agent-advisor
Entry point for AI-agent work on AWS: pick a runtime, plan a migration for existing workloads, and build an executable POC — one phased flow.
Skill by awsOfficial
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/aws-agent-advisor
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: frontend, devops, cloud, data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-advisor
What's inside
- Skill name
agent-advisor- Description
- Entry point for AI-agent work on AWS: pick a runtime, plan a migration for existing workloads, and build an executable POC — one phased flow. Triggers on: which runtime for my agent, AgentCore vs ECS vs EKS vs Lambda, AgentCore vs Lambda MicroVMs, deploy an AI agent on AWS, agent architecture on AWS, I have an agent idea what do I build, move/migrate my agents to AWS, agent migration plan, add AgentCore services (memory, gateway, identity, policy, observability) to an agent already on AWS, Temporal on AWS (migrate/run Temporal workers on AWS, a service orchestrated by Temporal, Temporal Cloud vs self-hosted). Temporal Workflow code is never rewritten into Step Functions. Requires at least one agentic component — a purely non-agent system (plain services, batch jobs, HTTP endpoints, non-agent Temporal Activities) is out of scope, redirected to gcp-to-aws / heroku-to-aws / llm-to-bedrock. Not for: compute/data migration with no AI agent; pure LLM SDK rewrite (use llm-to-bedrock); per-model pricing.
- License
- Apache-2.0
- Instructions
- 203 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (87)
- SKILL.md
- agentcore.md · references/decision-refs/
- batch.md · references/decision-refs/
- cost-levers.md · references/decision-refs/
- ecs.md · references/decision-refs/
- eks.md · references/decision-refs/
- freshness.md · references/decision-refs/
- lambda-microvms.md · references/decision-refs/
- lambda.md · references/decision-refs/
- managed-alternatives.md · references/decision-refs/
- maturity-readiness.md · references/decision-refs/
- model-selection.md · references/decision-refs/
- poc-shapes.md · references/decision-refs/
- temporal.md · references/decision-refs/
- workload-classes.md · references/decision-refs/
- build-diagram.md · references/diagram/
- handoff-migration.md · references/handoff/
- anthropic-bedrock-2026-07-21.json · references/models/
- anthropic-bedrock-2026-09-24.json · references/models/
- openai-bedrock-2026-08-21.json · references/models/
- openai-bedrock-2026-09-24.json · references/models/
- recommendation-doc.md · references/output-templates/
- add-capabilities-assemble.md · references/phases/add-capabilities/
- add-capabilities.md · references/phases/add-capabilities/
- clarify-assemble.md · references/phases/clarify/
- clarify-business.md · references/phases/clarify/
- clarify-technical.md · references/phases/clarify/
- clarify.md · references/phases/clarify/
- confirm-assemble.md · references/phases/confirm/
- confirm.md · references/phases/confirm/
- design-assemble.md · references/phases/design/
- design.md · references/phases/design/
- discover-assemble.md · references/phases/discover/
- discover.md · references/phases/discover/
- estimate-assemble.md · references/phases/estimate/
- estimate.md · references/phases/estimate/
- generate-assemble.md · references/phases/generate/
- generate-report.md · references/phases/generate/
- generate.md · references/phases/generate/
- intake-assemble.md · references/phases/intake/
- intake.md · references/phases/intake/
- migration-plan-assemble.md · references/phases/migration-plan/
- migration-plan-gcp-constraints.md · references/phases/migration-plan/
- migration-plan.md · references/phases/migration-plan/
- model-recommend-assemble.md · references/phases/model-recommend/
- model-recommend.md · references/phases/model-recommend/
- poc-assemble.md · references/phases/poc/
- poc-report.md · references/phases/poc/
- poc.md · references/phases/poc/
- report-help-banner.md · references/
- report-shell.md · references/
- agentcore.json · references/runtimes/
- ecs.json · references/runtimes/
- eks.json · references/runtimes/
- lambda.json · references/runtimes/
- lambda_microvms.json · references/runtimes/
- README.md · references/vendored/
- bedrock-pricing-cache.md · references/vendored/ai/
- INTERPRETER.md · references/vendored/dsl/
- anthropic_model_recommendation.py · scripts/
- …and 27 more
SKILL.md (first lines)
# AWS Agent Advisor
Helps startups decide how and where to run AI agents on AWS. Deterministic scoring
recommends a runtime; the conversation adapts to the user's technical background.
## Definitions
- **"Load"** = Read the file with the Read tool and follow it. Do not summarize or skip.
- **`$RUN_DIR`** = the run directory under `.agent-advisor/` (e.g. `.agent-advisor/0630-1430/`),
created in Intake.
- **`$PLUGIN`** = `${CLAUDE_PLUGIN_ROOT}` (the installed plugin root). On Claude Code this token
substitutes inline. **If `${CLAUDE_PLUGIN_ROOT}` does not resolve** (some Cursor/Codex builds,
or a literal `${CLAUDE_PLUGIN_ROOT}` string showing up in a path error), fall back to the
skill's own directory: this SKILL.md lives at `<plugin>/skills/agent-advisor/SKILL.md`, so the
engine and its data are all inside this skill — scripts at `./scripts/...`, runtime profiles at
`./references/runtimes/...`, and decision refs at `./references/decision-refs/...` relative to
it. Prefer `${CLAUDE_PLUGIN_ROOT}/skills/agent-advisor/...`; use the relative fallback only when
it fails to resolve.
## Prerequisites
- `uv` available (for scoring). Check: `uv --version`. If missing, tell the user to install
it from the official install guide (https://docs.astral.sh/uv/getting-started/installation/ — e.g. `brew install uv` or `pipx install uv`) and stop.
## Phase Structure (frontmatter)
Phase, fragment, and assembler files carry a YAML frontmatter block that declares how each
phase is composed — its inputs, triggers, fragments, assembler, artifacts, gates, and
ordering. The execution contract is the vendored `references/vendored/dsl/INTERPRETER.md`:
it defines every frontmatter key, the fragment/assembler model, the gate protocol
(`HANDOFF_OK` / `GATE_FAIL`), and the interpreter loop. **Load it first** (once, at the
start of a run), then execute each phase file's prose body. Elsewhere in this skill,
`INTERPRETER.md` (without a path) refers to this loaded contract.
## Execution
This skill is driven by the interpreter loop in `INTERPRETER.md` (§ The interpreter loop):
it reads `.phase-status.json`, determines the current phase, runs each phase's
`_preconditions` / fragments / `_assemble` / `_postconditions`, advances on `HANDOFF_OK`
via `_advances_to`, and validates state. The backbone (intake → discover → clarify →
confirm → design → estimate → generate → migration-plan → poc → complete) and the
one sidebar branch (add-capabilities) are derived
from the phase files' frontmatter — they are not restated here.
**Cold start (entry phase).** With no run under `.agent-advisor/` carrying a
`.phase-status.json`, begin at `references/phases/intake/intake.md` — this skill's entry
phase (the one carrying `_init: true`). On a warm start, `current_phase` in
`.phase-status.json` is authoritative (`INTERPRETER.md` § The interpreter loop).
**Skill bindings (`INTERPRETER.md` § Skill bindings).** This skill declares:
- **Run root**: `.agent-advisor/` — `$RUN_DIR` is this skill's name for the run directory
(`.agent-advisor/[MMDD-HHMM]/`). Intake's own prose performs the `_init` bootstrap.
- **State shape**: § State file below (advisor-specific keys such as `entry_point`,
`audience`, `recommendation_reviewed`, `migration_plan_ctx`, `migration_plan_unavailable`);
the shared state schema is not vendored.
- **Run seed (optional)**: `$RUN_DIR/seed.json`, else `.agent-advisor/seed.json` at the run root
(schema `scripts/schemas/seed.json`) supplies
machine-readable answers for a non-interactive run — the Clarify dimensions, the two gate
answers, the POC mode, the live-probe answer, and a `co_recommend` tie-break. It is the
HIGHEST-precedence source for every value it carries (clarify.md Step 2.5), which is what makes
a repeated run's score comparable: the deterministic engine gets byte-identical input. A gate
the seed omits is declined; a dimension the seed omits falls through to detection, then prose,
then an `assumed` value that MUST be recorded in `$RUN_DIR/UNANSWERED.md`. With no seed, the
interactive flow is unchanged.
- **Resolved statuses**: `skipped` (routing resolved the phase without running it), plus
`not_applicable` for `migration_plan` only.
- **Conditional backbone routing**: the entry-point routing below. When a routing rule
marks a phase not-applicable, set it `skipped` and advance through its `_advances_to` in
the same state write.
## Routing & gates (orchestration)
Sidebar placement and conditional backbone routing are orchestration prose owned by
this file (`INTERPRETER.md` § Skill bindings, § Backbone vs sidebar).
**Entry-point routing:**
- `build_scratch` → skip Discover; Clarify → Confirm → Design → Estimate → Generate → **Gate 2 → POC (any winning runtime)**. No migration plan (nothing existing to migrate).
- `build_deploy` → Discover (if code) → Clarify → Confirm → Design → Estimate → Generate → **Gate 1 → Migration Plan (if existing non-AWS AI workload detected and user confirms)** → **Gate 2 → POC (any winning runtime)**.
- `migrate` → Discover (if code) → Clarify → Confirm → Design → Estimate (target-state run cost; migration TCO comparison stays with the Migration Plan engine) → Generate → **Gate 1 → Migration Plan (in-skill, reusing the sibling `gcp-to-aws` skill)** → **Gate 2 → POC (any winning runtime, when the plan was produced)**. Declining Gate 1 keeps the classic handoff: pointer to `/aws-startup-advisor:llm-to-bedrock` with `handoff-summary.md`.
- `add_capabilities` → load `references/phases/add-capabilities/add-capabilities.md` and follow it (no runtime
scoring; writes `capabilities-recommendation.md`). This is a self-contained branch — it does
NOT pass through Clarify / Confirm / Design / Estimate / Generate, so the phase gate
below never applies to it.
- Temporal detection routes into `migrate` with temporal units pre-seeded (see discover).
**Gate semantics (backbone tail):**
- **Gate 1 → `migration_plan`** runs only when `generate` is done AND
`recommendation_reviewed == true` (generate.md Step 5.5) AND entry point ∈ {migrate,
build_deploy} AND the run is migration-eligible (generate.md Step 6) AND the user
confirmed Gate 1. Otherwise resolve it: `not_applicable` (build_scratch / no migratable
workload) or `skipped` (declined) — and advance.
- **Gate 2 → `poc`** runs only when `phases.poc == "in_progress"` (set when the user
answers Gate 2 "yes" — asked in generate.md Step 7 or migration-plan.md Step 6) AND
`recommendation_reviewed == true`. Any winning runtime (agentcore / ecs / eks / lambda /
lambda_microvms) — the POC shape follows the verdict (poc.md Step 3 dispatch on
`references/decision-refs/poc-shapes.md`). Gate 2 is only offered when `migration_plan`
∈ {completed, skipped, not_applicable} — or `in_progress` on build_deploy only (Stage 2
failed/aborted; fallback POC from design.json per migration-plan.md failure handling);
for entry point `migrate`, only when `migration_plan == "completed"` (the POC implements the
plan) OR when the stage resolved `not_applicable` with `migration_plan_unavailable ==
"engine_absent"` — a standalone deployment that does not bundle the migration engine, where
Gate 2 is offered by migration-plan.md Step -1 and the POC is design-backed. A migrate-POC
with no plan for any OTHER reason (the user declined) has nothing to implement.
- Persisting Gate 2 as `phases.poc = "in_progress"` BEFORE poc.md loads makes the
confirmation resumable: if the session breaks between the "yes" and the load, the
interpreter re-enters `poc` without re-asking. (A declared deviation from
`INTERPRETER.md` § The interpreter loop step 5's gate-then-`in_progress` ordering — the
user's confirmation is the entry event worth persisting.)
**Phase gate:** Do NOT load design.md / estimate.md / generate.md unless
`$RUN_DIR/.phase-status.json` exists and BOTH `phases.clarify == "completed"` AND
`phases.confirm == "completed"`. Confirm confirms the deployment model, the service
set, and (for a co_recommend tie) the user's `chosen_runtime` — Design and the diagram depend on
its `confirm.json` output, so it must not be skipped. If the user asks to skip Clarify or Pass 2,
refuse briefly and run it.From aws/agent-toolkit-for-aws, Apache-2.0.
More from aws/agent-toolkit-for-aws
- 0.843score
agents-build
aws-agentcoreOfficial
Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource…
SkillAFreshness: A★ 3KClaude Code +9 - 0.782score
agents-pay
aws-agentcoreOfficial
Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying…
SkillBFreshness: B★ 3KClaude Code +9 - 0.739score
agents-deploy
aws-agentcoreOfficial
Use when deploying your agent to AWS, or when a deploy has failed.
SkillCFreshness: C★ 3KClaude Code +9 - 0.739score
agents-optimize
aws-agentcoreOfficial
Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization.
SkillCFreshness: C★ 3KClaude Code +9 - 0.734score
agents-get-started
aws-agentcoreOfficial
Use when a developer wants to create a new agent project or get started with AgentCore.
SkillCFreshness: C★ 3KClaude Code +9 - 0.724score
agents-harden
aws-agentcoreOfficial
Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate…
SkillCFreshness: C★ 3KClaude Code +9 - 0.724score
aws-transform
AWSOfficial
Performs code upgrades, migrations, and transformations using the AWS Transform (ATX) CLI.
SkillCFreshness: C★ 3KClaude Code +9 - 0.724score
agents-debug
aws-agentcoreOfficial
Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues.
SkillCFreshness: C★ 3KClaude Code +9 - 0.700score
agents-connect
aws-agentcoreOfficial
Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies.
SkillCFreshness: C★ 3KClaude Code +9 - 0.682score
knowledge-base-for-startups
awsOfficial
AWS Startups reference content — Activate FAQ, credits guide, programs, partner offers, sample architectures, and hundreds of learn articles spanning…
SkillAFreshness: A★ 3KClaude Code +9 - 0.682score
aws-sms-voice
awsOfficial
Onboards RCS Business Messaging and Notify OTP via the pinpoint-sms-voice-v2 AWS CLI.
SkillAFreshness: A★ 3KClaude Code +9 - 0.682score
prompt-library-for-startups
awsOfficial
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly…
SkillAFreshness: A★ 3KClaude Code +9
Signals
- Stars
- 3,049
- Forks
- 394
- Open issues
- 40
- Last commit (this folder)
- Oct 22, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/aws/agent-toolkit-for-aws
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from aws
- 0.781score
AWS MCP Server
awsOfficial
A managed MCP server enabling AI agents to access AWS using docs, API calls, and SOP workflows.
ConnectorBFreshness: BLocal↓ 416.2K/wkClaude Code +5 - 0.781score
AWS MCP Server
awsOfficial
AWS MCP Server lets AI securely access AWS using docs, API calls, and SOP workflows.
ConnectorBFreshness: BLocal↓ 416.2K/wkClaude Code +5 - 0.682score
aws-sms-voice
awsOfficial
Onboards RCS Business Messaging and Notify OTP via the pinpoint-sms-voice-v2 AWS CLI.
SkillAFreshness: A★ 3KClaude Code +9 - 0.682score
prompt-library-for-startups
awsOfficial
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly…
SkillAFreshness: A★ 3KClaude Code +9 - 0.682score
knowledge-base-for-startups
awsOfficial
AWS Startups reference content — Activate FAQ, credits guide, programs, partner offers, sample architectures, and hundreds of learn articles spanning…
SkillAFreshness: A★ 3KClaude Code +9 - 0.682score
amazon-bedrock
awsOfficial
Builds generative AI applications on Amazon Bedrock.
SkillAFreshness: A★ 3KClaude Code +9
Cite this page
agent-advisor skill. Agent Mart. https://agentmart.dev/skills/aws-agent-advisor (last updated 2026-10-24)