CtrlK
BlogDocsLog inGet started
Tessl Logo

agents-get-started

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 framework", "Strands vs LangGraph", "hello world agent", "first agent", "create MCP server", "host MCP server", "agentcore dev", "dev server", "what port", "local development". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands, flag tables, and a well-sequenced workflow with validation checkpoints. It loses points on conciseness and progressive disclosure, where discursive explanations and inline detail could be tightened or offloaded to reference files.

Suggestions

Tighten the project-name rationale and framework-vs-model-provider prose to remove explanation Claude can infer, improving conciseness.

Move the BYO container path, language-specific notes, and framework-not-listed handling into a dedicated reference file (e.g. references/byo-container.md) and link to it from Step 2, improving progressive disclosure.

Keep the high-value tables (flags, ports) inline since they are directly actionable, but trim the surrounding discursive paragraphs.

DimensionReasoningScore

Conciseness

Largely efficient and avoids basic-concept padding, but the project-name rationale and the framework-vs-model-provider/BYO-container prose include unnecessary explanation that could be tightened.

2 / 3

Actionability

Provides executable commands (e.g. "agentcore create --name ... --framework Strands --model-provider Bedrock --build CodeZip --memory none"), a full flag-reference table, and exact port/CLI-value tables that are copy-paste ready.

3 / 3

Workflow Clarity

Steps 0-7 are clearly sequenced with explicit checkpoints (re-check version >=0.9.0 after update, validate project name before building the command, present command for confirmation before running).

3 / 3

Progressive Disclosure

The one in-bundle reference (references/example-support-agent.md, verified present) is one level deep and well-signaled, but substantial detail (BYO container path, framework-vs-model-provider, language notes) is inline that could be split into reference files.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise yet specific, naming concrete actions, an explicit trigger list, and clear disambiguation against sibling skills. It cleanly satisfies the what/when/completeness bar.

DimensionReasoningScore

Specificity

"Handles framework selection, project scaffolding, first deploy, and first invocation" lists multiple specific concrete actions, matching the score-3 anchor.

3 / 3

Completeness

It explicitly answers what (framework selection, scaffolding, deploy, invocation) and when ("Use when..." plus an explicit "Triggers on" list), matching the score-3 anchor.

3 / 3

Trigger Term Quality

"Triggers on: build an agent, create an agent, get started, new project, agentcore create, which framework, Strands vs LangGraph..." gives strong coverage of natural terms users would say.

3 / 3

Distinctiveness Conflict Risk

"Not for adding capabilities to existing projects — use agents-build or agents-connect" and migration/MCP routing notes give it a clear niche unlikely to trigger the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

14

/

16

Passed

Repository
aws/agent-toolkit-for-aws
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.