

    El skill ya está activo. Tu agente de IA puede usar adaptive-team-consult de inmediato en el proyecto actual.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

adaptive-team-consult

Install adaptive-team-consult, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Adaptive Team Consult

PM brings in the specialists whose lenses fit the topic and facilitates a plain-English discussion. No code is written; the output is shared understanding and a direction.

Pipeline

Step 0: PM Recovery / Grounding

PM reads, in order:

  1. .claude/rules/adaptive-team-rules.md
  2. .claude/adaptive-team-state/current-session.md (create from template if missing)
  3. .claude/adaptive-team-learned/pm-lessons.md
  4. TaskList

Step 1: Classify the Topic

PM identifies topic signals and selects reviewers per the Consult Mode rubric in the rules:

SignalSpawn
Schema, query, migration, index, graphdatabase
Prompt, tool use, model choice, agent design, evalllm-expert
Auth, permissions, authz, secretsarchitect
Test strategy, coverage, flakesdet
Architecture / coherencearchitect
Ambiguousarchitect as default

Default minimum: architect. Spawn only those the signal warrants — do not invite everyone by habit.

Step 2: Create or Join Team

If a team exists, join it — do not recreate. Otherwise TeamCreate with a descriptive name. Update current-session.md.

Step 3: Spawn Selected Reviewers

Use the deterministic names: architect, sdet, llm-expert, database. Each completes its startup sequence.

Step 4: Facilitate the Consult

PM forwards the user's topic to spawned reviewers and asks each for:

  • Their plain-English read
  • Risks or constraints specific to their lens
  • Recommended direction (not code)

Each reviewer writes a full analysis to .claude/adaptive-team-reviews/consult/<short-slug>/<reviewer>.md and returns a short summary to PM. PM synthesizes for the user by showing one paragraph per reviewer, verbatim from the summary line — PM does not re-author.

Step 5: Decide or Iterate

User decides the direction, asks follow-ups, or requests /adaptive-team-implement to build.

Step 6: Update Session State

PM updates current-session.md with any key decisions and the set of spawned reviewers (which remain persistent for this session).

When to Use

  • Approach or design questions before implementation
  • Choosing between options (model, schema, framework)
  • Understanding risk and tradeoffs on a specific topic

When NOT to Use

  • Actual implementation → /adaptive-team-implement
  • Capturing a lesson from something that went wrong → /adaptive-team-learning-moment

Habilidades relacionadas

Looking for an alternative to adaptive-team-consult or another community skill for your workflow? Explore these related open-source skills.

Ver todo

openclaw-release-maintainer

Logo of openclaw
openclaw

Resumen localizado: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

333.8k
0
Inteligencia Artificial

widget-generator

Logo of f
f

Resumen localizado: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and

149.6k
0
Inteligencia Artificial

flags

Logo of vercel
vercel

Resumen localizado: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
Navegador

pr-review

Logo of pytorch
pytorch

Resumen localizado: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
Desarrollador