- Home
- Skills
- Business & Operations
- StreamTeem Engineering Manager Expert
Works with the AI Agents you already use
StreamTeem Engineering Manager Expert
It writes a brief, then a charter with its diagrams, and stops for your approval.
$4.99
StreamTeem Engineering Manager Expert
Example session with this skill installed
The payments squad is slipping on the API migration. Start a Team Escalation under work item EM-731. Who is affected: the payments squad and the platform API owners. Decision needed now: whether to cut scope this sprint or pull two engineers from another squad for two weeks. No outside references yet.
- Read your context and instructions
- Compiled the streamteem engineering manager
Work item EM-731 is set up on the
Team Escalation workflow. Your role was already defined, so I went straight to the work item and its first phase, assess-situation.
Where things stand
| Item | Value |
|---|---|
| Work item | EM-731, payments squad API migration slip |
| Workflow | Team Escalation |
| Phase | Assess situation |
| Journal | engineering-manager/journals/work-items/EM-731/progress.md |
| Assessment (not written yet) | engineering-manager/work-items/EM-731/docs/escalations/assessment.md |
What I need before I write the assessment
"Continue" is not an answer.
- Confirm the facts: what is late, by how much, and what was committed.
- Who is affected beyond the payments squad and the platform API owners?
- What decision is needed now, and who can make it?
- Any people-sensitive context that must stay on this work item only?
Next steps
- Answer those questions. I record each answer in the journal in the same turn, then write
assessment.md. - Next comes impact analysis with options and who decides, then I stop until you say "I approve the response" or "Skip response approval".
- Only after that do I write the response record and what is being watched.
Connects securely to your tools. The creator never sees your data.
About this skill
Engineering Manager Expert makes your agent run a team toward an outcome the way an engineering manager does: delivery risk, delegation, staffing, stakeholder updates, and escalations, with the decisions written down.
Say "start". The pack asks what outcome the team is accountable for, who is on the team and who decides, what success looks like this period, and which staffing or dependency constraints are already known. It writes a brief, then a charter with its diagrams, and stops for your approval. The operating plan follows (milestones, owners, risks, 1:1 and hiring implications, stakeholder cadence, decisions needed) with a second approval gate. Only then does it write the action list, create the 1:1 cadence, the delivery tracker, the decision log, and the stakeholder list, and work through the actions one at a time: 1:1 agendas, hiring-loop notes, delivery-risk updates, delegation notes, stakeholder status. Verification and a close-out finish the work item.
A second workflow handles escalations: delivery slips, an urgent people decision, a production issue that lands on the team. It assesses, lays out the options and who decides, waits for your approval of a response, then records what was communicated and what is being watched.
Everything the pack knows lives in an engineering-manager/ folder in your project: a journal with the next step, the documents, and a memory of facts and rules about your role. Close the session, switch agents, come back next week, and "continue" picks up at the exact step where the work stopped.
What makes it different:
- "Continue" is never taken as approval. A gate clears only when you say "I approve the charter" (or the plan, the change, the response).
- Headcount and offers stay recommendations. The agent does not approve them unless you explicitly approve that action.
- People-sensitive notes (private conversations, performance, personal circumstances) stay on the work item and out of the role's long-term memory unless you say otherwise.
- It remembers. The pack starts with ten facts and ten rules for the role and adds your own.
- Skill names are prefixed
em-, so the pack installs beside the other StreamTeem packs.
Works on local Markdown files only; it does not send Slack or email, and it does not connect to Jira, Linear, or other tracking tools. Viewing the diagram page needs internet access, because the page loads Mermaid from a CDN. Python 3 is needed only to run the optional memory analysis script; without it the agent does the same counts by reading the files.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Requires
Permissions
Read/Write create the journal, charters, plans, diagrams, trackers, and notes under one folder in the project. Shell runs only the bundled read-only memory analysis script, and only when you ask for a memory check.