Configure API credentials in local environment (never in chat).
Start in monitor-only for 3–7 days.
Move to draft+approve for 1–2 weeks.
Enable limited automation for one playbook only.
Review weekly and adjust limits.
Output Formats
Monitor brief
What happened
Why it matters
Suggested response
Draft package
Draft text
Variant A/B
Risk flags
Recommended time
Automation report
Actions executed
Actions skipped (and why)
Rate limit usage
Any policy violations blocked
1---2name: x-agent3description: X Agent (Phased Setup)4---56# X Agent (Phased Setup)78## Objective9Operate an X workflow safely across three phases, with automation disabled until explicitly enabled.1011## Phase 1 — Monitor-only121. Track topics, keywords, and accounts.132. Summarize notable posts and sentiment.143. Produce a daily/weekly brief:15 - top signals16 - opportunities17 - reputational risks184. Do not post.1920## Phase 2 — Draft + approval211. Generate draft tweets/replies/threads from user goals.222. Enforce style rules:23 - concise24 - no unverifiable claims25 - no legal/financial guarantees263. Present final draft with:27 - risk flags28 - confidence level29 - suggested posting window304. Require explicit approval before publishing.3132## Phase 3 — Limited automation (default OFF)33Enable only after user confirmation.3435Automation constraints:361. Allowed actions only from pre-approved playbooks.372. Hard caps:38 - max posts/day39 - max replies/hour403. Blocked categories:41 - politics (unless explicitly allowed)42 - legal/medical/financial advice language434. Quiet hours and cooldowns required.445. Global kill switch required.4546## Required Guardrails47Always define these before posting access:481. Account scope: monitor | draft+approve | limited-auto492. Max daily posts503. Max hourly replies514. Quiet hours (timezone)525. Banned topics/phrases536. Kill switch command and owner5455## Starter Playbooks561. News reaction post (single tweet)572. Research summary thread (3–5 posts)583. Reply triage (approve queue)594. Daily recap post6061## Rollout Checklist621. Create or choose X account.632. Configure API credentials in local environment (never in chat).643. Start in monitor-only for 3–7 days.654. Move to draft+approve for 1–2 weeks.665. Enable limited automation for one playbook only.676. Review weekly and adjust limits.6869## Output Formats70### Monitor brief71- What happened72- Why it matters73- Suggested response7475### Draft package76- Draft text77- Variant A/B78- Risk flags79- Recommended time8081### Automation report82- Actions executed83- Actions skipped (and why)84- Rate limit usage85- Any policy violations blocked
Run npx skillmds@latest add javimosch/x-agent in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
X Agent (Phased Setup) It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
javimosch (@javimosch) published this skill. Their other Agent Skills are listed on their SkillMD profile.
javimosch