modelscope skill
scriptsManage ModelScope account information and save article drafts using direct HTTP requests and login cookies.
- GitHub stars
- 17
- Files
- 4
- Last commit
- Nov 9, 2026
- License
- Apache-2.0
- Allowed tools
- 1
What does the modelscope skill do?
modelscope manages ModelScope account information and save article drafts using direct HTTP requests and login cookies.
Summary generated from the skill's SKILL.md.
About the modelscope skill
Managing ModelScope account details and preparing article drafts through direct HTTP requests is what this skill enables. Developers and content creators use it to interact with the 魔搭社区 platform without needing a local browser or a paired browser instance. The skill utilizes a bundled Python script that communicates with web endpoints using cookies provided through the MODELSCOPE_COOKIES connection.
An agent should load this skill when it needs to inspect account information or save text to a draft. It relies on the Bash tool to execute the modelscope.py script located in the SKILL_DIR. Users can generate local previews of their content by running the draft command without the --confirm flag, ensuring the content is correct before any network or cookie access occurs. The tool is specifically designed for article preparation and does not support uploading models, datasets, or Spaces.
What an agent can do with it
- 1Inspect account informationCheck the current logged-in user status on the ModelScope platform.
- 2Save content draftsSubmit an article title and content file to the platform to create a draft.
- 3Format native editor contentSubmit content using native editor JSON formatting instead of plain text.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the modelscope skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the modelscope skill in Plugin
/plugin marketplace add AceDataCloud/Skills /plugin install acedatacloud-content@acedatacloud-skills
Install the modelscope skill in Claude Code
~/.claude/skills/modelscope/SKILL.md
$ npx degit AceDataCloud/Skills/skills/modelscope ~/.claude/skills/modelscopeInstall the modelscope skill in Claude Code (project)
.claude/skills/modelscope/SKILL.md
$ npx degit AceDataCloud/Skills/skills/modelscope .claude/skills/modelscopeInstall the modelscope skill in Codex
~/.agents/skills/modelscope/SKILL.md
$ npx degit AceDataCloud/Skills/skills/modelscope ~/.agents/skills/modelscopeInstall the modelscope skill in Gemini CLI
~/.gemini/skills/modelscope/SKILL.md
$ npx degit AceDataCloud/Skills/skills/modelscope ~/.gemini/skills/modelscopeInstall the modelscope skill in Claude.ai
npx degit AceDataCloud/Skills/skills/modelscope modelscope && zip -r modelscope.zip modelscope # claude.ai → Customize → Skills → + → Create skill → Upload a skill → modelscope.zip
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A skill needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableacedatacloud/skills/skills/modelscope is public and reachablegithub.com/acedatacloud/skills/tree/HEAD/skills/modelscope ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-09github.com/acedatacloud/skills/commits ↗Pass
- No download-and-run or credential theft in scripts2 scripts read; no download-and-run, remote eval, base64 execution or credential uploadPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/acedatacloud/skills/blob/HEAD/skills/modelscope/S ↗Pass
- Pre-approved tools are scopedBash lets the agent run any shell command without askinggithub.com/acedatacloud/skills/blob/HEAD/skills/modelscope/S ↗Finding
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 44 linesgithub.com/acedatacloud/skills/blob/HEAD/skills/modelscope/S ↗Pass
SKILL.md
View on GitHub魔搭社区 over HTTP
The connector injects MODELSCOPE_COOKIES as a JSON cookie array. Never print it.
Use this bundled Python standard-library client. It talks directly to the platform's web endpoints; no local browser or browser fallback runs during execution. Login cookies are initially captured by the ACE extension and encrypted in the connection vault.
python3 "$SKILL_DIR/scripts/modelscope.py" whoami
python3 "$SKILL_DIR/scripts/modelscope.py" draft --title "标题" --content-file /tmp/article.txt
python3 "$SKILL_DIR/scripts/modelscope.py" draft --title "标题" --content-file /tmp/article.txt --confirm
SKILL_DIR belongs to the most recently loaded skill. When switching back to this platform after loading another skill, load this skill again and immediately invoke its client through SKILL_DIR. Do not search shared cache directories for a script: they can contain older bundles.
Without trailing --confirm, writes only build a local preview: no cookies or network are accessed. Use --confirm only when the user's request authorizes that exact content, account and action. The script does not infer public-publication permission from a draft request.
Platform contract
The available create endpoint accepts ContentDraft only. It saves the body; it does not save the article title. Results explicitly return title_saved=false and the requested title for completion in the editor. Default text input creates literal paragraphs; for formatting use native content with --format native. This is not a model/dataset/Spaces upload skill.
Content and outcomes
- Preserve the complete article. The client does not re-host images or fetch external media. Use already hosted images and verify them in the editor; do not silently strip an image or change the content to make a request pass.
- The default input format is
text. Plain text does not render Markdown. Native editor JSON must be prepared explicitly and checked against the source before submission. - Account lookup must succeed before a write. A timeout, non-JSON/WAF page, missing result ID or business error stops the flow. Never retry a write through another route/browser automatically; inspect the original item first.
- Responses expose only selected account/result fields. Raw errors, CSRF tokens and cookies are never printed. HTTP 403 can mean WAF or account restrictions, not necessarily expiry. Reconnect at https://studio.acedata.cloud/console/connectors when login is invalid.
- A successful save response is not independent readback. Results include
readback_verified=false; inspect/reopen the returned item before claiming the complete text persisted. No HTTP public publication is implemented. - Do not call
publish_artifactas delivered for a draft or private post.
Protocol evidence
Request/response contracts inspected in MediaSync. The Python implementation is independent; no GPL source is bundled. Offline tests verify the wire contract and failure handling, not current live-account publishing access.
Files in this skill
4modelscope skill questions
How do I install the modelscope skill in Claude Code?
Run npx degit AceDataCloud/Skills/skills/modelscope ~/.claude/skills/modelscope. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the modelscope skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
Does this skill require a web browser to run?
No, it uses a bundled Python client to talk directly to web endpoints without needing a local browser.
How can I ensure my article draft is actually saved correctly?
A successful response does not guarantee a perfect readback; you should inspect and reopen the returned item to verify the text persisted.
Can I use Markdown directly in the draft content?
The default text input does not render Markdown; you must use native content formatting to ensure proper rendering.
Does the draft tool save the article title?
No, the create endpoint only saves the body content and returns the requested title for manual completion in the editor.