sandbaseai/sandbase-skills / research/twitter-intelligence
twitter-intelligence
VerifiedSearch tweets, analyze trends, monitor users, and gather social intelligence from Twitter/X through SandBase. Use when asked for Twitter research, social listening, trend analysis, influencer monitoring, sentiment tracking, or competitor social intelligence.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.7 KB |
| agents/openai.yaml | config | 239 B |
| references/sandbase-api-map.md | markdown | 1.6 KB |
SKILL.md
View on GitHub---
name: twitter-intelligence
description: Search tweets, analyze trends, monitor users, and gather social intelligence from Twitter/X through SandBase. Use when asked for Twitter research, social listening, trend analysis, influencer monitoring, sentiment tracking, or competitor social intelligence.
---
# Twitter Intelligence
Full-spectrum Twitter/X research and social listening through SandBase. Search public tweets, discover trends, analyze user profiles, and monitor discussions — all read-only, never posts or engages. Read [the API map](references/sandbase-api-map.md) before selecting a capability.
## Call SandBase capabilities
Use the capability identifiers below as discovery hints, not MCP tool names. Find the matching endpoint with `sandbase_discover(q: "<provider and capability>")`; use its returned `name` in `sandbase_inspect(name: "<returned name>")`. Read `inputSchema`, pricing, and `execute_as`, then call `sandbase_run` using `execute_as.arguments.name` and schema-defined `arguments`. If a `run_id` is returned, poll `sandbase_run_get(run_id: "<returned run_id>")` within the task budget until `completed` or `failed`; report pending or failed runs without resubmitting them automatically.
## Operating principles
- Use Twitter data as social signal evidence, not as representative public opinion.
- Separate observations (tweet volume, engagement, accounts posting) from interpretation (sentiment, trend direction).
- Preserve attribution: include tweet URLs, usernames, dates, and engagement metrics.
- Never post, like, retweet, follow, or engage on behalf of the user.
- Keep monitored accounts and strategy confidential unless sharing is requested.
## Workflow
### 1. Frame the research
Classify the request:
- **Trend discovery**: what's trending, emerging topics
- **Topic monitoring**: track discussions around a keyword or brand
- **User analysis**: profile, content, followers, engagement patterns
- **Sentiment tracking**: how people feel about a topic or brand
- **Competitor intelligence**: what competitors post and how audiences respond
### 2. Search tweets
Use `twitter_web_search_timeline` for keyword-based tweet discovery:
- Search for brand names, product names, hashtags, or topic phrases
- Use negative keywords to filter noise
- Compare search results for competitors side by side
Use `twitter_bulk_tweet_search` for higher-volume batch searches.
### 3. Discover trends
Use `twitter_web_trending` to find what's trending globally or by location.
### 4. Analyze users
Use `twitter_web_user_profile` for account details (bio, follower count, verified status).
Use `twitter_web_user_media` and tweet timeline tools for content analysis.
Use `twitter_web_user_followers` / `twitter_web_user_followings` for network analysis.
### 5. Deep-dive tweets
Use `twitter_web_tweet_detail` for specific tweet metrics and thread context.
Use `twitter_web_latest_post_comments` or `twitter_web_post_comments` for reply analysis.
## Output
Return: search scope, tweet volume summary, key accounts involved, sentiment signals, trend indicators, engagement patterns, and evidence gaps.
## Example tasks
- "What are people saying about [brand] on Twitter this week?"
- "Find trending topics in the AI/tech space right now."
- "Analyze @competitor's Twitter presence — posting frequency, engagement, top content."
- "Monitor mentions of [product launch] and summarize sentiment."
- "Who are the most influential voices discussing [topic] on Twitter?"
## Failure handling
- If SandBase is unavailable, report the failure and do not substitute a direct API.
- If searches return few results, try broader terms or related hashtags.
- If a user account is private/suspended, note the gap and continue with available data.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |