chatting-with-aws-devops-agent

Name: chatting-with-aws-devops-agent
Author: aws

258installs190forks

How to install chatting-with-aws-devops-agent?

aws/agent-toolkit-for-aws/chatting-with-aws-devops-agent

$npx -y skills add aws/agent-toolkit-for-aws --skill chatting-with-aws-devops-agent

Installs into the current project.

Summary

Have a fast, conversational analysis with the AWS DevOps Agent. Use for cost optimization, architecture review, topology mapping, knowledge / runbook discovery, security audits, dependency questions, and quick diagnostics — anything that needs a 5-30 second answer rather than a 5

Files · 1

View on GitHub

SKILL.md

1	# Chat with the AWS DevOps Agent
2
3	> AgentSpace routing (SigV4 only): If `list_agent_spaces` is available in your tool list and the multi-space orchestration skill has NOT been invoked yet this session, invoke it first to determine which `agent_space_id` to use. Then pass `agent_space_id` on all tool calls below. For bearer token auth this is unnecessary — the token is already scoped to one space.
4
5	Chat is the default. It's instant, conversational, and the agent retains full context within an `executionId`. Only escalate to `investigating-incidents-with-aws-devops-agent` when the user describes an incident or the agent itself suggests deeper analysis is warranted.
6
7	## How to send messages
8
9	Primary — use the `chat` tool:
10
11	```
12	aws_devops_agent__chat(message="What's causing the 503 errors on checkout-service?")
13	→ {"executionId": "uuid", "answer": "Based on my analysis..."}
14	```
15
16	One call, full answer. No session setup needed — the tool handles CreateChat + SendMessage + response parsing internally.
17
18	For follow-up messages in the same conversation, use `send_message` with the `execution_id` from the first response:
19
20	```
21	aws_devops_agent__send_message(
22	execution_id="<executionId from chat response>",
23	content="What about the upstream dependency?"
24	)
25	→ "The upstream service shows..."
26	```
27
28	The agent retains full context within an `executionId`. Reuse it for follow-ups — don't call `chat` again for the same conversation.
29
30	For browsing previous conversations:
31
32	```
33	aws_devops_agent__list_chats()
34	→ {"chats": [...]}
35	```
36
37	## Injecting local context
38
39	Pack local workspace knowledge into the `message` parameter. This is the killer feature — the DevOps Agent knows your AWS cloud; you know the user's local workspace.
40
41	```
42	aws_devops_agent__chat(message="""[Local Context]
43	Service: checkout-service (from package.json)
44	Last deploy: commit abc1234 — 2h ago
45	CDK Stack: lib/checkout-stack.ts — ECS Fargate behind ALB
46	Error: ConnectionError upstream connect error
47
48	[Question]
49	What's causing the 503 errors on the checkout-service?""")
50	```
51
52	Tailor by intent:
53
54	- Cost questions — include IaC files (CDK / CFN / Terraform), instance types, scaling policies
55	- Architecture review — IaC files + dependency manifest + public API surface
56	- Topology mapping — service name + key resources (cluster, ALB, RDS instance)
57	- Knowledge / runbook discovery — no local context needed, just ask
58	- Quick diagnostics — alarm/metric/error + `git log --oneline -10`
59
60	## Phrasing matters
61
62	The DevOps Agent's intent detection is keyword-based:
63
64	\| Phrasing \| Response time \|
65	\|----------\|---------------\|
66	\| "Analyze...", "Review...", "Compare...", "What if...", "Show topology..." \| 5–30s (chat) \|
67	\| "List...", "Show me...", "What is..." \| instant (discovery) \|
68	\| "Investigate...", "Root cause of...", "What's wrong with..." \| 5–8 min (deep — escalate to `investigating-incidents-with-aws-devops-agent` skill) \|
69
70	If the user phrases something as "investigate" but it's really a question, you can still chat — but if the agent suggests deeper analysis, escalate via the `investigating-incidents-with-aws-devops-agent` skill.
71
72	## Escalating to investigation
73
74	When chat surfaces a finding that needs deep multi-service correlation, hand off:
75
76	```
77	aws_devops_agent__investigate(title="Root cause of <thing chat found>")
78	```
79
80	Switch to the `investigating-incidents-with-aws-devops-agent` skill for the polling/progress workflow.
81
82	## Fallback path (aws-mcp)
83
84	If the remote MCP server (`aws-devops-agent`) is unavailable, fall back to `aws-mcp`:
85
86	```
87	aws devops-agent create-chat --agent-space-id SPACE_ID --user-id USER_ID --user-type IAM --region us-east-1
88	→ executionId
89	```
90
91	Then send a message:
92
93	```bash
94	aws devops-agent send-message \
95	--agent-space-id SPACE_ID \
96	--execution-id EXEC_ID \
97	--user-id USER_ID \
98	--content '<your question with local context>' \
99	--region us-east-1
100	```
101
102	Tell the user: "Remote server unavailable — using direct AWS API fallback."
103
104	## Timeout behavior
105
106	The `chat` tool buffers the full response server-side before returning. Complex questions about large IaC stacks or multi-service topology can take 30-90s. This is normal — don't retry prematurely.
107
108	If a response fails or times out:
109
110	1. Retry the same `chat` call once.
111	2. If it fails again, fall back to `aws-mcp`.
112
113	## Chat session lifecycle
114
115	- Single questions: Use `chat` — it creates a fresh session each time.
116	- Follow-ups: Use `send_message` with the `execution_id` from

People who liked this also viewed

6 picks

Type

chatting-with-aws-devops-agent

258installs190forks

View on GitHub

How to install chatting-with-aws-devops-agent?

aws/agent-toolkit-for-aws/chatting-with-aws-devops-agent

$npx -y skills add aws/agent-toolkit-for-aws --skill chatting-with-aws-devops-agent

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Chat with the AWS DevOps Agent
2
3	> AgentSpace routing (SigV4 only): If `list_agent_spaces` is available in your tool list and the multi-space orchestration skill has NOT been invoked yet this session, invoke it first to determine which `agent_space_id` to use. Then pass `agent_space_id` on all tool calls below. For bearer token auth this is unnecessary — the token is already scoped to one space.
4
5	Chat is the default. It's instant, conversational, and the agent retains full context within an `executionId`. Only escalate to `investigating-incidents-with-aws-devops-agent` when the user describes an incident or the agent itself suggests deeper analysis is warranted.
6
7	## How to send messages
8
9	Primary — use the `chat` tool:
10
11	```
12	aws_devops_agent__chat(message="What's causing the 503 errors on checkout-service?")
13	→ {"executionId": "uuid", "answer": "Based on my analysis..."}
14	```
15
16	One call, full answer. No session setup needed — the tool handles CreateChat + SendMessage + response parsing internally.
17
18	For follow-up messages in the same conversation, use `send_message` with the `execution_id` from the first response:
19
20	```
21	aws_devops_agent__send_message(
22	execution_id="<executionId from chat response>",
23	content="What about the upstream dependency?"
24	)
25	→ "The upstream service shows..."
26	```
27
28	The agent retains full context within an `executionId`. Reuse it for follow-ups — don't call `chat` again for the same conversation.
29
30	For browsing previous conversations:
31
32	```
33	aws_devops_agent__list_chats()
34	→ {"chats": [...]}
35	```
36
37	## Injecting local context
38
39	Pack local workspace knowledge into the `message` parameter. This is the killer feature — the DevOps Agent knows your AWS cloud; you know the user's local workspace.
40
41	```
42	aws_devops_agent__chat(message="""[Local Context]
43	Service: checkout-service (from package.json)
44	Last deploy: commit abc1234 — 2h ago
45	CDK Stack: lib/checkout-stack.ts — ECS Fargate behind ALB
46	Error: ConnectionError upstream connect error
47
48	[Question]
49	What's causing the 503 errors on the checkout-service?""")
50	```
51
52	Tailor by intent:
53
54	- Cost questions — include IaC files (CDK / CFN / Terraform), instance types, scaling policies
55	- Architecture review — IaC files + dependency manifest + public API surface
56	- Topology mapping — service name + key resources (cluster, ALB, RDS instance)
57	- Knowledge / runbook discovery — no local context needed, just ask
58	- Quick diagnostics — alarm/metric/error + `git log --oneline -10`
59
60	## Phrasing matters
61
62	The DevOps Agent's intent detection is keyword-based:
63
64	\| Phrasing \| Response time \|
65	\|----------\|---------------\|
66	\| "Analyze...", "Review...", "Compare...", "What if...", "Show topology..." \| 5–30s (chat) \|
67	\| "List...", "Show me...", "What is..." \| instant (discovery) \|
68	\| "Investigate...", "Root cause of...", "What's wrong with..." \| 5–8 min (deep — escalate to `investigating-incidents-with-aws-devops-agent` skill) \|
69
70	If the user phrases something as "investigate" but it's really a question, you can still chat — but if the agent suggests deeper analysis, escalate via the `investigating-incidents-with-aws-devops-agent` skill.
71
72	## Escalating to investigation
73
74	When chat surfaces a finding that needs deep multi-service correlation, hand off:
75
76	```
77	aws_devops_agent__investigate(title="Root cause of <thing chat found>")
78	```
79
80	Switch to the `investigating-incidents-with-aws-devops-agent` skill for the polling/progress workflow.
81
82	## Fallback path (aws-mcp)
83
84	If the remote MCP server (`aws-devops-agent`) is unavailable, fall back to `aws-mcp`:
85
86	```
87	aws devops-agent create-chat --agent-space-id SPACE_ID --user-id USER_ID --user-type IAM --region us-east-1
88	→ executionId
89	```
90
91	Then send a message:
92
93	```bash
94	aws devops-agent send-message \
95	--agent-space-id SPACE_ID \
96	--execution-id EXEC_ID \
97	--user-id USER_ID \
98	--content '<your question with local context>' \
99	--region us-east-1
100	```
101
102	Tell the user: "Remote server unavailable — using direct AWS API fallback."
103
104	## Timeout behavior
105
106	The `chat` tool buffers the full response server-side before returning. Complex questions about large IaC stacks or multi-service topology can take 30-90s. This is normal — don't retry prematurely.
107
108	If a response fails or times out:
109
110	1. Retry the same `chat` call once.
111	2. If it fails again, fall back to `aws-mcp`.
112
113	## Chat session lifecycle
114
115	- Single questions: Use `chat` — it creates a fresh session each time.
116	- Follow-ups: Use `send_message` with the `execution_id` from

People who liked this also viewed

6 picks

Type