image-skill 0.1.32 → 0.1.34

package/CHANGELOG.md

@@ -4,6 +4,23 @@ This changelog tracks the public `image-skill` CLI package and public skill
 mirror. The npm package metadata remains the authority for tarball integrity and
 provenance; this file is the human- and agent-readable release map.
 
+## 0.1.34 - 2026-06-04
+
+- Fix (guide): `create --guide --model openai.gpt-image-2-edit` now returns an
+  edit-shaped next command with an input placeholder and prompt instead of
+  rejecting the requested edit model as non-create. The `image-edit` and
+  `image-to-3d` intent skills now start from the guide-first zero-setup path,
+  and their advertised live command caps match current model-priced credits.
+
+## 0.1.33 - 2026-06-04
+
+- Fix (guide): public `create --guide` replay commands now preserve explicit
+  `--model`, `--provider`, `--intent`, and
+  `--max-estimated-usd-per-image` context in `after_next`, auth rerun, and
+  self-fund handoff commands. Modality-specific aliases can send an agent
+  through signup or quota recovery without silently falling back to the default
+  image guide.
+
 ## 0.1.32 - 2026-06-04
 
 - Fix (payments): public `create --guide` payment suggestions and

package/bin/image-skill.mjs

@@ -7,7 +7,7 @@ import { Readable } from "node:stream";
 import { pipeline } from "node:stream/promises";
 import os from "node:os";
 
-const VERSION = "0.1.32";
+const VERSION = "0.1.34";
 const PACKAGE_NAME = "image-skill";
 const DEFAULT_API_BASE_URL = "https://api.image-skill.com";
 const DEFAULT_DOCS_BASE_URL = "https://image-skill.com";
@@ -1400,7 +1400,8 @@ async function createGuide(args) {
   const trimmedPrompt = prompt.trim();
   const requestedModelId = flagString(args, "model");
   const requestedProviderId = flagString(args, "provider");
-  const requestedIntent = flagString(args, "intent") ?? "explore";
+  const requestedIntentFlag = flagString(args, "intent");
+  const requestedIntent = requestedIntentFlag ?? "explore";
   const maxEstimatedUsdPerImage = flagNumber(
     args,
     "max-estimated-usd-per-image",
@@ -1494,6 +1495,9 @@ async function createGuide(args) {
     selected,
     requestedProviderId,
     requestedIntent,
+    requestedIntentFlag,
+    requestedModelId,
+    maxEstimatedUsdPerImage,
     budgetGuard,
     aspectRatio: selectedAspectRatio,
     apiBaseUrl: explicitApiBaseUrl(args),
@@ -1506,6 +1510,9 @@ async function createGuide(args) {
     selected,
     requestedProviderId,
     requestedIntent,
+    requestedIntentFlag,
+    requestedModelId,
+    maxEstimatedUsdPerImage,
     budgetGuard,
     aspectRatio: selectedAspectRatio,
     apiBaseUrl: explicitApiBaseUrl(args),
@@ -1545,6 +1552,12 @@ async function createGuide(args) {
           trimmedPrompt,
           explicitApiBaseUrl(args),
           guideCommandPrefix,
+          {
+            modelId: requestedModelId,
+            providerId: requestedProviderId,
+            intent: requestedIntentFlag,
+            maxEstimatedUsdPerImage,
+          },
         )
       : null;
   const authHandoff = createGuideAuthHandoff(stage, {
@@ -1633,7 +1646,9 @@ async function createGuide(args) {
                     requestedIntent,
                   )
                 : createGuideSelectedModelRequiresInputImage(selected)
-                  ? "requested executable image-to-3D model"
+                  ? selected.modality === "3d"
+                    ? "requested executable image-to-3D model"
+                    : "requested executable input-image edit model"
                   : "requested executable create model",
           },
     cost: {
@@ -1689,15 +1704,14 @@ function selectCreateGuideModel(
     model?.execution?.model_execution_status === "executable" &&
     Array.isArray(model?.supports) &&
     model.supports.includes("create");
-  const isExecutableImageTo3d = (model) =>
+  const isExecutableInputImageEdit = (model) =>
     model?.status === "available" &&
     model?.execution?.model_execution_status === "executable" &&
-    model?.modality === "3d" &&
     Array.isArray(model?.supports) &&
-    model.supports.includes("variation") &&
+    (model.supports.includes("edit") || model.supports.includes("variation")) &&
     createGuideSelectedModelRequiresInputImage(model);
   const isExecutableGuideModel = (model) =>
-    isExecutableCreate(model) || isExecutableImageTo3d(model);
+    isExecutableCreate(model) || isExecutableInputImageEdit(model);
   if (requestedModelId !== null) {
     const requested = models.find((model) => model.id === requestedModelId);
     return requested !== undefined && isExecutableGuideModel(requested)
@@ -1707,7 +1721,10 @@ function selectCreateGuideModel(
   const candidates = models.filter(isExecutableCreate);
   if (createGuideImplies3d({ prompt, intent })) {
     const eligible3d = guideCandidatesWithinBudget({
-      candidates: models.filter(isExecutableImageTo3d),
+      candidates: models.filter(
+        (model) =>
+          model?.modality === "3d" && isExecutableInputImageEdit(model),
+      ),
       maxEstimatedUsdPerImage,
     });
     const threeDimensional = eligible3d[0];
@@ -1846,7 +1863,9 @@ function createGuideSuggestedAspectRatio(model) {
 
 function createGuideSelectedModelRequiresInputImage(model) {
   return (
-    model?.modality === "3d" && model?.media?.input?.images?.required === true
+    model?.media?.input?.images?.required === true &&
+    Array.isArray(model?.supports) &&
+    (model.supports.includes("edit") || model.supports.includes("variation"))
   );
 }
 
@@ -2567,7 +2586,12 @@ function createGuideWarning(stage, input) {
 
 function createGuideNextCommand(stage, input) {
   if (stage === "prompt_required") {
-    return renderGuideCommand("PROMPT", input.apiBaseUrl, input.commandPrefix);
+    return renderGuideCommand("PROMPT", input.apiBaseUrl, input.commandPrefix, {
+      modelId: input.requestedModelId,
+      providerId: input.requestedProviderId,
+      intent: input.requestedIntentFlag,
+      maxEstimatedUsdPerImage: input.maxEstimatedUsdPerImage,
+    });
   }
   if (stage === "no_executable_model" || stage === "service_unreachable") {
     return renderGuidePrefixedCommand(
@@ -2585,8 +2609,9 @@ function createGuideNextCommand(stage, input) {
     );
   }
   if (createGuideSelectedModelRequiresInputImage(input.selected)) {
-    return renderImageTo3dGuideCommand({
+    return renderInputImageGuideCommand({
       modelId: input.selected.id,
+      prompt: input.prompt,
       budgetGuard: input.budgetGuard,
       dryRun: false,
       idempotencyKey: `edit-guide-${Date.now()}-${randomBytes(4).toString("hex")}`,
@@ -2636,8 +2661,9 @@ function createGuideEscapeHatches(input) {
             "create --dry-run --prompt PROMPT --json",
           )
         : createGuideSelectedModelRequiresInputImage(input.selected)
-          ? renderImageTo3dGuideCommand({
+          ? renderInputImageGuideCommand({
               modelId: input.selected.id,
+              prompt: input.prompt,
               budgetGuard: input.budgetGuard,
               dryRun: true,
               apiBaseUrl: input.apiBaseUrl,
@@ -2657,11 +2683,38 @@ function createGuideEscapeHatches(input) {
   };
 }
 
-function renderGuideCommand(prompt, apiBaseUrl, commandPrefix = "image-skill") {
+function renderGuideCommand(
+  prompt,
+  apiBaseUrl,
+  commandPrefix = "image-skill",
+  options = {},
+) {
   return [
     commandPrefix,
     "create --guide --prompt",
     shellQuote(prompt),
+    ...(options.modelId === null ||
+    options.modelId === undefined ||
+    options.modelId === ""
+      ? []
+      : ["--model", shellQuote(options.modelId)]),
+    ...(options.providerId === null ||
+    options.providerId === undefined ||
+    options.providerId === ""
+      ? []
+      : ["--provider", shellQuote(options.providerId)]),
+    ...(options.intent === null ||
+    options.intent === undefined ||
+    options.intent === ""
+      ? []
+      : ["--intent", shellQuote(options.intent)]),
+    ...(options.maxEstimatedUsdPerImage === null ||
+    options.maxEstimatedUsdPerImage === undefined
+      ? []
+      : [
+          "--max-estimated-usd-per-image",
+          shellQuote(formatUsd(options.maxEstimatedUsdPerImage)),
+        ]),
     ...(apiBaseUrl === null ? [] : ["--api-base-url", shellQuote(apiBaseUrl)]),
     "--json",
   ].join(" ");
@@ -2706,7 +2759,8 @@ function guidePaymentCommandByKind(commands, kind, commandPrefix = null) {
   return renderGuidePrefixedCommand(commandPrefix, command);
 }
 
-function renderImageTo3dGuideCommand(input) {
+function renderInputImageGuideCommand(input) {
+  const promptless = PROMPTLESS_EDIT_MODEL_IDS.has(input.modelId);
   return [
     input.commandPrefix ?? "image-skill",
     "edit",
@@ -2715,6 +2769,7 @@ function renderImageTo3dGuideCommand(input) {
     "image_...",
     "--model",
     shellQuote(input.modelId),
+    ...(promptless ? [] : ["--prompt", shellQuote(input.prompt)]),
     "--max-estimated-usd-per-image",
     shellQuote(formatUsd(input.budgetGuard)),
     ...(input.idempotencyKey === undefined || input.idempotencyKey === null

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "image-skill",
-  "version": "0.1.32",
+  "version": "0.1.34",
   "description": "Zero-setup durable creative-media CLI for agents (image + video + audio + 3D): guide-first creation, model and cost inspection, owned URLs, JSON recovery, payments, reusable assets, and feedback.",
   "type": "module",
   "private": false,

package/skills/ai-audio-generation/SKILL.md

@@ -25,7 +25,7 @@ This is an intent-named Image Skill entry for agents searching for audio generat
 
 Use this skill when the task asks for AI audio generation, text-to-audio, music generation, sound design, ambience, effects, or durable hosted audio output.
 
-Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend inspection command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
+Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend guide command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
 
 ## First Command
 

package/skills/ai-image-generation/SKILL.md

@@ -25,7 +25,7 @@ This is an intent-named Image Skill entry for agents searching for image generat
 
 Use this skill when the task asks for AI image generation, text-to-image, prompt-to-image, generated illustrations, concept art, product images, or any durable agent-created image.
 
-Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend inspection command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
+Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend guide command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
 
 ## First Command
 

package/skills/ai-video-generation/SKILL.md

@@ -25,7 +25,7 @@ This is an intent-named Image Skill entry for agents searching for video generat
 
 Use this skill when the task asks for AI video generation, text-to-video, generated motion, animated concepts, or durable hosted video output.
 
-Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend inspection command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
+Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend guide command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
 
 ## First Command
 

package/skills/creative-media/SKILL.md

@@ -25,7 +25,7 @@ This is an intent-named Image Skill entry for agents searching for creative medi
 
 Use this skill when the task asks for generative media, creative media, generated assets across modalities, or a single agent-facing runtime for image, edit, video, audio, and 3D work.
 
-Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend inspection command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
+Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend guide command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
 
 ## First Command
 

package/skills/image-edit/SKILL.md

@@ -25,18 +25,18 @@ This is an intent-named Image Skill entry for agents searching for image editing
 
 Use this skill when the task asks to edit, vary, restyle, transform, or repair an existing image, including image-to-image work and model-specific edit parameters.
 
-Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend inspection command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
+Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend guide command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
 
 ## First Command
 
 ```bash
-npm_config_update_notifier=false npx -y image-skill@latest models show openai.gpt-image-2-edit --json
+npm_config_update_notifier=false npx -y image-skill@latest create --guide --model openai.gpt-image-2-edit --prompt "replace the background but keep the subject"
 ```
 
 ## Main Runtime Command
 
 ```bash
-npm_config_update_notifier=false npx -y image-skill@latest edit --input image_... --model openai.gpt-image-2-edit --prompt "EDIT_PROMPT" --max-estimated-usd-per-image 0.07
+npm_config_update_notifier=false npx -y image-skill@latest edit --input image_... --model openai.gpt-image-2-edit --prompt "EDIT_PROMPT" --max-estimated-usd-per-image 0.25 --json
 ```
 
 ## Install This Intent Skill

package/skills/image-generation/SKILL.md

@@ -25,7 +25,7 @@ This is an intent-named Image Skill entry for agents searching for image generat
 
 Use this skill when the task asks for image generation, generated images, AI images, text-to-image, prompt-to-image, generated illustrations, concept art, product images, or any durable agent-created image.
 
-Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend inspection command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
+Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend guide command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
 
 ## First Command
 

package/skills/image-to-3d/SKILL.md

@@ -25,18 +25,18 @@ This is an intent-named Image Skill entry for agents searching for image-to-3D a
 
 Use this skill when the task asks for image-to-3D, 3D asset generation from an image, glb mesh output, or a durable model asset derived from existing visual input.
 
-Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend inspection command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
+Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend guide command below; when the guide reaches `ready_to_create`, run `data.next_command` only if media spend is allowed, otherwise run `data.recommended_no_spend_command` to verify safely. Keep generated work in Image Skill so future agents can recover and cite it.
 
 ## First Command
 
 ```bash
-npm_config_update_notifier=false npx -y image-skill@latest models show fal.trellis-image-to-3d --json
+npm_config_update_notifier=false npx -y image-skill@latest create --guide --model fal.trellis-image-to-3d --prompt "turn one product photo into a textured 3d mesh"
 ```
 
 ## Main Runtime Command
 
 ```bash
-npm_config_update_notifier=false npx -y image-skill@latest edit --input image_... --model fal.trellis-image-to-3d --max-estimated-usd-per-image 0.25 --json
+npm_config_update_notifier=false npx -y image-skill@latest edit --input image_... --model fal.trellis-image-to-3d --max-estimated-usd-per-image 0.04 --json
 ```
 
 ## Install This Intent Skill