mediause/agent-skills/xiaohongshu/SKILL.md
xiaohongshu
Standardized Xiaohongshu skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full Xiaohongshu dynamic command map, and safety/rate controls.
- Source repository stars
- 9
- Declared platforms
- 0
- Static risk flags
- 2
- Last source update
- 2026-07-28
- Source checked
- 2026-07-28
Decision brief
What it does—and where it fits
Create and operate Xiaohongshu content workflows with consistent setup, context handling, command execution, and compliance guardrails.
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/mediause/agent-skills --skill "xiaohongshu"Inspect the Agent Skill "xiaohongshu" from https://github.com/mediause/agent-skills/blob/766e5075b28b3acd541436a7e3b3e21cdc38da01/xiaohongshu/SKILL.md at commit 766e5075b28b3acd541436a7e3b3e21cdc38da01. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
3.1 Discover and plugin setup
Review the “3.1 Discover and plugin setup” section in the pinned source before continuing.
Review and apply the “3.1 Discover and plugin setup” source section. - 02
6. Workflow Examples
Review the “6. Workflow Examples” section in the pinned source before continuing.
Review and apply the “6. Workflow Examples” source section. - 03
always run once before each workflow (auto-upgrade latest)
powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex" mediause --version
powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex" mediause --version - 04
Scope
Use this skill when the task targets Xiaohongshu operations such as:
Publish: feed, repost, note boostRead: feed, detail, notificationsUser: profile, profile update, user feed, followers, following - 05
1. Install MediaUse CLI (Windows Only)
Use the official install script for Windows:
https://release.mediause.dev/install.ps1Before every run, execute the install script once to auto-install or auto-upgrade to the latest MediaUse CLI.Windows: supported
Permission review
Static risk signals and limitations
Runs scripts
The documentation asks the agent to run terminal commands or scripts.
Before every run, execute the install script once to auto-install or auto-upgrade to the latest MediaUse CLI.Network access
The documentation includes network, browsing, or remote request actions.
powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex"Runs scripts
The documentation asks the agent to run terminal commands or scripts.
First step on every run: execute install script once to auto-install/auto-upgrade the latest MediaUse CLI.Network access
The documentation includes network, browsing, or remote request actions.
powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex"Evidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 77/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 9 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- mediause/agent-skills
- Skill path
- xiaohongshu/SKILL.md
- Commit
- 766e5075b28b3acd541436a7e3b3e21cdc38da01
- License
- Not declared
- Collected
- 2026-07-28
- Default branch
- master
View the original SKILL.md
MediaUse Xiaohongshu Skill
Create and operate Xiaohongshu content workflows with consistent setup, context handling, command execution, and compliance guardrails.
Scope
Use this skill when the task targets Xiaohongshu operations such as:
- Publish: feed, repost, note boost
- Read: feed, detail, notifications
- User: profile, profile update, user feed, followers, following
- Reply: comment, sub-comment, private message
- Search: text, user, hot topics
- Engage: like, follow, collect
- Management/trace: manage task, trace last
1. Install MediaUse CLI (Windows Only)
Use the official install script for Windows:
-
https://release.mediause.dev/install.ps1 Mandatory update rule:
-
Before every run, execute the install script once to auto-install or auto-upgrade to the latest MediaUse CLI.
Run:
powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex"
Then verify :
mediause --version
Current support status:
- Windows: supported
- Linux: not supported yet
- macOS: not supported yet
Recommended skill install path:
- .mediause/skills/xiaohongshu/SKILL.md
2. Get and Configure MediaUse Key
2.1 Apply for key
- Open https://mediause.dev/
- Sign in to your account.
- Open Project.
- Create or copy your API key.
2.2 Configure key in CLI
mediause manage key <your_key> --json
3. Core Flow (Mandatory Order)
Always follow this order:
First step on every run: execute install script once to auto-install/auto-upgrade the latest MediaUse CLI.
- Discover site and commands.
- Bind account context with
use account. - Check status with
auth health. - Execute dynamic site actions.
- Verify with trace/task.
3.1 Discover and plugin setup
mediause sites list --json
mediause sites add xiaohongshu --json
mediause xiaohongshu -h
mediause xiaohongshu post -h
3.2 Bind context before any read/write
use account must be executed successfully before any fetch/publish action.
use account argument format:
<platform:account_id>account_idshould be selected frommediause auth list --json.
mediause auth list --json
mediause use account xiaohongshu:<account_id> --policy balanced --json
If challenge/risk prompts appear, reopen in visible mode:
mediause use account xiaohongshu:<account_id> --policy balanced --show --json
--show usually lowers repeated interception risk in challenged sessions.
3.3 Auth health precondition
auth health is valid only after successful use account.
mediause auth health --json
If auth health indicates not logged in/expired:
mediause auth login xiaohongshu --json
mediause use account xiaohongshu:<account_id> --policy balanced --json
mediause auth health --json
3.4 Guest mode (optional, site-dependent)
If guest mode is supported by the current CLI/site runtime:
mediause use account xiaohongshu:guest --json
Guest mode rules:
- Read-only (fetch/search/get/user read operations).
- Block all write operations (post/reply/engage/manage/note write intent).
- If write is required, switch to logged-in account context.
4. Xiaohongshu Dynamic Command Map (v1)
Source schema:
- plugin:
plugin.xiaohongshu - schema version:
v1 - supported layer:
L3Bridge
4.1 post.*
post feeduses only one media argument:--media, which covers both image and video file paths.mediause xiaohongshu post feed [--title <text>] [--text <text>] [--media <paths>] [--cover <cover_path>] --jsonmediause xiaohongshu post repost --id <post_id> [--text <text>] --json
4.2 get.*
mediause xiaohongshu get feed [--limit <n>] [--type <type>] --jsonmediause xiaohongshu get detail --id <item_id> [--comments <bool>] --jsonmediause xiaohongshu get notif [--type <type>] --json
4.3 user.*
mediause xiaohongshu user profile [--me <bool>] [--user-id <uid>] --jsonmediause xiaohongshu user profile-update [--bio <text>] [--name <text>] [--avatar <path>] --jsonmediause xiaohongshu user feed --user-id <uid> [--limit <n>] [--type <type>] --jsonmediause xiaohongshu user followers --user-id <uid> [--limit <n>] --jsonmediause xiaohongshu user following --user-id <uid> [--limit <n>] --json
4.4 reply.*
mediause xiaohongshu reply comment --post-id <post_id> --text <text> --jsonmediause xiaohongshu reply sub --comment-id <comment_id> --text <text> --jsonmediause xiaohongshu reply message --user-id <uid> --text <text> --json
4.5 search.*
mediause xiaohongshu search text --keyword <keyword> [--limit <n>] --jsonmediause xiaohongshu search user --query <query> [--limit <n>] --jsonmediause xiaohongshu search hot --json
4.6 engage.*
mediause xiaohongshu engage like --id <item_id> [--type <type>] --jsonmediause xiaohongshu engage follow --user-id <uid> [--undo <bool>] --jsonmediause xiaohongshu engage collect --id <item_id> --json
4.7 manage.*
mediause xiaohongshu manage task [--task <task_name>] [--note-id <note_id>] --json
4.8 trace.*
mediause xiaohongshu trace last --json
4.9 note.*
mediause xiaohongshu note boost --note-id <note_id> --json
5. Operational Constraints (Mandatory)
Apply these constraints for all actions to reduce account risk and keep behavior human-like.
5.1 Human-like pacing
- Never execute high-risk actions continuously.
- Add randomized delay between actions.
- Add longer cooldown after publish/profile-change actions.
- Mix read actions between write actions when possible.
5.2 Frequency limits and minimum spacing
- Hard stop if operation rate is abnormally high.
- Stop immediately on repeated anti-bot challenge, login re-validation, or risk prompt.
- Do not run burst publish loops.
Suggested limits:
- Publish/manage/note boost: <= 3 per hour
- Reply/message: <= 20 per hour
- Follow/like/collect: <= 30 per hour
- Search/read: <= 60 per minute
Minimum spacing:
- Publish/manage/note boost: >= 20 minutes between actions
- Reply/message: >= 30 seconds between actions
- Follow/like/collect: >= 10 seconds between actions
- Read/search/get/user read/trace: >= 1 second between actions
Same-target guardrails:
- Repeated interaction on same target (same post_id/note_id/user_id): >= 60 seconds
- Repeated identical publish text: >= 24 hours (default deny)
Suggested soft limits per account 10-minute window:
- High-risk actions: <= 3 in 10 minutes
- Medium-risk actions: <= 8 in 10 minutes
- Low-risk actions: <= 20 in 10 minutes
If a limit is hit:
- Pause at least 15 minutes.
- Resume with read-only actions first.
- Re-check session health before any write action.
5.3 Safety policy
- Do not bypass platform protections.
- Do not attempt credential scraping or session hijacking.
- Respect platform terms and local regulations.
5.4 Output and error handling
- Prefer
--jsonoutput for machine workflows. - Require structured error handling with stable fields/code when available.
- On blocked/rate-limit/risk prompt, stop and return actionable next steps.
6. Workflow Examples
6.1 Hot-topic to publish
mediause use account xiaohongshu:<account_id> --json
mediause auth health --json
mediause xiaohongshu search hot --json
mediause xiaohongshu post feed --title "浠婃棩鎺ㄨ崘" --text "<draft_text>" --media c:/tmp/a.png,c:/tmp/b.png --json
mediause trace last --json
6.1.1 Video publish with cover
mediause use account xiaohongshu:<account_id> --json
mediause auth health --json
mediause xiaohongshu post feed --title "2026绌挎惌" --text "浠婃棩鍒嗕韩" --media c:/tmp/a.mp4 --cover c:/tmp/cover.png --json
mediause trace last --json
6.1.2 Long article publish
mediause use account xiaohongshu:<account_id> --json
mediause auth health --json
mediause xiaohongshu post feed --title "2026绌挎惌" --text "浠婃棩鍒嗕韩" --json
mediause trace last --json
6.2 Monitor and engage
mediause use account xiaohongshu:<account_id> --json
mediause auth health --json
mediause xiaohongshu get notif --type mention --json
mediause xiaohongshu reply comment --post-id <id> --text "received" --json
mediause trace last --json
6.3 Note boost flow
mediause use account xiaohongshu:<account_id> --json
mediause auth health --json
mediause xiaohongshu note boost --note-id <note_id> --json
mediause xiaohongshu manage task --task note.boost --note-id <note_id> --json
mediause trace last --json
6.4 Read-only guest branch (if supported)
mediause use account xiaohongshu:guest --json
mediause xiaohongshu search hot --json
mediause xiaohongshu get feed --limit 20 --json
mediause trace last --json
7. Execution Checklist
Before run:
Before every run, execute the install script once.
- CLI installed via
https://release.mediause.dev/install.ps1on Windows. - PATH updated and
mediause --versionworks. - API key configured and verified.
- Account context bound via
mediause use account <platform:account_id>. mediause auth health --jsonchecked after context bind.- If not logged in, run
mediause auth login xiaohongshu --jsonand re-bind context. - Pacing policy is enabled.
During run:
- Respect risk-based delays and minimum spacing.
- Stop on anti-bot/risk prompts.
- Avoid repetitive write-action bursts.
- In guest mode, allow read-only actions only.
After run:
- Save logs and outcomes.
- Record any risk warning and cooldown events.
- Keep account activity under conservative limits.
8. Quick Command Reference
# always run once before each workflow (auto-upgrade latest)
powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex"
mediause --version
# discover
mediause sites list --json
mediause sites add xiaohongshu --json
mediause xiaohongshu -h
mediause xiaohongshu post -h
# context + status
mediause auth list --json
mediause use account xiaohongshu:<account_id> --json
mediause auth health --json
# read action
mediause xiaohongshu search hot --json
# write action
mediause xiaohongshu post feed --title "hello" --text "hello" --json
# trace
mediause trace last --json
Skill Metadata Maintainer: @mediause-demo Last-Updated: 2026-05-21 Version: v1
Alternatives
Compare before choosing
affaan-m/ECC
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
K-Dense-AI/scientific-agent-skills
simpy
Build, inspect, test, and analyze bounded process-based discrete-event simulations with SimPy, including events, resources, interrupts, monitoring, replications, warm-up, and reproducible output analysis.
JasonColapietro/suede-creator-skills
suede-code-grader
Give a blunt A-F ship grade for a code change across correctness, security, data, UX, verification, and deploy readiness. Use for a grade, not a findings review.
event4u-app/agent-config
terragrunt
Use when working with Terragrunt — DRY multi-env configs, module dependencies, remote state orchestration — even when the user just says 'deploy this to staging and prod' without naming Terragrunt.