agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
Skill by microsoftOfficial
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/microsoft-agent-collaboration
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-collaboration
What's inside
- Skill name
agent-collaboration- Description
- Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
- License
- MIT
- Instructions
- 45 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Context
Every agent on the team follows identical collaboration patterns for worktree awareness, decision recording, and cross-agent communication. These were previously duplicated in every charter's Collaboration section (~300 bytes × 18 agents = ~5.4KB of redundant context). Now centralized here.
The coordinator's spawn prompt already instructs agents to read decisions.md and their history.md. This skill adds the patterns for WRITING decisions and requesting help.
## Patterns
### Worktree Awareness
Use the `TEAM ROOT` path provided in your spawn prompt. All `.squad/` paths are relative to this root. If TEAM ROOT is not provided (rare), run `git rev-parse --show-toplevel` as fallback. Never assume CWD is the repo root.
### Decision Recording
After making a decision that affects other team members, write it to:
`.squad/decisions/inbox/{your-name}-{brief-slug}.md`
Format:
```
### {date}: {decision title}
**By:** {Your Name}
**What:** {the decision}
**Why:** {rationale}
```
### Cross-Agent Communication
If you need another team member's input, say so in your response. The coordinator will bring them in. Don't try to do work outside your domain.
### Reviewer Protocol
If you have reviewer authority and reject work: include concrete counter-evidence,
the violated requirement, affected scope, and minimum condition for approval.
The Coordinator assigns a different qualified revision owner, not the locked-out
author or rejecting gate. Do not implement, pair on, or advise the immediate
revision; perform only the focused rereview. After successful focused rereview of the independently
corrected revision, the selected gate may issue approval/PASS, not native repository approval,
merge or publishing authority. This is Squad coordination, not an ordinary Copilot workflow.
**Rai/Fact Checker output boundary:** Charter output/persistence restrictions take precedence over generic history, audit-trail or
decision-inbox instructions. Return findings in the current review response; only an authorized
coordinator or Scribe handles required persistence under the current state contract.
## Anti-Patterns
- Don't read all agent charters — you only need your own context + decisions.md
- Don't write directly to `.squad/decisions.md` — always use the inbox drop-box
- Don't modify other agents' history.md files — that's Scribe's job
- Don't assume CWD is the repo root — always use TEAM ROOTFrom microsoft/waza, MIT.
More from microsoft/waza
- 0.827score
waza-runner
spboyerOfficial
Run evaluations on Agent Skills to measure their effectiveness.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.825score
azd-publish
spboyerOfficial
Prepare and publish a new version of the waza azd extension.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
coordinator-init-mode
microsoftOfficial
The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
squad
microsoftOfficial
Squad's command catalog and interactive menu.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
code-explainer
microsoftOfficial
**UTILITY SKILL** - Explain code snippets, functions, and algorithms in plain language.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
waza
microsoftOfficial
**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
coordinator-response-mode
microsoftOfficial
Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is Response Mode.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
iterative-retrieval
microsoftOfficial
Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
squad-commands
microsoftOfficial
Categorized catalog of common Squad operations.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
cross-squad
microsoftOfficial
Coordinating work across multiple Squad instances — discovery, delegation, and disambiguation when the user says 'squad' (the product) vs casual English…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
coordinator-source-of-truth
microsoftOfficial
The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
waza-interactive
microsoftOfficial
Interactive workflow partner for creating, testing, and improving AI agent skills with waza.
SkillAFreshness: A★ 1.4KClaude Code +9
Signals
- Stars
- 1,427
- Forks
- 92
- Open issues
- 5
- Last commit (this folder)
- Oct 16, 2026 (12 days ago)
- Last release
- Oct 20, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/microsoft/waza
- Website
- microsoft.github.io/waza/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.278score
agent-collaboration
jb-apei
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
SkillCFreshness: CClaude Code +9 - 0.278score
agent-collaboration
kamelkh
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
SkillCFreshness: CClaude Code +9
More from microsoft
- 0.714score
skillopt-sleep
microsoftOfficial
Reference-only OpenClaw adaptation of SkillOpt-Sleep.
SkillAFreshness: A★ 18.7KClaude Code +9 - 0.707score
Playwright MCP
microsoftOfficial
Playwright Tools.
ConnectorAFreshness: ALocal★ 38.6KClaude Code +5 - 0.687score
squad
microsoftOfficial
Squad's command catalog and interactive menu.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
coordinator-response-mode
microsoftOfficial
Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is Response Mode.
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
coordinator-source-of-truth
microsoftOfficial
The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may…
SkillAFreshness: A★ 1.4KClaude Code +9 - 0.687score
squad-commands
microsoftOfficial
Categorized catalog of common Squad operations.
SkillAFreshness: A★ 1.4KClaude Code +9
Cite this page
agent-collaboration skill. Agent Mart. https://agentmart.dev/skills/microsoft-agent-collaboration (last updated 2026-10-24)