CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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, optionally captures aggregate OpenAI, OpenRouter, or Anthropic cost and token usage through consent-gated provider APIs, 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.

Quality

83%

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

63%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 skill is operationally excellent — executable commands, explicit validation checkpoints, and real error-recovery loops at every phase — but it is buried in a 1367-line monolith where large design-rationale and schema blocks that belong in reference files are inlined. Conciseness is the dominant weakness; workflow clarity and progressive disclosure are also reduced by the sheer volume and a numbering defect in C0.

Suggestions

Move Step 1.5's ~200-line usage-profile merge rules and the usage-baseline.json schema into a reference file (e.g. references/usage-baseline.md), keeping only the glob command, the reuse decision, and a pointer in SKILL.md — this alone would cut the body dramatically and lift both conciseness and progressive disclosure.

Strip revision-history and design-justification asides (e.g. 'An earlier version of this skill invoked gcp-to-aws via a cross-skill Skill-tool call…', 'Reusing "unknown"'s policy here… keeps the SAME double-counting protection') into a CHANGELOG or design-notes file; the operative rule can stand in one sentence.

Fix the C0 ordered list so its stages number consistently (currently 1, 1, 2, 1) and present the Stage 0 / saved-context / fresh-run branches as a named checklist so the resume path is unambiguous.

DimensionReasoningScore

Conciseness

At 1367 lines the body is severely verbose, dominated by design-rationale meta-commentary and revision history rather than instruction — e.g. the ~200-line Step 1.5 provenance branching ("Reusing \"unknown\"'s policy here, rather than inventing a distinct \"uncertain\" rule, keeps the SAME double-counting protection…") and asides like "An earlier version of this skill invoked gcp-to-aws via a cross-skill Skill-tool call; that mechanism is Claude-Code-specific…". It does not explain basic concepts Claude already knows (so not the 1 anchor's failure mode), but the padding goes well beyond the 2 anchor's 'several unnecessary explanations' being a minor issue — it is borderline 1; the 3 anchor's 'mostly efficient' clearly does not fit.

2 / 5

Actionability

Guidance is fully executable throughout: exact bash commands (preflight, validator, git-root and key-format checks), a complete JSON schema for usage-baseline.json, an exact line-by-line context-block format agents parse, per-reason branch tables for every failure mode, and a stateless fixer-retry with explicit caps. Parameterized placeholders (paths, model lists) are unavoidable and specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

Sequencing is explicit (Step 0 → 1.5 → Phases A/B/C → C0–C7) with validation at every step (validator exit codes, CONTROL=blocked/partial flows, run-context mismatch invalidation table, resume walks) and genuine feedback loops — this exceeds the 4 anchor and approaches 5. It falls short of 5 because C0's ordered list numbering is broken (items renumber 1, 1, 2, 1 around lines 944–1034, making the actual stage order ambiguous on a resume) and the sheer density of Step 1.5 and the C4/C5 conditional prose obscures the mainline path.

4 / 5

Progressive Disclosure

The bundle structure itself is good and well-used — helper references exist on disk, are injected selectively per dispatch via an explicit table, and scripts/schemas are real and referenced by exact path. But the SKILL.md body inlines hundreds of lines that clearly belong in separate reference files (Step 1.5's merge rules and schema, AC1's model-access explainer, the full context-block spec, the C0 invalidation table), matching the 3 anchor's 'content that should be separate is inline' despite the references themselves being clearly signaled.

3 / 5

Total

14

/

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.

An exemplary description: explicit trigger clause, concrete action list covering both usage modes, quoted natural user phrasings, and explicit disambiguation against neighboring skills. Its only cost is length, but the length is information-dense scope definition rather than fluff, so no dimension is docked.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "assesses the codebase", "rewrites SDK calls", "evaluates output quality against Bedrock", "delivers a ready-to-merge git branch", "checks each model and walks the right access step" — covering both the full-migration and access-only modes comprehensively. It is long but dense rather than padded; every clause carries scope information, so it matches the 'multiple specific concrete actions; comprehensive coverage' anchor and not the 4 anchor's 'minor gaps in coverage'.

5 / 5

Completeness

It explicitly answers both questions: what ("assesses… rewrites SDK calls, evaluates output quality… delivers a ready-to-merge git branch", plus the access-only mode's what) and when ("Use when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock", with concrete trigger phrases). It also adds explicit negative scope ("Not for agent runtime selection or agent migration planning… nor standalone cost estimates"), which exceeds the 5 anchor's requirement; the 4 anchor's 'when could be more explicit' does not apply.

5 / 5

Trigger Term Quality

It covers natural terms users would actually say — "migrate code", "OpenAI", "Gemini/Google AI", "Anthropic", "OpenRouter", "Amazon Bedrock" — and even quotes verbatim user phrasings ("request access to Claude on Bedrock", "which models do I turn on") that pass the 'would a user naturally say this' test. Synonyms are included (Gemini/Google AI), matching the comprehensive-coverage anchor rather than the 4 anchor's 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche — LLM SDK migration to Bedrock — and actively de-conflicts by naming where sibling concerns go ("use agent-advisor") and excluding standalone cost estimates and infra-only migration. The explicit sibling-skill requirement ("REQUIRES gcp-to-aws OR azure-to-aws installed alongside") further reduces wrong-trigger risk; this matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

20

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1372 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 1 missing, 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 5 missing, 3 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

aws/agent-toolkit-for-aws

Path

plugins/aws-startup-advisor/skills/llm-to-bedrock/SKILL.md

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.