Skip to content

mediause/agent-skills / weibov2

weibov2

Verified

Standardized weibov2 skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full weibov2 dynamic command map, and safety/rate controls.

MediaUse weibov2 Skill

Execute weibov2 social workflows with guided auth context, dynamic command routing, and safe pacing controls.

Scope

Use this skill when the task targets weibov2 operations such as:

  • Publish: feed, repost
  • 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

1. Install MediaUse CLI

Install the MediaUse CLI in the user's own secure environment using the official npm package:

npm install -g @mediause/cli
mediause --version

If the CLI is already installed, run the version check again to confirm it is available in PATH.

Current support status:

  • Windows: supported
  • Linux: not supported yet
  • macOS: not supported yet

Recommended skill install path:

  • .mediause/skills/weibov2/SKILL.md

2. Get and Configure MediaUse Key

2.1 Apply for key

  1. Open https://mediause.dev/ in the user's browser.
  2. Sign in to the user's account.
  3. Open the Project settings.
  4. Create or view the API key in the user's own secure environment; never paste it into chat, logs, terminal history, or a CLI command.

2.2 Configure key in CLI

mediause manage 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.

  1. Discover site and commands.
  2. Bind account context with use account.
  3. Check status with auth health.
  4. Execute dynamic site actions.
  5. Verify with trace/task.

3.1 Discover and plugin setup

mediause plugin list --json
mediause plugin add weibov2 --json
mediause weibov2 -h
mediause weibov2 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_id should be selected from mediause auth list --json.
mediause auth list --json
mediause use account weibov2:<account_id> --policy balanced --json

If challenge/risk prompts appear, reopen in visible mode:

mediause use account weibov2:<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 weibov2 --json
mediause use account weibov2:<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 weibov2:guest --json

Guest mode rules:

  • Read-only (fetch/search/get/user read operations).
  • Block all write operations (post/reply/engage write intent).
  • If write is required, switch to logged-in account context.

4. weibov2 Dynamic Command Map (v1)

Source schema:

  • plugin: plugin.weibov2
  • schema version: v1
  • supported layer: L3Bridge

4.1 post.*

  • mediause weibov2 post feed [--title <text>] [--text <text>] [--media <paths>] --json
  • mediause weibov2 post repost --id <post_id> [--text <text>] --json

4.2 get.*

  • mediause weibov2 get feed [--limit <n>] [--type <type>] --json
  • mediause weibov2 get detail --id <item_id> [--comments <bool>] --json
  • mediause weibov2 get notif [--type <type>] --json

4.3 user.*

  • mediause weibov2 user profile [--me <bool>] [--user-id <uid>] --json
  • mediause weibov2 user profile-update [--bio <text>] [--name <text>] [--avatar <path>] --json
  • mediause weibov2 user feed --user-id <uid> [--limit <n>] [--type <type>] --json
  • mediause weibov2 user followers --user-id <uid> [--limit <n>] --json
  • mediause weibov2 user following --user-id <uid> [--limit <n>] --json

4.4 reply.*

  • mediause weibov2 reply comment --post-id <post_id> --text <text> --json
  • mediause weibov2 reply sub --comment-id <comment_id> --text <text> --json
  • mediause weibov2 reply message --user-id <uid> --text <text> --json

4.5 search.*

  • mediause weibov2 search text --keyword <keyword> [--limit <n>] --json
  • mediause weibov2 search user --query <query> [--limit <n>] --json
  • mediause weibov2 search hot --json

4.6 engage.*

  • mediause weibov2 engage like --id <item_id> [--type <type>] --json
  • mediause weibov2 engage follow --user-id <uid> [--undo <bool>] --json
  • mediause weibov2 engage collect --id <item_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: <= 3 per hour
  • Reply/message: <= 20 per hour
  • Follow/like/collect: <= 30 per hour
  • Search/read: <= 60 per minute

Minimum spacing:

  • Publish (post): >= 20 minutes between actions
  • Reply/message: >= 30 seconds between actions
  • Follow/like/collect: >= 10 seconds between actions
  • Read/search/get/user read: >= 1 second between actions

Same-target guardrails:

  • Repeated interaction on same target (same post_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:

  1. Pause at least 15 minutes.
  2. Resume with read-only actions first.
  3. 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 --json output 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 weibov2:<account_id> --json
mediause auth health --json
mediause weibov2 search hot --json
mediause weibov2 post feed --text "<draft_text>" --media c:/tmp/a.png --json
mediause trace last --json

6.2 Monitor and engage

mediause use account weibov2:<account_id> --json
mediause auth health --json
mediause weibov2 get notif --type mention --json
mediause weibov2 reply comment --post-id <id> --text "received" --json
mediause trace last --json

6.3 Read-only guest branch (if supported)

mediause use account weibov2:guest --json
mediause weibov2 search hot --json
mediause weibov2 get feed --limit 20 --json
mediause trace last --json

7. Execution Checklist

Before run:

Before every run, execute the install script once.

  1. CLI installed via npm install -g @mediause/cli on Windows.
  2. PATH updated and mediause --version works.
  3. API key configured and verified.
  4. Account context bound via mediause use account <platform:account_id>.
  5. mediause auth health --json checked after context bind.
  6. If not logged in, run mediause auth login weibov2 --json and re-bind context.
  7. Pacing policy is enabled.

During run:

  1. Respect risk-based delays and minimum spacing.
  2. Stop on anti-bot/risk prompts.
  3. Avoid repetitive write-action bursts.
  4. In guest mode, allow read-only actions only.

After run:

  1. Save logs and outcomes.
  2. Record any risk warning and cooldown events.
  3. Keep account activity under conservative limits.

8. Quick Command Reference

# always run once before each workflow (auto-upgrade latest)
mediause --version
mediause --version

# discover
mediause plugin list --json
mediause plugin add weibov2 --json
mediause weibov2 -h
mediause weibov2 post -h

# context + status
mediause auth list --json
mediause use account weibov2:<account_id> --json
mediause auth health --json

# read action
mediause weibov2 search hot --json

# write action
mediause weibov2 post feed --text "hello" --json

# trace
mediause trace last --json

Skill Metadata Maintainer: @mediause-demo Last-Updated: 2026-08-22 Version: v2

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall