agents-get-started

Name: agents-get-started
Author: aws

582installs190forks

How to install agents-get-started?

aws/agent-toolkit-for-aws/agents-get-started

$npx -y skills add aws/agent-toolkit-for-aws --skill agents-get-started

Installs into the current project.

Summary

Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: "build an agent", "create an agent", "get started", "new project", "agentcore create", "which

Files · 1

View on GitHub

SKILL.md

1	# get-started
2
3	Walk a developer from zero to a running agent on AWS.
4
5	## When to use
6
7	- Developer wants to build an agent on AWS and doesn't know where to start
8	- Developer wants to create a new AgentCore project
9	- Developer is choosing between frameworks (Strands, LangGraph, GoogleADK, OpenAI Agents)
10	- Developer just ran `agentcore create` and wants to know what to do next
11
12	Do NOT use for:
13
14	- Environment/prerequisite issues (CLI not found, credentials broken) → use `agents-debug`
15	- Adding capabilities to an existing project (memory, tools, policies) → use `agents-build` or `agents-connect`
16	- Migrating an existing Bedrock Agent → use `agents-build` (loads [`references/migrate.md`](../agents-build/references/migrate.md))
17
18	## Input
19
20	`$ARGUMENTS` can be:
21
22	- A framework preference: "using LangGraph", "with Strands"
23	- A protocol: "MCP server", "A2A"
24	- A description of what the agent should do: "a customer support agent"
25	- Empty — the skill will guide framework selection
26
27	## Process
28
29	### Step 0: Verify CLI version
30
31	```bash
32	agentcore --version
33	```
34
35	This skill requires v0.9.0 or later.
36
37	If the version is older:
38	> Your AgentCore CLI is out of date (found vX.Y.Z, need v0.9.0+).
39
40	Offer to run the update: `agentcore update`. After the update completes, re-check the version to confirm it's ≥0.9.0 before continuing. Preserve any context the developer already provided (framework preference, project name, what they want to build) so they don't have to repeat themselves.
41
42	If `agentcore` is not found:
43	> The AgentCore CLI isn't installed. Run `npm install -g @aws/agentcore` (requires Node.js 20+).
44	> If you're having trouble with installation, I can run the `agents-debug` skill (which loads [`references/doctor.md`](../agents-debug/references/doctor.md)) to diagnose your environment.
45
46	### Step 1: Determine intent — exploring or ready to create?
47
48	Before jumping into framework selection, figure out where the developer is:
49
50	Ask the developer: "Are you exploring options (comparing frameworks, understanding what AgentCore does) or ready to create a project?"
51
52	- Exploring → Go to Step 2 (framework comparison). Present the options, answer questions, and wait. Do not construct a `create` command until they signal they're ready.
53	- Ready to create → Skip to Step 3 (create the project). If they already specified a framework, skip Step 2 entirely.
54	- Already has a project → Look for `agentcore/agentcore.json` in the current directory. If found, read it and skip to Step 5 (what to do next). Don't re-scaffold.
55
56	If the developer's intent is clear from `$ARGUMENTS` (e.g., "create a Strands agent called MyBot"), skip straight to Step 3.
57
58	### Step 2: Framework selection
59
60	Check conversation context first. If the developer already discussed frameworks earlier in this conversation (e.g., from a previous skill invocation), don't re-present the full table. Summarize what was discussed and ask if they've decided, or if anything changed.
61
62	If this is the first time discussing frameworks, present the options:
63
64	Supported frameworks (CLI-scaffolded, Python):
65
66	\| Framework \| CLI value \| Best for \|
67	\|---\|---\|---\|
68	\| Strands \| `Strands` \| AWS-native, simplest path, best AgentCore integration \|
69	\| LangGraph \| `LangChain_LangGraph` \| Complex graph-based workflows, existing LangChain investment \|
70	\| Google ADK \| `GoogleADK` \| Teams already using Google's agent toolkit \|
71	\| OpenAI Agents \| `OpenAIAgents` \| Teams already using OpenAI's agent SDK \|
72
73	Ask the developer to choose. Present the options and wait for their selection. Don't assume a default unless they explicitly say they have no preference.
74
75	> Note on naming: The CLI flag value is the exact string to pass to `--framework`. In prose use the shorter names.
76
77	Default recommendation (only when the developer says "no preference" or "you pick"): Strands — AWS-native framework with the tightest AgentCore integration and the most samples/docs.
78
79	Key decision points to surface:
80
81	- "Do you have existing agent code in LangGraph or OpenAI Agents?" → use that framework
82	- "Do you need complex graph-based workfl

People who liked this also viewed

6 picks

Type

agents-get-started

582installs190forks

View on GitHub

How to install agents-get-started?

aws/agent-toolkit-for-aws/agents-get-started

$npx -y skills add aws/agent-toolkit-for-aws --skill agents-get-started

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# get-started
2
3	Walk a developer from zero to a running agent on AWS.
4
5	## When to use
6
7	- Developer wants to build an agent on AWS and doesn't know where to start
8	- Developer wants to create a new AgentCore project
9	- Developer is choosing between frameworks (Strands, LangGraph, GoogleADK, OpenAI Agents)
10	- Developer just ran `agentcore create` and wants to know what to do next
11
12	Do NOT use for:
13
14	- Environment/prerequisite issues (CLI not found, credentials broken) → use `agents-debug`
15	- Adding capabilities to an existing project (memory, tools, policies) → use `agents-build` or `agents-connect`
16	- Migrating an existing Bedrock Agent → use `agents-build` (loads [`references/migrate.md`](../agents-build/references/migrate.md))
17
18	## Input
19
20	`$ARGUMENTS` can be:
21
22	- A framework preference: "using LangGraph", "with Strands"
23	- A protocol: "MCP server", "A2A"
24	- A description of what the agent should do: "a customer support agent"
25	- Empty — the skill will guide framework selection
26
27	## Process
28
29	### Step 0: Verify CLI version
30
31	```bash
32	agentcore --version
33	```
34
35	This skill requires v0.9.0 or later.
36
37	If the version is older:
38	> Your AgentCore CLI is out of date (found vX.Y.Z, need v0.9.0+).
39
40	Offer to run the update: `agentcore update`. After the update completes, re-check the version to confirm it's ≥0.9.0 before continuing. Preserve any context the developer already provided (framework preference, project name, what they want to build) so they don't have to repeat themselves.
41
42	If `agentcore` is not found:
43	> The AgentCore CLI isn't installed. Run `npm install -g @aws/agentcore` (requires Node.js 20+).
44	> If you're having trouble with installation, I can run the `agents-debug` skill (which loads [`references/doctor.md`](../agents-debug/references/doctor.md)) to diagnose your environment.
45
46	### Step 1: Determine intent — exploring or ready to create?
47
48	Before jumping into framework selection, figure out where the developer is:
49
50	Ask the developer: "Are you exploring options (comparing frameworks, understanding what AgentCore does) or ready to create a project?"
51
52	- Exploring → Go to Step 2 (framework comparison). Present the options, answer questions, and wait. Do not construct a `create` command until they signal they're ready.
53	- Ready to create → Skip to Step 3 (create the project). If they already specified a framework, skip Step 2 entirely.
54	- Already has a project → Look for `agentcore/agentcore.json` in the current directory. If found, read it and skip to Step 5 (what to do next). Don't re-scaffold.
55
56	If the developer's intent is clear from `$ARGUMENTS` (e.g., "create a Strands agent called MyBot"), skip straight to Step 3.
57
58	### Step 2: Framework selection
59
60	Check conversation context first. If the developer already discussed frameworks earlier in this conversation (e.g., from a previous skill invocation), don't re-present the full table. Summarize what was discussed and ask if they've decided, or if anything changed.
61
62	If this is the first time discussing frameworks, present the options:
63
64	Supported frameworks (CLI-scaffolded, Python):
65
66	\| Framework \| CLI value \| Best for \|
67	\|---\|---\|---\|
68	\| Strands \| `Strands` \| AWS-native, simplest path, best AgentCore integration \|
69	\| LangGraph \| `LangChain_LangGraph` \| Complex graph-based workflows, existing LangChain investment \|
70	\| Google ADK \| `GoogleADK` \| Teams already using Google's agent toolkit \|
71	\| OpenAI Agents \| `OpenAIAgents` \| Teams already using OpenAI's agent SDK \|
72
73	Ask the developer to choose. Present the options and wait for their selection. Don't assume a default unless they explicitly say they have no preference.
74
75	> Note on naming: The CLI flag value is the exact string to pass to `--framework`. In prose use the shorter names.
76
77	Default recommendation (only when the developer says "no preference" or "you pick"): Strands — AWS-native framework with the tightest AgentCore integration and the most samples/docs.
78
79	Key decision points to surface:
80
81	- "Do you have existing agent code in LangGraph or OpenAI Agents?" → use that framework
82	- "Do you need complex graph-based workfl

People who liked this also viewed

6 picks

Type