agent-team-builder
Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.
What this skill does
# Agent Team Builder
Design and generate production-ready multi-agent team configurations for business workflows through an interactive discovery session. This skill generates configuration files; it does not execute or deploy agents.
## Contents
- `references/team-templates.md` — Sales, Support, Research, and Content team starting points.
- `references/config-schema.md` — Full `team-config.yaml` schema plus advanced features (A2A messaging, scaling, shared context).
- `references/output-files.md` — Files to generate and the final response format.
## Workflow
Always complete discovery before designing. Never generate a team config without understanding the business process first.
1. **Run discovery.** Ask the user, one area at a time:
- Process name (what to automate).
- Current state (who is involved, handoff points).
- Pain points (where delays, errors, or bottlenecks occur).
- Volume (runs per day/week/month).
- Success metrics (time, error rate, satisfaction).
- Constraints (compliance, approval gates, human-in-the-loop).
- Integrations (CRM, email, Slack, databases, APIs).
2. **Design the team architecture.** Determine the minimum number of agents (typically 3-7). Select role types as needed:
- Coordinator — orchestrates workflow, routes tasks, handles exceptions.
- Specialist — deep expertise in one domain.
- Validator — quality assurance, compliance checking, output review.
- Interface — handles external communication.
- Data — manages retrieval, transformation, and storage.
Pick a communication pattern: hub-and-spoke (sequential), pipeline (linear), mesh (collaborative), or broadcast (notification). Start from a template in `references/team-templates.md` when one fits.
3. **Specify each agent.** Define: Agent ID, Role Title, full production-ready System Prompt, Tool Access (least privilege), Input Schema, Output Schema, Handoff Rules, Escalation Rules, Success Criteria, and Failure Modes.
4. **Generate the configuration files.** Produce `team-config.yaml`, per-agent `agents/{id}/prompt.md`, `workflow.md`, and `test-scenarios.yaml` per `references/output-files.md`, conforming to `references/config-schema.md`.
5. **Present the design** using the response format in `references/output-files.md`.
## Execution Rules
1. Always start with discovery.
2. Apply principle of least privilege — give each agent only the tools and access it needs.
3. Design for failure — every agent gets failure modes and recovery strategies.
4. Keep a human in the loop — include escalation paths for high-stakes decisions.
5. Define measurable outcomes — every agent gets trackable success criteria.
6. Start small — recommend 3-4 agents and expand based on performance data.
7. Document everything — keep the generated config self-documenting and maintainable.
8. Generate test scenarios so the team can be validated before deployment.
9. Recommend a pilot phase before full deployment.
10. Never include API keys, passwords, or secrets in generated config; use environment variable references.
The generated `team-config.yaml` is designed to be consumed by an agent orchestration framework. Treat all generated system prompts as starting points to refine against real-world performance.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.