@acedatacloud/skills 2026.505.0 → 2026.606.0

package/AGENTS.md

@@ -27,7 +27,7 @@ Skills are located in the `skills/` directory (also mirrored to `.agents/skills/
 - **wan-video** — Generate videos with Alibaba Wan
 
 ### AI Chat & Tools
-- **ai-chat** — Unified LLM gateway — GPT, Claude, Gemini, DeepSeek, Grok (50+ models)
+- **ai-chat** — Unified LLM gateway — GPT, Claude, Gemini, Kimi, Grok (50+ models)
 - **google-search** — Search the web, images, news, maps, places, and videos via Google
 - **face-transform** — Face analysis, beautification, age/gender transform, swap, cartoon
 - **short-url** — Create and manage short URLs

package/README.md

@@ -46,7 +46,7 @@ Compatible with **30+ AI coding agents** via the [agentskills.io](https://agents
 
 | Skill | Description |
 |-------|-------------|
-| [ai-chat](skills/ai-chat/) | Unified LLM gateway — GPT, Claude, Gemini, DeepSeek, Grok (50+ models) |
+| [ai-chat](skills/ai-chat/) | Unified LLM gateway — GPT, Claude, Gemini, Kimi, Grok (50+ models) |
 | [google-search](skills/google-search/) | Search the web, images, news, maps, places, and videos via Google |
 | [face-transform](skills/face-transform/) | Face analysis, beautification, age/gender transform, swap, cartoon |
 | [short-url](skills/short-url/) | Create and manage short URLs |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@acedatacloud/skills",
-  "version": "2026.505.0",
+  "version": "2026.606.0",
   "description": "Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search. Compatible with Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and 30+ AI coding agents.",
   "keywords": [
     "agent-skills",

package/skills/acedatacloud-api/SKILL.md

@@ -111,7 +111,7 @@ Error response format:
 
 | Category | Services | Base Path |
 |----------|----------|-----------|
-| **AI Chat** | GPT, Claude, Gemini, DeepSeek, Grok | `/v1/chat/completions` |
+| **AI Chat** | GPT, Claude, Gemini, Kimi, Grok | `/v1/chat/completions` |
 | **Image Gen** | Midjourney, Flux, Seedream, NanoBanana | `/midjourney/*`, `/flux/*`, etc. |
 | **Video Gen** | Luma, Sora, Veo, Kling, Hailuo, Seedance, Wan | `/luma/*`, `/sora/*`, etc. |
 | **Music Gen** | Suno, Producer, Fish Audio | `/suno/*`, `/producer/*`, `/fish/*` |

package/skills/ai-chat/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ai-chat
-description: Access 50+ LLM models through a unified OpenAI-compatible API via AceDataCloud. Use when you need chat completions from GPT, Claude, Gemini, DeepSeek, Grok, or other models through a single endpoint. Supports streaming, function calling, and vision.
+description: Access 50+ LLM models through a unified OpenAI-compatible API via AceDataCloud. Use when you need chat completions from GPT, Claude, Gemini, Kimi, Grok, or other models through a single endpoint. Supports streaming, function calling, and vision.
 license: Apache-2.0
 metadata:
   author: acedatacloud
@@ -62,6 +62,7 @@ print(response.choices[0].message.content)
 
 | Model | Type | Best For |
 |-------|------|----------|
+| `claude-opus-4-8` | Latest Opus | Highest capability |
 | `claude-opus-4-6` | Latest Opus | Highest capability |
 | `claude-sonnet-4-6` | Latest Sonnet | Balanced quality/speed |
 | `claude-opus-4-5-20251101` | Opus 4.5 | Premium tasks |
@@ -78,15 +79,6 @@ print(response.choices[0].message.content)
 | `gemini-1.5-pro` | Long context, complex tasks |
 | `gemini-1.5-flash` | Fast, efficient |
 
-### DeepSeek
-
-| Model | Best For |
-|-------|----------|
-| `deepseek-r1` | Deep reasoning |
-| `deepseek-r1-0528` | Latest reasoning |
-| `deepseek-v3` | General-purpose |
-| `deepseek-v3-250324` | Latest general |
-
 ### xAI Grok
 
 | Model | Best For |
@@ -192,10 +184,10 @@ POST /v1/chat/completions
 
 ## Stateful Conversations Endpoint
 
-For stateful, session-based chat (no need to send the full history each time), use the `/aichat/conversations` endpoint:
+For stateful, session-based chat (no need to send the full history each time), use `POST /aichat2/conversations` (recommended). `POST /aichat/conversations` remains available for legacy compatibility.
 
 ```bash
-curl -X POST https://api.acedata.cloud/aichat/conversations \
+curl -X POST https://api.acedata.cloud/aichat2/conversations \
   -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
   -H "Content-Type: application/json" \
   -d '{"model": "gpt-4.1", "question": "What is quantum computing?", "stateful": true}'

package/skills/flux-image/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: flux-image
-description: Generate and edit images with Flux (Black Forest Labs) via AceDataCloud API. Use when creating images from text prompts, editing existing images with text instructions, or when high-quality image generation is needed. Supports multiple Flux models including dev, pro, ultra, and kontext for editing.
+description: Generate and edit images with Flux (Black Forest Labs) via AceDataCloud API. Use when creating images from text prompts, editing existing images with text instructions, or when high-quality image generation is needed. Supports multiple Flux models including dev, pro, Flux 2 variants, and kontext for editing.
 license: Apache-2.0
 metadata:
   author: acedatacloud
@@ -23,7 +23,7 @@ curl -X POST https://api.acedata.cloud/flux/images \
   -d '{"prompt": "a cat wearing a space helmet, photorealistic", "model": "flux-dev", "callback_url": "https://api.acedata.cloud/health"}'
 ```
 
-> **Async:** See [async task polling](../_shared/async-tasks.md). Poll via `POST /flux/tasks` with `{"task_id": "..."}`.
+> **Async:** See [async task polling](../_shared/async-tasks.md). Poll via `POST /flux/tasks` with `{"id": "..."}`.
 
 ## Models
 
@@ -31,8 +31,9 @@ curl -X POST https://api.acedata.cloud/flux/images \
 |-------|---------|-------|-------|----------|
 | `flux-dev` | Good | Fast | 256–1440px | Quick generation (default) |
 | `flux-pro` | High | Medium | 256–1440px | Production work |
-| `flux-pro-1.1` | Higher | Medium | 256–1440px | Better prompt following |
-| `flux-pro-1.1-ultra` | Highest | Slow | Aspect ratios | Maximum quality |
+| `flux-2-flex` | High | Fast | 256–1440px | Faster high-quality generation |
+| `flux-2-pro` | Higher | Medium | 256–1440px | Better prompt following |
+| `flux-2-max` | Highest | Slow | 256–1440px | Maximum quality generation |
 | `flux-kontext-pro` | High | Medium | Aspect ratios | Image editing |
 | `flux-kontext-max` | Highest | Slow | Aspect ratios | Complex editing |
 
@@ -43,7 +44,7 @@ POST /flux/images
 {
   "prompt": "a minimalist logo of a mountain",
   "action": "generate",
-  "model": "flux-pro-1.1",
+  "model": "flux-2-pro",
   "size": "1024x1024",
   "count": 1
 }
@@ -51,10 +52,10 @@ POST /flux/images
 
 ### Size Options
 
-**For dev/pro/pro-1.1** (pixel dimensions):
+**For dev/pro/flux-2** (pixel dimensions):
 - `"1024x1024"`, `"1344x768"`, `"768x1344"`, `"1024x576"`, `"576x1024"`
 
-**For ultra/kontext** (aspect ratios):
+**For kontext** (aspect ratios):
 - `"1:1"`, `"16:9"`, `"9:16"`, `"4:3"`, `"3:4"`, `"3:2"`, `"2:3"`, `"21:9"`, `"9:21"`
 
 ## Edit Images
@@ -73,10 +74,10 @@ POST /flux/images
 
 ## Gotchas
 
-- Use pixel dimensions (e.g., `"1024x1024"`) with dev/pro models, aspect ratios (e.g., `"16:9"`) with ultra/kontext models
+- Use pixel dimensions (e.g., `"1024x1024"`) with dev/pro/flux-2 models, aspect ratios (e.g., `"16:9"`) with kontext models
 - Editing requires kontext models (`flux-kontext-pro` or `flux-kontext-max`) — other models only support generation
 - `count` parameter generates multiple images in one request (increases cost proportionally)
-- Ultra model produces highest quality but is slowest — use dev for iteration, ultra for final output
-- All generation is async — always set `"callback_url"` to get a `task_id` immediately, then poll `/flux/tasks`
+- `flux-2-max` produces highest quality but is slowest — use dev/flex for iteration and max for final output
+- All generation is async — always set `"callback_url"` to get a task id immediately, then poll `/flux/tasks` using `{"id":"<task_id>"}` or `{"ids":[...],"action":"retrieve_batch"}`
 
 > **MCP:** `pip install mcp-flux-pro` | Hosted: `https://flux.mcp.acedata.cloud/mcp` | See [all MCP servers](../_shared/mcp-servers.md)

package/skills/google-gmail/SKILL.md

@@ -132,9 +132,17 @@ curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \
   --get "https://gmail.googleapis.com/gmail/v1/users/me/messages" \
   --data-urlencode 'q=is:unread in:inbox newer_than:7d' \
   --data-urlencode 'maxResults=20' \
-  | jq '.messages[]'
+  | jq '.messages // [] | .[]'
 ```
 
+**Always default `.messages` to `[]`** — Gmail's `messages.list` omits the
+field entirely when there are zero matches (the response is just
+`{"resultSizeEstimate": 0}`), so a bare `.messages[]` will crash jq
+with `Cannot iterate over null (null)` and exit 5. Same applies to
+`.threads`, `.labels`, `.drafts` on their list endpoints. If the result
+is empty, tell the user plainly (e.g. "No unread mail in the last 7
+days") instead of retrying.
+
 The `messages.list` endpoint returns only `{id, threadId}` — you have
 to fan out to `messages.get` for headers / body. Cheap pattern: list
 ids → get with `format=metadata&metadataHeaders=From,Subject,Date` for
@@ -147,8 +155,10 @@ IDS=$(curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \
   --get "https://gmail.googleapis.com/gmail/v1/users/me/messages" \
   --data-urlencode 'q=is:unread in:inbox' \
   --data-urlencode 'maxResults=10' \
-  | jq -r '.messages[].id')
+  | jq -r '.messages // [] | .[].id')
 
+# If $IDS is empty the for-loop below runs zero times — tell the user
+# "no unread mail" rather than echoing an empty result.
 for ID in $IDS; do
   curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \
     --get "https://gmail.googleapis.com/gmail/v1/users/me/messages/$ID" \
@@ -195,7 +205,7 @@ curl -sS -H "Authorization: Bearer $GOOGLE_GMAIL_TOKEN" \
   --data-urlencode 'metadataHeaders=From' \
   --data-urlencode 'metadataHeaders=Subject' \
   --data-urlencode 'metadataHeaders=Date' \
-  | jq '{id, historyId, messages: [.messages[] | {id, snippet, from: (.payload.headers | from_entries.From), date: (.payload.headers | from_entries.Date)}]}'
+  | jq '{id, historyId, messages: [(.messages // [])[] | {id, snippet, from: (.payload.headers | from_entries.From), date: (.payload.headers | from_entries.Date)}]}'
 ```
 
 ### Search by Gmail query

package/skills/suno-music/SKILL.md

@@ -23,7 +23,7 @@ curl -X POST https://api.acedata.cloud/suno/audios \
   -d '{"prompt": "a happy pop song about coding", "model": "chirp-v5-5", "callback_url": "https://api.acedata.cloud/health"}'
 ```
 
-> **Async:** All generation is async. See [async task polling](../_shared/async-tasks.md). Poll via `POST /suno/tasks` with `{"task_id": "..."}` every 3-5 seconds.
+> **Async:** All generation is async. See [async task polling](../_shared/async-tasks.md). Poll via `POST /suno/tasks` with `{"id": "<task_id>"}` every 3-5 seconds.
 
 ## Available Models
 
@@ -103,7 +103,7 @@ For best results follow this multi-step workflow:
 1. **Generate lyrics** — `POST /suno/lyrics` with a topic/prompt
 2. **Optimize style** — `POST /suno/style` to refine style description
 3. **Generate music** — `POST /suno/audios` with custom action, lyrics + style
-4. **Poll task** — `POST /suno/tasks` with task_id until status is complete
+4. **Poll task** — `POST /suno/tasks` with `id` (or `ids` for batch) until status is complete
 5. **Optional: Extend** — Use extend action to add more sections
 6. **Optional: Concat** — Use concat action to merge extended segments
 7. **Optional: Convert** — Get WAV (`/suno/wav`), MIDI (`/suno/midi`), or MP4 (`/suno/mp4`)
@@ -149,7 +149,7 @@ For best results follow this multi-step workflow:
 
 | Parameter | Type | Description |
 |-----------|------|-------------|
-| `lyric_prompt` | string | Prompt for auto-generating lyrics (used when `custom: true` without explicit `lyric`) |
+| `lyric_prompt` | object | Structured prompt payload for auto-generating lyrics (used when `custom: true` without explicit `lyric`) |
 | `style_negative` | string | Style tags to avoid (e.g., `"heavy metal, distortion"`) |
 | `style_influence` | number | Strength of style influence (advanced custom mode, v5+ only) |
 | `audio_weight` | number | Weight for audio reference when covering (advanced, v5+ only) |
@@ -174,7 +174,7 @@ Ending lyrics
 
 ## Gotchas
 
-- All generation is **async** — always set `"callback_url"` to get a `task_id` immediately, then poll `/suno/tasks`
+- All generation is **async** — always set `"callback_url"` to get a task id immediately, then poll `/suno/tasks` using `{"id":"<task_id>"}` or `{"ids":[...],"action":"retrieve_batch"}`
 - **CRITICAL:** Check the `state` field — only `state: "complete"` with `success: true` means done. During `pending`, the API may return intermediate `audio_url` values (streaming previews). Do NOT stop polling just because `audio_url` is non-empty
 - Lyrics max ~3000 characters. For longer songs, use the **extend** workflow
 - Style tags are descriptive phrases, not enum values (e.g., "Synthwave, Electronic, Dreamy")