@remixmate/cli 0.9.12 → 0.9.13

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "schemaVersion": 1,
3
- "version": "0.9.12",
4
- "generatedAt": "2026-08-12T01:53:36.480Z",
3
+ "version": "0.9.13",
4
+ "generatedAt": "2026-08-12T07:37:17.101Z",
5
5
  "skills": [
6
6
  {
7
7
  "id": "export-jianying",
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@remixmate/cli",
3
- "version": "0.9.12",
3
+ "version": "0.9.13",
4
4
  "description": "AI media generation skills for Claude Code / Codex — 12 skills covering image, video, voice, digital human, web screenshot, web recording, script, template registry, rendering, Jianying export, and video deconstruction.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -9,6 +9,8 @@ description: |
9
9
  - Turn a topic into a video structure / video content plan
10
10
 
11
11
  Even when the user does not say "generate the DSL", use this skill whenever they want to turn a topic into a structured video plan.
12
+
13
+ ⚠️ Stop-and-confirm gate: after this skill returns a DSL, show the full script and wait for the user's explicit confirmation. Never call `prepare_video_assets` in the same turn.
12
14
  triggers:
13
15
  - Write a video script, generate a video script, plan a video, write storyboards
14
16
  - Create a short video, plan video content, generate a Video DSL
@@ -19,6 +21,13 @@ triggers:
19
21
 
20
22
  Turns a user-supplied **topic** into a **Video DSL v1alpha1** JSON describing what the final video should look like (scene structure, asset requirements, narration text, visual layout). It never produces any asset itself.
21
23
 
24
+ > ⚠️ **Stop-and-confirm gate (mandatory, do not skip).**
25
+ > This skill produces a *draft* for the user to review, not an input to chain onward automatically.
26
+ > After it returns, show the full script and **stop your turn** — wait for the user to explicitly confirm.
27
+ > **Never** call `prepare_video_assets` in the same turn as `gen_script`: asset generation spends
28
+ > image and TTS credits that cannot be refunded, and a wrong narration line means paying for the
29
+ > whole batch twice. See **"Agent behavior: script confirmation"** below for the required summary format.
30
+
22
31
  ## Core concepts
23
32
 
24
33
  - **Video DSL**: a declarative description language for videos — describes the final structure, not the orchestration calls.
@@ -84,9 +93,19 @@ This skill does not hit any external API; no token required. The script only doe
84
93
  ### Confirmation flow
85
94
 
86
95
  1. After the agent generates or modifies the DSL, **show the script summary first; do not pass it downstream yet**.
87
- 2. Wait for the user to explicitly confirm (e.g. "OK", "looks good", "continue with template binding") before handing it to `prepare-video-assets` (or `template-registry` for a list-only lookup).
96
+ 2. **End your turn there and wait** for the user to explicitly confirm (e.g. "OK", "looks good", "continue with template binding") before handing it to `prepare-video-assets` (or `template-registry` for a list-only lookup).
88
97
  3. If the user asks for changes (adjust narration, add or remove scenes, change durations), the agent updates the DSL and shows the summary again, then waits for confirmation once more.
89
98
 
99
+ > ⚠️ **Never** call `prepare_video_assets` before the user has confirmed — not even when the original
100
+ > request was a single end-to-end instruction like "make me a video about X". That request authorizes
101
+ > the *pipeline*, not the skipping of its review steps. "Finish the task in one go" does **not** apply
102
+ > here: stopping for confirmation **is** the correct completion of this step.
103
+
104
+ ### Showing the script
105
+
106
+ Show **every scene in full** — do not collapse them with phrases like "scenes 2–6 same as above".
107
+ The user is reviewing the narration word by word; a summary they cannot proofread defeats the gate.
108
+
90
109
  ### Summary content
91
110
 
92
111
  The agent should show the following in clear Markdown:
@@ -9,6 +9,8 @@ description: |
9
9
  - Regenerate one asset (image / audio) for a specific scene
10
10
 
11
11
  Next step: after the user confirms the resolved assets, call `render_video` with the `job_id` returned by this skill.
12
+
13
+ ⚠️ Stop-and-confirm gate: this skill runs only after the user has confirmed the script, and after it returns you must show the resolved assets and wait for the user's explicit confirmation. Never call `render_video` in the same turn.
12
14
  triggers:
13
15
  - Generate / prepare video assets
14
16
  - Resolve missing assets in a DSL
@@ -20,6 +22,14 @@ triggers:
20
22
 
21
23
  Phase 1 of the two-phase video pipeline. Takes a Video DSL plus a template binding, walks every `AssetRef` declared in the DSL, calls the matching atomic skills to fill in missing assets (`gen-image`, `gen-voice`, `gen-video`, `gen-digital-human`), persists the resulting RenderPlan to ab-api, and prints a `job_id` for the user-confirmation step.
22
24
 
25
+ > ⚠️ **Stop-and-confirm gate (mandatory, do not skip) — both sides of this skill.**
26
+ > **Before**: only run this skill after the user has confirmed the script produced by `gen_script`.
27
+ > **After**: show the resolved assets (images inline, audio as links) and **stop your turn** — wait for
28
+ > the user to explicitly confirm before rendering. **Never** call `render_video` in the same turn as
29
+ > `prepare_video_assets`. This is the last checkpoint where a bad image or a wrong TTS take can be
30
+ > fixed for the price of one asset instead of a whole re-render.
31
+ > See **"Pre-render user confirmation (Phase 2)"** below for the required summary format.
32
+
23
33
  > **Next step**: after the user reviews the assets and confirms, call **`render_video`** with the `job_id` returned by this skill.
24
34
 
25
35
  ## Pipeline (this skill's part only)
@@ -94,7 +104,13 @@ python3 <SkillDir>/scripts/prepare_video_assets.py \
94
104
 
95
105
  ## Pre-render user confirmation (Phase 2)
96
106
 
97
- This skill is the **first half** of a two-phase user-confirmation flow. After it returns, the agent must show the user the resolved assets and wait for confirmation before calling `render_video`. The recommended summary format:
107
+ This skill is the **first half** of a two-phase user-confirmation flow. After it returns, the agent **must** show the user the resolved assets, then **end its turn and wait** for confirmation before calling `render_video`.
108
+
109
+ > ⚠️ **Never** start the final render before the user confirms. An end-to-end request ("make me a video
110
+ > about X") authorizes the pipeline, not the skipping of its review steps — stopping here **is** the
111
+ > correct completion of this step, not an unfinished task.
112
+
113
+ Read the `job_id` from the stdout line `📦 render job jobId: N` and remember it; asset URLs come from the `🔊 TTS audio:` and `🖼 Image assets:` sections. Show images inline (`![name](https://...)`) and audio as links (`[🔊 listen](http://cdn.../x.mp3)`) so the user can actually review them. The recommended summary format:
98
114
 
99
115
  ```markdown
100
116
  ## Render confirmation
@@ -9,6 +9,8 @@ description: |
9
9
  - Render with Remotion
10
10
 
11
11
  Prerequisite: assets must already be generated via `prepare_video_assets`. This skill never resolves or regenerates assets — pass it a `job_id` from a previous `prepare_video_assets` call.
12
+
13
+ ⚠️ Stop-and-confirm gate: never call this skill until the user has explicitly confirmed the assets prepared by `prepare_video_assets`. If those assets were prepared in the current turn and the user has not replied since, stop and ask instead of rendering.
12
14
  triggers:
13
15
  - Render the video, composite the video, export the video
14
16
  - Turn the prepared assets into the final clip
@@ -22,6 +24,17 @@ Loads a persisted RenderPlan from the database (or a local file fallback), compi
22
24
 
23
25
  > **Prerequisite**: assets must already be generated via `prepare_video_assets`. That skill returns a `job_id` integer; pass it here.
24
26
 
27
+ > ⚠️ **Stop-and-confirm gate (mandatory, do not skip).**
28
+ > **Never** call this skill until the user has explicitly confirmed the assets shown after
29
+ > `prepare_video_assets`. If those assets were prepared in the current turn and the user has not
30
+ > replied since, **stop and ask** — do not render. This step spends render credits and uploads the
31
+ > result; it is the one action in the pipeline that cannot be walked back cheaply.
32
+ >
33
+ > "Confirmed" means the user said so **in a message of their own** (e.g. "confirm", "go ahead",
34
+ > "looks good", "continue"). An end-to-end instruction from earlier in the conversation
35
+ > ("make me a video about X") is **not** confirmation — it authorizes the pipeline, not the
36
+ > skipping of its review steps. Stopping to ask **is** the correct completion of this step.
37
+
25
38
  ## Render pipeline (this skill's part only)
26
39
 
27
40
  ```