Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Provides AWS SAM bootstrap patterns: generates `template.yaml` and `samconfig.toml` for new projects via `sam init`, creates SAM templates for existing Lambda/CloudFormation code migration, validates build/package/deploy workflows, and configures local testing with `sam local invoke`. Use when the user asks about SAM projects, `sam init`, `sam deploy`, serverless deployments, or needs to bootstrap/migrate Lambda functions with SAM templates.
.claude/skills/giuseppe-trisciuoglio-aws-sam-bootstrap/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 143% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -12% | 0% |
Generates SAM project artifacts for greenfield and migration scenarios. Creates the minimum required files (template.yaml, samconfig.toml, events/), validates with sam build, and configures sam deploy workflows following AWS SAM conventions.
sam init, sam deploy)sam init, sam build, sam local invoke, sam deploy)template.yaml or samconfig.toml for serverless deploymentssam local invoke for Lambda functionssam init to scaffold.template.yaml manually.Use current non-deprecated runtimes. Package type: Zip (default) or Image (container/native deps).
bashsam init sam build sam local invoke <LogicalFunctionId> -e events/event.json sam deploy --guided
template.yaml with Transform: AWS::Serverless-2016-10-31AWS::Serverless::Function and related SAM resourcessamconfig.toml with deploy defaults and environment overridesevents/event.json payload samples for local invocationsam validate and sam build before deploy.
├── template.yaml
├── samconfig.toml
└── events/
└── event.jsonSee reference templates: examples.md, migration-checklist.md
sam validate succeedssam build succeedstemplate.yaml has correct logical IDs and handlerssamconfig.toml contains deploy parameters for target environmentsbashsam init # Interactive scaffold sam build sam local invoke HelloFunction -e events/event.json sam deploy --guided
template.yaml with SAM transformsamconfig.toml with stack_name, capabilities, resolve_s3events/event.json → validate with sam buildFull templates in references/examples.md.
samconfig.toml committed for deterministic deployments[default], [prod]) instead of CLI flagsCAPABILITY_IAM is required when IAM resources are createdsam deploy --guided writes local configuration; review before committing| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,888 | 11,186 | -19% | 1 | 1 | 0% | 2,616 | 3,019 | +15% | 0 | 0 | — |
case-02 | fail→pass | 14,650 | 10,095 | -31% | 1 | 1 | 0% | 2,616 | 2,786 | +6% | 0 | 0 | — |
case-03 | pass→pass | 21,597 | 7,630 | -65% | 1 | 1 | 0% | 2,529 | 2,236 | -12% | 0 | 0 | — |
case-04 | pass→pass | 12,044 | 6,532 | -46% | 1 | 1 | 0% | 1,846 | 1,960 | +6% | 0 | 0 | — |
case-05 | fail→pass | 9,209 | 5,110 | -45% | 1 | 1 | 0% | 1,477 | 1,676 | +13% | 0 | 0 | — |
case-06 | pass→pass | 12,097 | 9,595 | -21% | 1 | 1 | 0% | 2,053 | 2,347 | +14% | 0 | 0 | — |
case-07 | fail→pass | 11,919 | 10,081 | -15% | 1 | 1 | 0% | 2,239 | 2,641 | +18% | 0 | 0 | — |
case-08 | pass→pass | 2,991 | 2,462 | -18% | 1 | 1 | 0% | 476 | 1,132 | +138% | 0 | 0 | — |
case-09 | fail→fail | 4,535 | 4,861 | +7% | 1 | 1 | 0% | 634 | 1,688 | +166% | 0 | 0 | — |
case-10 | pass→pass | 2,782 | 2,277 | -18% | 1 | 1 | 0% | 396 | 1,130 | +185% | 0 | 0 | — |
case-11 | pass→pass | 15,396 | 9,250 | -40% | 1 | 1 | 0% | 2,312 | 2,182 | -6% | 0 | 0 | — |
case-12 | pass→fail | 5,706 | 4,048 | -29% | 1 | 1 | 0% | 598 | 1,455 | +143% | 0 | 0 | — |
case-13 | pass→pass | 13,376 | 10,379 | -22% | 1 | 1 | 0% | 2,151 | 2,561 | +19% | 0 | 0 | — |
case-14 | fail→fail | 2,672 | 2,931 | +10% | 1 | 1 | 0% | 404 | 1,258 | +211% | 0 | 0 | — |
case-15 | pass→pass | 11,585 | 9,648 | -17% | 1 | 1 | 0% | 2,041 | 2,506 | +23% | 0 | 0 | — |
case-16 | pass→pass | 9,635 | 4,844 | -50% | 1 | 1 | 0% | 1,586 | 1,645 | +4% | 0 | 0 | — |
case-17 | pass→pass | 2,519 | 3,392 | +35% | 1 | 1 | 0% | 423 | 1,348 | +219% | 0 | 0 | — |
case-18 | pass→pass | 7,935 | 4,968 | -37% | 1 | 1 | 0% | 1,312 | 1,659 | +26% | 0 | 0 | — |
case-19 | pass→pass | 3,594 | 2,709 | -25% | 1 | 1 | 0% | 559 | 1,270 | +127% | 0 | 0 | — |
case-20 | pass→pass | 9,446 | 6,541 | -31% | 1 | 1 | 0% | 1,810 | 2,032 | +12% | 0 | 0 | — |
case-21 | pass→pass | 5,868 | 4,989 | -15% | 1 | 1 | 0% | 1,018 | 1,656 | +63% | 0 | 0 | — |
case-22 | pass→pass | 3,387 | 3,306 | -2% | 1 | 1 | 0% | 507 | 1,331 | +163% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.