@acedatacloud/skills 2026.728.0 → 2026.728.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@acedatacloud/skills",
-  "version": "2026.728.0",
+  "version": "2026.728.1",
   "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/bilibili/SKILL.md

@@ -54,7 +54,7 @@ Stats come straight from Bilibili: `view` (阅读), `like` (点赞), `reply` (
 ```sh
 BILI="$SKILL_DIR/scripts/bilibili.py"; [ -f "$BILI" ] || BILI=$(find /tmp -maxdepth 8 -path '*/skills/*/scripts/bilibili.py' 2>/dev/null | head -1)
 python3 "$BILI" whoami
-# → {"mid": 91207595, "name": "...", "level": 4}
+# → {"mid": 10000000, "name": "...", "level": 4}
 ```
 
 On a not-logged-in / auth error the cookie is expired — have the user reconnect

package/skills/csdn/SKILL.md

@@ -53,7 +53,7 @@ Stats come straight from CSDN: `view_count` (阅读), `digg_count` (点赞),
 ```sh
 CSDN="$SKILL_DIR/scripts/csdn.py"; [ -f "$CSDN" ] || CSDN=$(find /tmp -maxdepth 8 -path '*/skills/*/scripts/csdn.py' 2>/dev/null | head -1)
 python3 "$CSDN" whoami
-# → {"username": "...", "nickname": "...", "articles_total": 1597}
+# → {"username": "...", "nickname": "...", "articles_total": 0}
 ```
 
 On a WAF 403 / auth error the cookie is expired — tell the user to reconnect at

package/skills/discord/SKILL.md

@@ -63,15 +63,15 @@ python3 scripts/discord_user.py whoami
 # list the servers (guilds) the account is in
 python3 scripts/discord_user.py guilds
 # list text channels in a server
-python3 scripts/discord_user.py channels --guild 1133012399448928276
+python3 scripts/discord_user.py channels --guild GUILD_ID
 # read recent messages in a channel
-python3 scripts/discord_user.py messages --channel 1133012400174534792 --limit 20
+python3 scripts/discord_user.py messages --channel CHANNEL_ID --limit 20
 # send — dry-run first, then re-run with a trailing --confirm
-python3 scripts/discord_user.py send --channel 1133012400174534792 --text "hello"
-python3 scripts/discord_user.py send --channel 1133012400174534792 --text "hello" --confirm
+python3 scripts/discord_user.py send --channel CHANNEL_ID --text "hello"
+python3 scripts/discord_user.py send --channel CHANNEL_ID --text "hello" --confirm
 # reply to a specific message
 python3 scripts/discord_user.py reply \
-  --channel 1133012400174534792 --message 987654321098765432 --text "on it" --confirm
+  --channel CHANNEL_ID --message MESSAGE_ID --text "on it" --confirm
 ```
 
 `--confirm` is honored ONLY as the final argument (one strip), so a message body

package/skills/discord/scripts/discord_user.py

@@ -17,10 +17,10 @@ account access — NEVER echo or print it.
 Examples:
   python3 discord_user.py whoami
   python3 discord_user.py guilds
-  python3 discord_user.py channels --guild 1133012399448928276
-  python3 discord_user.py messages --channel 1133012400174534792 --limit 20
-  python3 discord_user.py send --channel 1133012400174534792 --text "hello" --confirm
-  python3 discord_user.py reply --channel 1133012400174534792 --message 987654321 --text "on it" --confirm
+  python3 discord_user.py channels --guild GUILD_ID
+  python3 discord_user.py messages --channel CHANNEL_ID --limit 20
+  python3 discord_user.py send --channel CHANNEL_ID --text "hello" --confirm
+  python3 discord_user.py reply --channel CHANNEL_ID --message MESSAGE_ID --text "on it" --confirm
 """
 
 from __future__ import annotations

package/skills/google-gmail/SKILL.md

@@ -383,7 +383,7 @@ BODY='Hi Alice,
 Just a quick test note from the AceDataCloud Gmail connector.
 
 Best,
-Qingcai'
+YOUR_NAME'
 
 # Multi-line subject lines need MIME encoded-word for non-ASCII; ASCII is fine raw.
 RAW=$(printf 'To: %s\r\nSubject: %s\r\nContent-Type: text/plain; charset=UTF-8\r\nMIME-Version: 1.0\r\n\r\n%s' \

package/skills/juejin/SKILL.md

@@ -47,7 +47,7 @@ Stats come straight from 掘金: `view_count` (阅读), `digg_count` (点赞),
 ```sh
 JJ="$SKILL_DIR/scripts/juejin.py"; [ -f "$JJ" ] || JJ=$(find /tmp -maxdepth 8 -path '*/skills/*/scripts/juejin.py' 2>/dev/null | head -1)
 python3 "$JJ" whoami
-# → {"user_id": "...", "name": "...", "post_article_count": 336}
+# → {"user_id": "...", "name": "...", "post_article_count": 0}
 ```
 
 On an auth error (`err_no` 401 / "请登录") the cookie is expired — have the user

package/skills/mastodon/SKILL.md

@@ -64,7 +64,7 @@ curl -sS -X POST "$MASTODON_BASE_URL/api/v1/statuses" \
 Use the `id` from `verify_credentials`:
 
 ```bash
-ACCT_ID="14715"   # from verify_credentials
+ACCT_ID="ACCOUNT_ID"   # from verify_credentials
 curl -sS "$MASTODON_BASE_URL/api/v1/accounts/$ACCT_ID/statuses?limit=20&exclude_replies=true&exclude_reblogs=true" \
   -H "Authorization: Bearer $MASTODON_ACCESS_TOKEN" \
   | jq '.[] | {id, url, boosts: .reblogs_count, favs: .favourites_count, replies: .replies_count, created_at}'

package/skills/personal-wechat/SKILL.md

@@ -98,7 +98,7 @@ python3 $WX conversations --history --limit 20
 First list conversations, then use the `id` as `conversation_id`:
 
 ```bash
-python3 $WX messages "34642176898@chatroom" --limit 50 --order asc
+python3 $WX messages "CONVERSATION_ID" --limit 50 --order asc
 ```
 
 ### Historical Messages
@@ -107,7 +107,7 @@ Read from Wisdom's decrypted WeChat local databases:
 
 ```bash
 python3 $WX history --limit 50
-python3 $WX history --talker "34642176898@chatroom" --limit 50
+python3 $WX history --talker "CONVERSATION_ID" --limit 50
 python3 $WX history --limit 20 --offset 20
 ```
 

package/skills/telegram/SKILL.md

@@ -51,7 +51,7 @@ last argument** so a message/caption that merely contains "--confirm" can never
 
 ```sh
 python3 "$TG" whoami
-# → {"id": 8367450178, "username": "GermeyAce", "name": "Germey", "phone": "..."}
+# → {"id": 100000000, "username": "<the connected handle>", "name": "<display name>", "phone": "..."}
 ```
 
 On an auth/session error the stored session is dead — tell the user to reconnect at

package/skills/toutiao/SKILL.md

@@ -54,7 +54,7 @@ Stats come straight from 头条: `impression_count` (展现), `read_count` (阅
 ```sh
 TT="$SKILL_DIR/scripts/toutiao.py"; [ -f "$TT" ] || TT=$(find /tmp -maxdepth 8 -path '*/skills/*/scripts/toutiao.py' 2>/dev/null | head -1)
 python3 "$TT" whoami
-# → {"user_id": ..., "name": "...", "articles_total": 273}
+# → {"user_id": ..., "name": "...", "articles_total": 0}
 ```
 
 On an auth error the cookie is expired — tell the user to reconnect at

package/skills/x/SKILL.md

@@ -50,8 +50,8 @@ python3 "$X" whoami          # confirm the shipped CLI can read the authenticate
 ## Read commands (run directly)
 
 ```sh
-python3 $X whoami --expect GermeyAce                         # verify this exact account
 python3 $X whoami                                            # discover the authenticated account
+python3 $X whoami --expect SCREEN_NAME                       # optional: assert a specific account
 python3 $X search --query "ai agents" --product Latest --limit 20   # Top | Latest | Media
 python3 $X search-users --query "openai" --limit 10
 python3 $X timeline --limit 20                               # my home timeline
@@ -65,19 +65,22 @@ python3 $X trends --category trending --limit 20             # trending|for-you|
 ## Verify the connection first
 
 ```sh
-python3 $X whoami --expect GermeyAce
-# → {"id": "...", "screen_name": "GermeyAce", "identity_verified": true, ...}
+python3 $X whoami
+# → {"id": "...", "screen_name": "<the connected handle>", "identity_verified": true, ...}
 ```
 
 `whoami` reads the authenticated account's screen name from X account settings,
-then resolves its public profile. `--expect` compares that server-authenticated
-screen name with the required account before any write. This avoids X's
-Cloudflare-blocked `UserByRestId` endpoint without trusting a local identity
-cookie. Always use `--expect` when the user names the required account.
+then resolves its public profile. This avoids X's Cloudflare-blocked
+`UserByRestId` endpoint without trusting a local identity cookie.
+
+`--expect <screen_name>` is optional: pass it only when the user explicitly names
+the account they want to act as, and it will abort if the connected cookie
+belongs to someone else. Do not invent an expected handle — plain `whoami` is
+the default.
 
 On an actual auth error the cookie is expired — have the user reconnect at
 <https://auth.acedata.cloud/user/connections>. A Cloudflare block is different:
-reconnecting cookies does not fix it. Use `--expect` for identity checks; other
+reconnecting cookies does not fix it. Use `whoami` for identity checks; other
 blocked endpoints need `X_PROXY` or the official X API. Do **not** loop-retry.
 
 ## Write commands — GATED (dry-run unless trailing `--confirm`)

package/skills/x/scripts/x.py

@@ -19,7 +19,7 @@ breakage.
 
 Examples:
   python3 x.py whoami
-    python3 x.py whoami --expect GermeyAce
+  python3 x.py whoami --expect SCREEN_NAME
   python3 x.py search --query "python" --product Latest --limit 20
   python3 x.py timeline --limit 20
   python3 x.py user-tweets --user elonmusk --type Tweets --limit 20
@@ -107,7 +107,7 @@ def cloudflare_block_message(error: Exception) -> str | None:
     ray = f" Ray ID: {ray_match.group(1)}." if ray_match else ""
     return (
         "X blocked this automated web-API request at Cloudflare; the login cookies may still be valid."
-        f"{ray} For identity checks, use `whoami --expect <screen_name>`; for other blocked endpoints, "
+        f"{ray} For identity checks, use `whoami`; for other blocked endpoints, "
         "configure X_PROXY or use the official X API."
     )
 

package/skills/yuque/SKILL.md

@@ -43,8 +43,8 @@ python3 "$SKILL_DIR/scripts/yuque.py" whoami
 
 # List knowledge bases, then the documents in one.
 python3 "$SKILL_DIR/scripts/yuque.py" repos
-python3 "$SKILL_DIR/scripts/yuque.py" docs germey/blog --limit 20
-python3 "$SKILL_DIR/scripts/yuque.py" doc germey/blog DOC_ID
+python3 "$SKILL_DIR/scripts/yuque.py" docs REPO_NAMESPACE --limit 20
+python3 "$SKILL_DIR/scripts/yuque.py" doc REPO_NAMESPACE DOC_ID
 ```
 
 ## Create and update
@@ -55,18 +55,18 @@ by default and only publishes publicly with an explicit `--public`.
 
 ```bash
 # First call is always a dry run and does not load credentials or call the API.
-python3 "$SKILL_DIR/scripts/yuque.py" create germey/blog \
+python3 "$SKILL_DIR/scripts/yuque.py" create REPO_NAMESPACE \
   --title "标题" --content-file /tmp/article.md
 
 # Create it privately after the user confirms.
-python3 "$SKILL_DIR/scripts/yuque.py" create germey/blog \
+python3 "$SKILL_DIR/scripts/yuque.py" create REPO_NAMESPACE \
   --title "标题" --content-file /tmp/article.md --confirm
 
 # Public publishing additionally requires --public.
-python3 "$SKILL_DIR/scripts/yuque.py" create germey/blog \
+python3 "$SKILL_DIR/scripts/yuque.py" create REPO_NAMESPACE \
   --title "标题" --content-file /tmp/article.md --public --confirm
 
-python3 "$SKILL_DIR/scripts/yuque.py" update germey/blog DOC_ID \
+python3 "$SKILL_DIR/scripts/yuque.py" update REPO_NAMESPACE DOC_ID \
   --title "新标题" --content-file /tmp/article.md --public --confirm
 ```
 
@@ -81,7 +81,7 @@ first if the user only wants part of it changed.
 ## Delete
 
 ```bash
-python3 "$SKILL_DIR/scripts/yuque.py" delete germey/blog DOC_ID --confirm
+python3 "$SKILL_DIR/scripts/yuque.py" delete REPO_NAMESPACE DOC_ID --confirm
 ```
 
 Use the real returned `doc_id` and URL. Do not retry a timed-out write

package/skills/zhihu/SKILL.md

@@ -138,7 +138,7 @@ python3 "$BLOG" question <question-id>     # a question's info + whether I answe
 ```sh
 ZDIR="$SKILL_DIR"; [ -f "$ZDIR/scripts/blog.py" ] || ZDIR=$(find /tmp -maxdepth 8 -path '*/skills/*/scripts/blog.py' 2>/dev/null | head -1 | sed 's#/scripts/blog.py##')
 python3 "$ZDIR/scripts/blog.py" whoami
-# → {"id": "...", "name": "崔庆才丨静觅", "url_token": "Germey", ...}
+# → {"id": "...", "name": "<the connected display name>", "url_token": "<the connected handle>", ...}
 ```
 
 On a `401`/`403` the cookie is expired — tell the user to reconnect at