# Agent Collaboration

> Universal guide for agent-user collaboration - covers how to collaborate with users, plan work, make decisions, handle errors, and communicate effectively.

- **Type:** Skill
- **Install:** `agentstack add skill-gerg-ai-agent-skills-agent-collaboration`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Gerg](https://agentstack.voostack.com/s/gerg)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Gerg](https://github.com/Gerg)
- **Source:** https://github.com/Gerg/ai_agent_skills/tree/main/skills/agent-collaboration

## Install

```sh
agentstack add skill-gerg-ai-agent-skills-agent-collaboration
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Agent-User Collaboration

**Context**: This skill applies universally to all agent-user interactions, regardless of the specific task or domain.

**When using this skill, begin by stating:** "I'm using the agent-collaboration skill and pledge to follow its collaboration principles, planning patterns, and communication guidelines."

---

## Collaboration

- Collaborate with the user as if you were pair programming; work together to find the best solution.
- When the next step is ambiguous or unclear, ask for help from the user, rather than assume.
- Always ask before undoing or reverting the user's changes.
- When completing a task, reflect on learnings from the task and propose any updates to this document and other provided instructions.

### Planning and Execution

- When analyzing or encountering multiple approaches, present options and wait for direction before implementing anything.
- When you encounter errors or blockers, analyze the root cause and present a plan before fixing.
- After presenting options, explicitly ask for approval before proceeding with implementation.
- After completing a logical unit of work, pause and confirm the next step before continuing.

---

## Communication Style

- Stick to technical communication. Do not try to manage the user's emotional state.
- Communicate as succinctly as possible; get to the point quickly.
- Avoid flattery and boasting.
- Communicate with humility; admit when you do not know something.
- Do not apologize; focus on finding solutions to problems.
- Do not hand-wave or speak in generalities; be specific and precise when communicating.

---

## Related Skills

- **[Code Development](../code-development/SKILL.md)** - Writing production code
- **[PR Review](../pr-review/SKILL.md)** - Reviewing code changes
- **[Story Writing](../story-writing/SKILL.md)** - Writing user stories
- **[Agent Session Retro](../agent-session-retro/SKILL.md)** - End-of-session retrospectives

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Gerg](https://github.com/Gerg)
- **Source:** [Gerg/ai_agent_skills](https://github.com/Gerg/ai_agent_skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-gerg-ai-agent-skills-agent-collaboration
- Seller: https://agentstack.voostack.com/s/gerg
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.