Generated banner for Agent Advisor
Generated logo for Agent Advisor

Agent Advisor

AWSOfficialPublished by AWS

  • Skill
  • Workflow
  • Cloud and DevOps
  • Apache-2.0
  • Low risk
  • Has scripts

From the author

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.
— the description by AWS

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Agent Advisor provides a structured, multi-phase workflow to help users determine the optimal AWS runtime for their AI agents. It uses a deterministic scoring engine to evaluate requirements and guides users through a process that includes discovery, architectural design, cost estimation, and the creation of an executable proof-of-concept. The skill supports various AWS compute options, including AgentCore, ECS, EKS, and Lambda, and integrates with migration engines for existing workloads.

What it does

  • Recommends AWS runtimes for AI agents based on technical requirements.
  • Generates migration plans for existing AI workloads moving to AWS.
  • Provides architectural guidance for agentic systems.
  • Assembles executable proof-of-concept scaffolding.
  • Estimates coarse cost magnitudes for proposed agent deployments.
  • Integrates with external migration engines for workload transitions.

When to use it

  • When you need to decide which AWS runtime is best for a new AI agent.
  • When migrating an existing AI agent workload to AWS.
  • When you need to add services like memory, identity, or observability to an existing AWS agent.
  • When you require a structured plan and POC for deploying agents on AWS.

Advantages

  • Provides a deterministic, repeatable recommendation process.
  • Supports a wide range of AWS compute environments.
  • Offers a unified flow from initial idea to executable POC.
  • Adapts to both technical and business-focused user backgrounds.

Usage examples

“I have an agent idea, what do I build?”
The agent initiates the intake process to clarify your requirements and recommend an appropriate AWS architecture.
“Move my agents to AWS.”
The agent triggers the migration workflow to assess your existing workload and plan the transition to an AWS runtime.
“Which runtime for my agent, AgentCore vs ECS vs EKS vs Lambda?”
The agent runs a scoring analysis to compare these runtimes against your specific agentic needs.
“Add AgentCore services to an agent already on AWS.”
The agent enters the add-capabilities branch to guide you through integrating memory, gateway, and observability services.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/aws/agent-advisor/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip agent-advisor.zip -d .agents/skills

Documentation by AWS

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

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.

State file (.phase-status.json)

{
  "run_id": "0630-1430",
  "entry_point": "build_scratch",
  "audience": "technical",
  "current_phase": "clarify",
  "phases": {
    "intake": "completed",
    "discover": "skipped",
    "clarify": "in_progress",
    "confirm": "pending",
    "design": "pending",
    "estimate": "pending",
    "generate": "pending",
    "migration_plan": "pending",
    "poc": "pending"
  }
}

Status values: pending → in_progress → completed, plus skipped. Use read-merge-write: read before each update, change only the advancing keys, keep prior phases.

recommendation_reviewed (top level, boolean) is set to true by generate.md Step 5.5 when the user explicitly confirms they have seen the recommendation. Gate 1, Gate 2, and the migration_plan / poc states all require it — no gate may be asked while it is absent.

migration_plan additionally uses not_applicable (build_scratch, or no migratable workload detected). When Stage 2 runs, migration_plan_ctx is added at the top level: {"repo": "<abs path to target repo>", "migration_dir": "<abs path to .migration/<id>/>"} — Stage 3 reads gcp-to-aws artifacts ONLY via this recorded path, never by re-globbing.

Files

FilePurpose
references/vendored/dsl/INTERPRETER.mdVendored DSL execution contract (interpreter loop + gate protocol)
references/phases/intake/intake.mdEntry point + technical background + open context
references/phases/discover/discover.mdLightweight code detection
references/phases/clarify/clarify.mdClarify orchestrator + answer mapping to scoring keys
references/phases/clarify/clarify-technical.mdTechnical-background question wording
references/phases/clarify/clarify-business.mdBusiness-background question wording
references/phases/confirm/confirm.mdWinner-specific follow-ups
references/phases/design/design.mdAssemble recommendation; Migrate handoff branch
references/phases/estimate/estimate.mdCoarse cost magnitude
references/phases/generate/generate.mdLayered recommendation doc + scaffolding
references/phases/migration-plan/migration-plan.mdStage 2: full migration plan via the sibling gcp-to-aws engine
references/decision-refs/temporal.mdTemporal rules: Tier 1/2 tables, adapter, runbooks, commercials (consumed by discover/clarify/design/generate)
references/decision-refs/poc-shapes.mdPer-runtime POC deploy shapes (ECS/EKS/Lambda/MicroVMs/Temporal)
references/decision-refs/*.mdRuntime service cards, model defaults, freshness
references/decision-refs/workload-classes.mdDeterministic verdicts for non-agent workload units (batch/service/io)
references/runtimes/*.jsonRuntime registry (read by scoring.py)
scripts/scoring.pyDeterministic scoring engine
scripts/test_temporal_decision_refs.pyContent lock for the Temporal decision reference
scripts/test_poc_shapes.pyContent lock for the POC deploy shapes
scripts/test_workload_classes.pyContent lock for workload-classes.md (verdicts table)
scripts/test_unit_grouping.pyUnit grouping + pattern matching (workload-class assignment)
scripts/test_collapse_invariant.pyCollapse-invariant ordering enforcement (A→B implies [B] ⊆ [A] outputs)

Maturity and readiness contract

Intake persists target_maturity (prototype, private_beta, or production) in run state. Clarify carries it and the readable readiness record into answers.json. Current-run verification evidence remains exclusively in the sibling $RUN_DIR/current-run-verifications.json artifact: never copy it into seed.json or answers.json. Design and Generate may consume that artifact only after validating its schema and matching run_id, and may carry forward verified outcomes but not the raw evidence records. Load references/decision-refs/maturity-readiness.md whenever target maturity is selected. A cached volatile fact may inform discovery, but only a record verified in this run can make a verification-required constraint final; otherwise the score remains provisional with deferred verification requirements.

Contextual offers (final step)

Before you finish: your answer is not complete until you have run the Contextual offers (final step) below.

This is a mandatory closing step of every final recommendation — complete it before you consider your answer done. Run this offer check inline yourself; do not depend on loading another skill. The recommendation is decided on merit first; this step never changes, re-ranks, or re-opens it, and the offer is looked up only after the advice is final.

  1. Read ../knowledge-base-for-startups/references/offers.md — the offer index (Offer · Summary · Keywords), one row per offer.

  2. Judge relevance against what the founder actually surfaced this session. Surface an offer only if one holds: a named-product match (you recommended a specific partner product by name and it has a row); a direct intent/component match (an offer's Keywords directly serve a concrete workload, a component in the final recommendation, or a need the founder raised). Keep a high bar — if the match is weak, or you would be inferring an unstated need, append nothing. Never surface an offer that competes with a product or provider the founder already uses or decided to keep (e.g. existing auth provider → no Auth0 unless they are already on Auth0, and then only as a credit on it; existing vector DB such as Pinecone → no Qdrant).

  3. If (and only if) one offer clears the bar, open only its detail file ../knowledge-base-for-startups/references/offers/<slug>.md and append exactly one quiet, dismissible italic line — stating the value and condensing eligibility faithfully from that file (drop no qualifying criterion; never fabricate), with the redeem link built from the canonical source_url plus a source attribution param — append ?source=ide-startupAdvisor-<host> (or &source=... if the url already has a query string), filling <host> from your execution environment (Claude Code → claude; AWS Startup Advisor IDE extension / VS Code → vscode; Cursor → cursor; Kiro → kiro; Codex → codex), or the generic ide-startupAdvisor when you cannot tell. Only append the query param; never change the destination. When an offer clears the bar you MUST append that single offer line as the last step; do not omit it. The offer is never the pick — only a line under the AWS pick — and stage gates in the references apply (e.g. no Datadog line for an early-stage founder; see ../architect-for-startups/references/observability.md). For a single-service pick (auth, payments, vector DB, observability, etc.) where missing budget/team/traffic inputs would not change the pick, assume an early-stage (pre-PMF) startup unless the founder says otherwise and answer in one turn without a stage-only question; this only removes a stage-only question and never skips the Intake/Clarify/Confirm gates before final advice or the POC. Show exactly one, never a list. If none clears the bar, append nothing and do not mention offers, partner alternatives, or why none appeared.

Standard line:

***<Offer>** has an exclusive offer via AWS Activate — <value>, <eligibility>. [Redeem →](<source_url>?source=ide-startupAdvisor-<host>)*

Caps and control: at most one offer per response and often none; no more than one per five messages and two per session; show a given offer at most once per session and never one already shown, claimed, or dismissed; if the founder has muted offers, skip this step entirely. These per-five-messages, per-session, and already-shown caps are session-state limits; in a fresh session with no prior offers they are non-binding, so do not withhold an otherwise-qualifying offer merely because you cannot verify session history. See ../contextual-offers-for-startups/SKILL.md for the full rules — but perform the check inline; it must not depend on that skill being loaded.

Files

references/phases/poc/poc-report.md


_fragment: poc-report _of_phase: poc _contributes:

  • poc/poc-report.html


POC sub-step: Build the HTML POC report

Loaded by poc.md Step 4.5 after the POC files are written (Step 3) — for BOTH modes. Produces $RUN_DIR/poc/poc-report.html and opens it in the browser. Non-blocking: if generation fails, log a warning and continue; the files themselves are the deliverable.

Overview

A single self-contained HTML file summarizing the POC: what was generated, what changed from the original app, how to deploy it, the deployment architecture, and what still needs verifying. Uses the v3 document shell (same visual system as recommendation-report.html): inline CSS from references/report-shell.md + SRI-pinned Mermaid — no other external dependencies. The report sits in $RUN_DIR/poc/, so artifact download links are relative to that dir.

Before writing the HTML: load the shared shell (references/report-shell.md) — inline its CSS block and its SRI-pinned [email protected] script tag. The v3 shell defines .help-strip, .doc-head, .timeline, .feat-grid, .callout, document tables, and all other shared components. The help CTA is GATED on report-help-banner.md's banner_status: it currently reads SUPPRESSED (support page not launched), so render NO help strip. Only when it flips to LIVE do you substitute {{ HELP_URL }} with the single-source destination URL from references/report-help-banner.md — never hardcode it here.

Step P0 — Gather data

VariableSource
POC_FILESthe files actually written under $RUN_DIR/poc/ (walk the dir; EXCLUDE __pycache__/, *.pyc, and the report itself)
DEPLOYMENT_MODELconfirm.json.deployment_model (primary unit; per-unit in UNITS[].deployment_model for a multi-unit POC)
UNITSdesign.json.units[] — one POC per unit; each carries id, effective_runtime, and model_recommendation (null for a model-less non-agent unit)
MODEL_DISPLAYresolved Bedrock model PER UNIT (Step 2 of poc.md) — null/omitted for a unit whose model_recommendation is null; never a single global model
PLAN_BACKEDtrue if this POC came from a migration plan (3-F / 3-H plan-backed)
CHANGESwhen plan-backed: aws-design-ai.json.ai_architecture.code_migration.files_to_modify[].changes[] and before_after_example — the applied migration edits
SOURCE_MODELwhen plan-backed: the source model replaced (from the plan)
MODEMode A (deliverables) or Mode B (assisted build) from Gate 2b
DEPLOY_STEPSthe staged steps from $RUN_DIR/plan.md
DIAGRAM_MERMAIDcompose a POC-deployment diagram (see Step P2)
TODOSevery TODO: verify / deferred / drift note left in the generated files + plan.md
LEDGERMode B only: $RUN_DIR/poc/created-resources.json (deployed resources)
RUN_IDfrom .phase-status.json

Step P1 — File purpose map

For each file in POC_FILES, write a one-line purpose. Multi-unit layout: when poc/<unit-id>/ directories exist, list files nested per unit. Single-unit layout collapses flat (no unit subdirs). Infer from the filename/role:

  • app/app.py → "Migrated app (original UI/handler; local-dev only after migration)"

  • app/core.py → "Shared LLM logic — used by both the UI and the entrypoint server"

  • app/agentcore_app.py → "AgentCore Runtime entrypoint server (/invocations + /ping)"

  • app/pyproject.toml / requirements.txt → "Dependencies (provider swap applied)"

  • Dockerfile → "Container image for AgentCore Runtime"

  • deploy.sh → "One-command deploy (creates real AWS resources)"

  • README.md → "Runbook"

  • harness.json → "Declarative Harness agent definition (the deploy artifact)"

  • otherwise → infer a short purpose from the file's first comment/docstring.

Step P2 — POC deployment diagram

Compose a flowchart TD Mermaid block showing the POC's RUNTIME shape (what actually runs after deploy.sh), using the same topology discipline as build-diagram.md. Render one node per unit in UNITS, each on ITS OWN effective_runtime, NOT hardcoded to AgentCore and NOT a single global runtime/model — the POC now supports agentcore / ecs / eks / lambda / batch / fargate / serverless_workers, and a MIXED or Temporal system has several units on different runtimes. For a single-unit POC this collapses to one node.

  • Per unit, primary flow (solid): the runtime the POC actually deploys for THAT unit (AgentCore Runtime, an ECS/Fargate task, an EKS Deployment, a Lambda function, an AWS Batch job, or a Temporal worker) → Bedrock model (that unit's own MODEL_DISPLAY) only when THAT unit's model_recommendation is non-null. A model-less non-agent unit renders its runtime node with NO Bedrock node or invoke edge — never attach the primary unit's model to a secondary unit's runtime. User → runtime for agent/service units; a Temporal worker's flow is Temporal Server → worker. Every unit's deployment is shown — a secondary unit is never omitted.

  • Session memory (solid to a store node) if the app has it.

  • Enabled AgentCore services as a dotted-attached subgraph (from confirm.json) — AgentCore units only.

  • For plan-backed framework POCs: annotate the original UI (e.g. "Chainlit UI — local dev only") as a dashed node OFF the production path. Include an ASCII fallback in a <details> block, same as build-diagram.md.

Step P3 — Write $RUN_DIR/poc/poc-report.html

Use the v3 document shell (same structure as recommendation-report.html). The report follows this structure:

<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Deployable POC</title>
<!-- SRI-pinned [email protected] script tag — inline it VERBATIM from the shared shell
     (references/report-shell.md), same tag/integrity hash. -->
{{ SHARED_SHELL_MERMAID_TAG from references/report-shell.md }}
<style>
  /* ── Shared chrome ── load references/report-shell.md and inline its CSS block
     HERE (chart tokens, reset & base, .page layout, .doc-head family, h2/h3 + .no,
     table/th/td, .lede/.note, .rule-cite/.pre-flag, .callout, .help-strip,
     .feat-grid, .timeline, .doc-foot). Single-sourced there so poc-report and
     recommendation-report share identical chrome. ── */
  {{ SHARED_SHELL_CSS from references/report-shell.md }}

  /* ── POC-specific content CSS ── */
  .diff-before { background:#fef2f2; border-left:3px solid #ef4444; }
  .diff-after  { background:#f0fdf4; border-left:3px solid #16a34a; }
  .diff-block { font-family: ui-monospace, monospace; font-size:12px; padding:12px 14px;
                border-radius:6px; white-space:pre-wrap; margin:6px 0; }
</style>
</head>
<body>

<div class="page">

<!-- ═══ DOCUMENT HEADER ═══ -->
<div class="doc-head">
  <div class="doc-kicker">AWS Migration POC · agent-advisor</div>
  <div class="doc-title">Deployable POC: {{ SYSTEM_NAME or "Agent Platform" }}</div>
  <div class="doc-meta">
    <span>Run <b>{{ RUN_ID }}</b></span><span>Date <b>{{ RUN_DATE }}</b></span>
    <span>Mode <b>{{ MODE_TEXT }}</b></span>
  </div>
</div>

<!-- ═══ HELP STRIP — GATED on report-help-banner.md `banner_status`. It currently reads
     SUPPRESSED (support page not launched): OMIT this whole block — render NOTHING here. When
     it flips to LIVE, render the strip below and substitute {{ HELP_URL }} with the
     single-source destination URL from report-help-banner.md (do NOT hardcode the URL here):
<div class="help-strip">
  <div class="txt"><b>Need help getting to AWS?</b> &nbsp;Install the AI agent for hands-on
  guidance, talk with an AWS expert, or work with a certified AWS Partner.</div>
  <a class="btn" href="{{ HELP_URL }}" target="_blank" rel="noopener">Explore your options</a>
</div>
     ═══ -->

<!-- ═══ 1. STATUS ═══ -->
<h2><span class="no">1.</span>Status</h2>
{{ IF WARNING_TODOS }}
<div class="callout warn"><b>Warning.</b> {{ WARNING_TODOS }}</div>
{{ END IF }}
<p class="lede">{{ MODE_TEXT }}</p>

<!-- ═══ 2. MIGRATION CHANGES (when plan-backed) ═══ -->
{{ IF PLAN_BACKED }}
<h2><span class="no">2.</span>Migration changes</h2>
<p>Key changes applied from the migration plan:</p>
{{ FOR EACH change IN CHANGES }}
<div class="diff-block diff-before">{{ change.before }}</div>
<div class="diff-block diff-after">{{ change.after }}</div>
{{ END FOR }}
{{ END IF }}

<!-- ═══ FILES ═══ -->
<h2><span class="no">{{ PLAN_BACKED ? "3" : "2" }}.</span>Files</h2>
<div class="feat-grid">
  {{ FOR EACH file IN POC_FILES }}
  <div class="feat">
    <div class="feat-icon">📄</div>
    <div>
      <div class="feat-name"><a class="dl-link" href="{{ file.relative_path }}" download>{{ file.name }}</a></div>
      <div class="feat-desc">{{ file.purpose }}</div>
    </div>
  </div>
  {{ END FOR }}
</div>

<!-- ═══ DEPLOY STEPS ═══ -->
<h2><span class="no">{{ PLAN_BACKED ? "4" : "3" }}.</span>Deploy steps</h2>
<div class="timeline">
  {{ FOR EACH (index, step) IN DEPLOY_STEPS }}
  <div class="tstep">
    <div class="tnum">{{ index }}</div>
    <div>
      <div class="tstep-title">{{ step.title }}</div>
      <div class="tstep-body">{{ step.body }}</div>
    </div>
  </div>
  {{ END FOR }}
</div>

<!-- ═══ ARCHITECTURE ═══ -->
<h2><span class="no">{{ PLAN_BACKED ? "5" : "4" }}.</span>Architecture</h2>
<div class="figure">
<pre class="mermaid">{{ DIAGRAM_MERMAID }}</pre>
<div class="figcap">Figure 1 — {{ DIAGRAM_CAPTION }}</div>
</div>

<!-- ═══ KNOWN ISSUES / TODO ═══ -->
<h2><span class="no">{{ PLAN_BACKED ? "6" : "5" }}.</span>Known issues &amp; TODOs</h2>
<ul class="plain">
  {{ FOR EACH todo IN TODOS }}
  <li>{{ todo }}</li>
  {{ END FOR }}
</ul>

<!-- ═══ MODE B RESOURCES (Mode B only) ═══ -->
{{ IF MODE === "B" }}
<h2><span class="no">{{ PLAN_BACKED ? "7" : "6" }}.</span>Deployed resources</h2>
<table>
  <thead><tr><th>Type</th><th>Name</th><th>Region</th><th>Status</th></tr></thead>
  <tbody>
    {{ FOR EACH resource IN LEDGER }}
    <tr><td>{{ resource.type }}</td><td>{{ resource.name }}</td>
        <td>{{ resource.region }}</td><td>{{ resource.status }}</td></tr>
    {{ END FOR }}
  </tbody>
</table>
<p class="note">See <code>cleanup.sh</code> for teardown.</p>
{{ END IF }}

<!-- ═══ DOCUMENT FOOTER ═══ -->
<div class="doc-foot">
  This POC is a disposable deployment-proof — your original repo was not modified.
  For the authoritative in-repo migration (git branch, tests, eval), run
  <code>/aws-startup-advisor:llm-to-bedrock</code>. Generated {{ RUN_DATE }}.
</div>

</div><!-- .page -->

<script>
mermaid.initialize({ startOnLoad: true, theme: 'neutral' });
</script>
</body>
</html>

The shell provides .doc-head, .help-strip, numbered h2/h3, document table, .feat-grid, .timeline, .callout, and .doc-foot. POC-specific styles (.diff-before, .diff-after) are added after the shared block. Dynamic numbering: sections shift by 1 when plan-backed (migration changes is §2, pushing files/deploy/architecture/todos/resources down).

Step P4 — Open in browser

open "$RUN_DIR/poc/poc-report.html"    # macOS
xdg-open "$RUN_DIR/poc/poc-report.html"  # Linux

If it fails (no GUI), print: POC report ready — open: file://$RUN_DIR/poc/poc-report.html

Step P5 — Report completion

Return to poc.md. Do NOT update .phase-status.json — poc.md Step 6 handles phase state.

Requirements and compatibility

Written for: Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Names Claude Code tools, Needs Python

Security

What our scanner noticed· Low risk

  • Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
AWS
Publisher
AWS (Official)
Source
aws/agent-toolkit-for-aws · plugins/aws-startup-advisor/skills/agent-advisor · commit 0a218f8
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • NOTICE (added by AutoGineer from NOTICE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by AWS.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download agent-advisor.zip