agent-teams-dm-default-always-prefer
Sub-skill of agent-teams: DM (default — always prefer) (+2).
Best use case
agent-teams-dm-default-always-prefer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sub-skill of agent-teams: DM (default — always prefer) (+2).
Teams using agent-teams-dm-default-always-prefer should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/dm-default-always-prefer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-teams-dm-default-always-prefer Compares
| Feature / Agent | agent-teams-dm-default-always-prefer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sub-skill of agent-teams: DM (default — always prefer) (+2).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# DM (default — always prefer) (+2)
## DM (default — always prefer)
```python
SendMessage(type="message", recipient="teammate-name",
content="Graph YAML looks good. Add edge: skill-creator → improve.",
summary="Graph edge addition request")
```
## Broadcast (expensive — use only for critical team-wide issues)
```python
SendMessage(type="broadcast",
content="STOP. Found a merge conflict in SKILLS_GRAPH.yaml. Hold all writes.",
summary="Critical: stop all writes")
```
Broadcast = N messages (one per teammate). Use for genuine emergencies only.
## Plan approval (when teammate has plan_mode_required)
```python
SendMessage(type="plan_approval_response", request_id="abc-123",
recipient="teammate", approve=True)
```Related Skills
teams-meeting-pipeline
Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.
parallel-batch-executor-1-always-set-a-default
Sub-skill of parallel-batch-executor: 1. Always Set a Default (+4).
json-config-loader-1-always-provide-defaults
Sub-skill of json-config-loader: 1. Always Provide Defaults (+4).
git-sync-manager-1-always-check-before-operating
Sub-skill of git-sync-manager: 1. Always Check Before Operating (+4).
agent-teams-workspace-work-profile-updated-2026-03-10
Sub-skill of agent-teams: Workspace Work Profile (Updated 2026-03-10).
agent-teams-work-queue-integration
Sub-skill of agent-teams: Work Queue Integration.
agent-teams-subagent-startup-convention
Sub-skill of agent-teams: Subagent startup convention (+2).
agent-teams-idle-state
Sub-skill of agent-teams: Idle State.
agent-teams-decision-matrix-team-vs-sequential
Sub-skill of agent-teams: Decision Matrix: Team vs Sequential.
agent-teams-core-constraint
Sub-skill of agent-teams: Core Constraint.
agent-teams-agent-types-for-common-tasks
Sub-skill of agent-teams: Agent Types for Common Tasks.
agent-teams-activation
Sub-skill of agent-teams: Activation.