mediause/agent-skills/twitter/SKILL.md
Standardized Twitter/X skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full Twitter/X 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
Run Twitter/X read and write workflows in MediaUse with consistent setup, context binding, command routing, and safe pacing controls.
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 "twitter"Inspect the Agent Skill "twitter" from https://github.com/mediause/agent-skills/blob/766e5075b28b3acd541436a7e3b3e21cdc38da01/twitter/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
6.1 Discover to publish workflow
Review the “6.1 Discover to publish workflow” section in the pinned source before continuing.
Review and apply the “6.1 Discover to publish workflow” source section. - 04
6.2 Monitoring and engagement workflow
Review the “6.2 Monitoring and engagement workflow” section in the pinned source before continuing.
Review and apply the “6.2 Monitoring and engagement workflow” source section. - 05
6.3 Moderation workflow
Review the “6.3 Moderation workflow” section in the pinned source before continuing.
Review and apply the “6.3 Moderation workflow” source section.
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 or 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 | 72/100 | 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
- twitter/SKILL.md
- Commit
- 766e5075b28b3acd541436a7e3b3e21cdc38da01
- License
- Not declared
- Collected
- 2026-07-28
- Default branch
- master
View the original SKILL.md
MediaUse Twitter X Skill
Run Twitter/X read and write workflows in MediaUse with consistent setup, context binding, command routing, and safe pacing controls.
Scope
Use this skill when the task targets Twitter/X operations such as:
- Account: health checks
- Search: post search and trending topics
- User: profile, feed, followers, following, likes
- Get: timeline, bookmarks, notifications
- List: list feed, list tweets, add/remove list members
- Post: publish and reply
- Engage: like, bookmark, follow, unfollow, unbookmark
- Moderate: delete, hide-reply, block, unblock
- Message: accept DM requests and send replies
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/twitter/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 or 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 or task.
3.1 Discover and plugin setup
mediause plugin list --json
mediause plugin add twitter --json
3.2 Bind context before any read or write
use account must be executed successfully before any read or write 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 twitter:<account_id> --policy balanced --json
If challenge or risk prompts appear, reopen in visible mode:
mediause use account twitter:<account_id> --policy balanced --show --json
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 or expired:
mediause auth login twitter --json
mediause use account twitter:<account_id> --policy balanced --json
mediause auth health --json
3.4 Guest mode
The manifest default account is guest, so guest context can be selected when your runtime supports it.
mediause use account twitter:guest --json
Guest mode guardrails:
- Treat as read-only by default.
- Block all write actions such as post, engage, moderate, message, or list member changes unless switched to a logged-in account.
4. Twitter X Dynamic Command Map v1
Source schema:
- plugin: plugin.twitter
- schema version: v1
4.1 account commands
- mediause twitter account health --json
4.2 search commands
- mediause twitter search posts --query [--filter <top|latest|people|media>] [--limit ] --json
- mediause twitter search trending [--limit ] --json
4.3 user commands
- mediause twitter user profile --username --json
- mediause twitter user feed --username [--limit ] --json
- mediause twitter user followers --username [--limit ] --json
- mediause twitter user following --username [--limit ] --json
- mediause twitter user likes --username [--limit ] --json
4.4 get commands
- mediause twitter get timeline [--type <for-you|following>] [--limit ] --json
- mediause twitter get bookmarks [--limit ] --json
- mediause twitter get notifications [--limit ] --json
4.5 list commands
- mediause twitter list feed [--limit ] --json
- mediause twitter list tweets --list_id <list_id> [--limit ] --json
- mediause twitter list add --list_id <list_id> --username --json
- mediause twitter list remove --list_id <list_id> --username --json
4.6 post commands
- mediause twitter post feed --text --json
- mediause twitter post reply --url <tweet_url> --text --json
4.7 engage commands
- mediause twitter engage like --url <tweet_url> --json
- mediause twitter engage bookmark --url <tweet_url> --json
- mediause twitter engage follow --username --json
- mediause twitter engage unfollow --username --json
- mediause twitter engage unbookmark --url <tweet_url> --json
4.8 moderate commands
- mediause twitter moderate delete --url <tweet_url> --json
- mediause twitter moderate hide-reply --url <tweet_url> --json
- mediause twitter moderate block --username --json
- mediause twitter moderate unblock --username --json
4.9 message commands
- mediause twitter message accept --query [--max ] --json
- mediause twitter message reply --text [--max ] [--skip_replied <true|false>] --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, moderation, and message actions.
- Mix read actions between write actions when possible.
5.2 Frequency limits and minimum spacing
Suggested limits:
- Publish actions: <= 3 per hour
- Reply and message actions: <= 20 per hour
- Follow, like, bookmark actions: <= 30 per hour
- Search and read actions: <= 60 per minute
Minimum spacing:
- Post operations: >= 20 minutes between actions
- Reply and message operations: >= 30 seconds between actions
- Engage operations: >= 10 seconds between actions
- Read and search operations: >= 1 second between actions
Same-target guardrails:
- Repeated interaction on same target: >= 60 seconds
- Repeated identical publish text: >= 24 hours default deny
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 --json output for machine workflows.
- Require structured error handling with stable fields or code when available.
- On blocked, rate-limit, risk prompt, or challenge pages, stop and return actionable next steps.
6. Workflow Examples
6.1 Discover to publish workflow
mediause use account twitter:<account_id> --json
mediause auth health --json
mediause twitter search trending --limit 10 --json
mediause twitter post feed --text "Daily update" --json
mediause trace last --json
6.2 Monitoring and engagement workflow
mediause use account twitter:<account_id> --json
mediause auth health --json
mediause twitter get notifications --limit 20 --json
mediause twitter engage like --url <tweet_url> --json
mediause twitter engage follow --username <username> --json
mediause trace last --json
6.3 Moderation workflow
mediause use account twitter:<account_id> --json
mediause auth health --json
mediause twitter moderate hide-reply --url <tweet_url> --json
mediause twitter moderate block --username <username> --json
mediause trace last --json
6.4 Guest read-only workflow
mediause use account twitter:guest --json
mediause twitter search posts --query "ai" --limit 10 --json
mediause twitter get timeline --type for-you --limit 20 --json
mediause trace last --json
7. Minimal Validation Checklist
Before run:
- CLI installed via https://release.mediause.dev/install.ps1 on Windows.
- PATH updated and mediause --version works.
- API key configured.
- Account context bound via mediause use account platform:account_id.
- mediause auth health --json checked after context bind.
During run:
- Respect pacing and cooldown constraints.
- Stop on anti-bot or risk prompts.
- Keep write actions conservative.
After run:
- Confirm result structure is parseable JSON.
- Check trace output for diagnostics.
- Record warnings and cooldown events.
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 plugin list --json
mediause plugin add twitter --json
# context and status
mediause auth list --json
mediause use account twitter:<account_id> --json
mediause auth health --json
# read actions
mediause twitter search posts --query "openai" --limit 5 --json
mediause twitter get timeline --type for-you --limit 10 --json
mediause twitter user profile --username openai --json
# write actions
mediause twitter post feed --text "hello" --json
mediause twitter engage like --url <tweet_url> --json
# trace
mediause trace last --json
Skill Metadata Maintainer: @mediause-demo Last-Updated: 2026-06-06 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.