一键导入
test
Verify sparX setup is working correctly. Use when the user wants to check their installation, test skills, or troubleshoot setup issues.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Verify sparX setup is working correctly. Use when the user wants to check their installation, test skills, or troubleshoot setup issues.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Read real engagement analytics from X via browser automation. Use when the user wants to check how their posts are performing, review analytics, or get real engagement data without manual entry. Requires claude-in-chrome.
Draft algorithm-optimized X posts. Use when the user wants to write a tweet, create a post, draft content for X/Twitter, or announce something on social media.
Manage replies and conversations on X via browser automation. Surfaces comments worth replying to, drafts optimized replies, and posts them with your approval. Activates the 75-150x conversation velocity multiplier. Requires claude-in-chrome.
Generate scroll-stopping opening lines for X posts. Use when the user needs hook ideas, opening lines, first lines, or attention-grabbing openers for tweets.
Plan and create visual content for X posts. Use when the user wants to add images, videos, GIFs, screenshots, or any visual media to their X content. Also use when deciding what kind of visual would best complement a post.
Score and rewrite X post drafts for maximum algorithm reach. Use when the user has a draft tweet or post they want improved, reviewed, or scored against the Phoenix algorithm.
| name | test |
| description | Verify sparX setup is working correctly. Use when the user wants to check their installation, test skills, or troubleshoot setup issues. |
| argument-hint | [all | skills | browser | remotion] |
Quick verification that everything is wired up correctly. Runs a series of checks and reports status.
Run all checks (or a subset if the user specifies). Present results as a checklist.
✅ / ❌ CLAUDE.md loaded — check that Phoenix algorithm context is available
✅ / ❌ Reference docs exist — check reference/scoring.md, reference/penalties.md, etc.
✅ / ❌ Skills discovered — list all skills Claude can see (should be 15)
How to verify:
CLAUDE.md and confirm it contains "Phoenix Algorithm"reference/scoring.md existsRun a quick /hooks generation to prove the content pipeline works:
Generate 3 hooks for: "a new open-source developer tool"
Pass criteria:
✅ / ❌ Skill pipeline — /hooks produced scored output
Check if the Remotion project exists:
ls marketing/remotion.config.ts 2>/dev/null
✅ / ❌ Remotion project — marketing/ directory with remotion.config.ts
✅ / ❌ Remotion skills — marketing/.claude/skills/remotion-best-practices/SKILL.md
✅ / ❌ Tailwind configured — marketing/tailwind.config.ts or similar
If not installed:
⬜ Remotion not installed — run: pnpm create video --blank marketing
Check if claude-in-chrome is available by attempting to get tab context:
mcp__claude-in-chrome__tabs_context_mcp()
✅ / ❌ Chrome connection — claude-in-chrome responds
✅ / ❌ Can create tab — tabs_create_mcp succeeds
If not available:
⬜ Chrome not connected — install claude-in-chrome extension
Check environment for optional integrations:
✅ / ❌ / ⬜ OpenTweet MCP — check if opentweet tools are available
✅ / ❌ / ⬜ last30days — check if ~/.claude/skills/last30days/SKILL.md exists
✅ / ❌ / ⬜ X API — check if TWITTER_API_KEY env var is set
Present a summary dashboard:
sparX Setup Report
══════════════════
Core
✅ CLAUDE.md loaded (Phoenix algorithm context)
✅ Reference docs (6/6 files)
✅ Skills discovered (15/15)
✅ Skill pipeline (hooks generated successfully)
Remotion
✅ Project exists (marketing/)
✅ Agent skills installed
✅ Tailwind configured
Browser (claude-in-chrome)
✅ Chrome connected
✅ Tab creation works
Optional Integrations
⬜ OpenTweet MCP (not configured — run /setup opentweet)
⬜ last30days (not installed — run /setup last30days)
⬜ X API (not configured — run /setup x-api)
Status: Ready to go! Core + Remotion + Browser all working.
Use ✅ for pass, ❌ for fail (with fix suggestion), ⬜ for not installed (optional).