llm-to-bedrock
Use when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. End-to-end: assesses the codebase, rewrites SDK calls, evaluates output quality against Bedrock, and delivers a ready-to-merge git branch. Also has an access-only mode for checking or enabling Bedrock model access for specific models (e.g. 'request access to Claude on Bedrock', 'which models do I turn on') with no code migration — it checks each model and walks the right access step, then stops. Not for agent runtime selection or agent migration planning (use agent-advisor), nor standalone cost estimates or infra-only migration. The full migration REQUIRES gcp-to-aws OR azure-to-aws installed alongside this skill (gcp-to-aws preferred when both are present); access-only mode needs neither.
Agent Skill from aws/agent-toolkit-for-aws
Copilot Studio
Passes documented load rulesNo documented load rule failed.
Microsoft 365 Copilot Preview, Frontier tenants only
Needs changes- Fails: Instructions are under 20,000 characters (M365-INSTRUCTIONS)
instructions are 92,497 characters
rule · Microsoft 365 Copilot: What is a skill - Fails: Directory depth is at most 3 (M365-DEPTH)
deepest file is 4 folders down
rule · Microsoft 365 Copilot: Support matrix - Fails: Every file has a supported file type (M365-FILE-TYPES)
3 unsupported: references/helpers/bedrock-known-fixes/references/bedrock-vision.py.template, scripts/pyproject.toml, scripts/uv.lock
rule · Microsoft 365 Copilot: Supported file and script types
Warnings (don't change the verdict):
- Warning: No sign of network access, package installs or authenticated calls (M365-SANDBOX)
SKILL.md mentions npm/npx install, system package install
rule · Microsoft 365 Copilot: Script execution sandbox - Warning: No sign of network access, package installs or authenticated calls (M365-SANDBOX)
declares dependencies (scripts/pyproject.toml); the sandbox can't install packages
rule · Microsoft 365 Copilot: Script execution sandbox - Warning: No sign of network access, package installs or authenticated calls (M365-SANDBOX)
scripts: references/vendored/telemetry/metric_emission/client.py (Python HTTP client); scripts/iam_policy.py (credentials / authenticated call); scripts/preflight_bedrock.py (credentials / authenticated call); scripts/resolve_source_model.py (Python HTTP client, credentials / authenticated call); scripts/source_baseline.py (Python HTTP client, credentials / authenticated call); …
rule · Microsoft 365 Copilot: Script execution sandbox
An agent can have at most 8 skills. Custom skills aren't available in tenants that use Microsoft Purview Information Barriers.
Standards signals
Meets the agentskills.io required fields.
| Frontmatter | Present and parsed Spec: frontmatter |
| name | Meets the spec (1-64 chars, a-z 0-9 hyphens) Spec: name |
| description | Present, 1-1,024 characters Spec: description |
| compatibility | Absent or under 500 characters Spec: compatibility |
| Name matches folder | Yes (llm-to-bedrock)Spec: name |
Observed from the public SKILL.md at the commit above on 2026-10-23. Not a certification: AAIF and the Agent Skills project don't certify skills. Validate your own skill with skills-ref validate.
| Source repo | aws/agent-toolkit-for-aws |
| Path | plugins/aws-startup-advisor/skills/llm-to-bedrock/SKILL.md |
| Commit checked | 9ab50636d125 |
| Repo license | Apache-2.0 |
| Files | 52 |
| Scripts | 29 (29 scanned for the sandbox heuristic) |
| Instructions | 92,497 characters |
| Deepest folder | 4 below the skill folder |
| Rules version | 2026-10-22 |
Re-check the latest version How skill checks work
Rule-based checks of public files against Microsoft's documented load rules, not tested in Copilot Studio or Microsoft 365 Copilot. Independent project, not affiliated with Microsoft.