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.

75

Quality

95%

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

90%Weight 40%Scale 1-5

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

The body is a highly actionable, well-sequenced getting-started workflow with concrete commands, flag tables, and validation checkpoints throughout. Its main weakness is progressive disclosure: with only one reference file, a lot of detailed material (framework comparison, BYO Container path, model-provider guidance) remains inlined in the main skill rather than split out.

Suggestions

Move the 'Framework not listed?' / BYO Container path and the 'Framework vs. model provider' sections into a dedicated reference file (e.g. references/framework-selection.md) and link to it from Step 2, keeping the main body to the core 8-step flow.

Trim inferable prose in Step 2 (e.g. the 'Framework vs. model provider — a common confusion' framing) to tighten conciseness toward the score-5 bar.

Consider extracting the project-name validation rules and flag reference table into references/create-command.md so the main 'Process' section reads as a lean overview.

DimensionReasoningScore

Conciseness

Largely efficient and free of basic-concept padding, with every section anchored by concrete commands or tables; however sections like 'Framework vs. model provider — a common confusion' and the BYO Container / language-specific notes add explanation a competent Claude could infer, keeping it just below the score-5 'every token earns its place' bar. Confirmed not 3 because there is no significant over-explanation or padding, and not 5 because some prose could be trimmed.

4 / 5

Actionability

Fully executable guidance throughout — concrete `agentcore create` commands with full flag reference, `agentcore dev`/`deploy`/`invoke`/`status`, validated project-name rules with worked character-count examples, and port tables — copy-paste ready and covering the common cases, matching the score-5 anchor.

5 / 5

Workflow Clarity

Clear Step 0–7 sequence with explicit validation checkpoints and feedback loops (CLI version check → offer update → re-check; project-name validation before constructing the command; present-for-confirmation before running create), matching the score-5 anchor for explicit validation steps and error-recovery loops.

5 / 5

Progressive Disclosure

Good structure with a clearly signaled one-level-deep reference (references/example-support-agent.md, verified to exist) linked from a task-mapping table, plus inline cross-skill references one level deep; however most content (framework tables, BYO Container path, model-provider guidance) lives in the body rather than being split into reference files, so the 'appropriately split / easy navigation' bar of score 5 is only partially met. Confirmed not 3 because references are clearly signaled and not buried, and not 5 because the body carries bulk content that could be externalized.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 exemplary: third-person voice, concrete actions, a comprehensive set of natural trigger phrases, and explicit negative boundary routing that distinguishes it from sibling skills. It clearly answers both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'framework selection, project scaffolding, first deploy, and first invocation' — giving comprehensive coverage of what the skill does, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (handles framework selection, scaffolding, deploy, invocation) and 'when' via the 'Triggers on:' clause, plus explicit negative boundary guidance — matching the score-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases a developer would actually say — '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', 'dev server', 'what port' — matching the score-5 anchor for coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

Clear niche with explicit routing boundaries ('Not for adding capabilities to existing projects — use agents-build or agents-connect'; 'Strands vs LangGraph in a migration context routes to agents-build'; 'Connecting to an existing MCP server routes to agents-connect'), minimizing conflict risk — matching the score-5 anchor.

5 / 5

Total

20

/

20

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.