Xquik Social Data
Use this skill when a task needs current public X/Twitter evidence through Xquik.
Keep the work evidence-first: fetch small, relevant samples, cite post IDs or URLs,
and separate direct observations from interpretation.
When To Use
- Search public posts for a topic, brand, account, incident, product, or campaign.
- Look up public X/Twitter accounts or posts before writing a summary.
- Compare public conversation themes, sentiment, repeated questions, or complaints.
- Build a traceable evidence set for social listening, OSINT, marketing research, or support triage.
- Check trends or public activity before drafting a post or recommendation.
Do not use this skill for private messages, login-gated content, credential sharing,
platform bypassing, or claims that need complete official analytics.
Setup
- API base:
https://xquik.com/api/v1
- Docs:
https://docs.xquik.com
- Authentication: send the user's Xquik API key as
x-api-key.
Never print or store API keys. If no API key is available, provide the exact
request shape and ask the user to run it in their approved environment.
Workflow
Clarify scope.
- Topic, account, date range, language, geography, and desired output.
- If the user gives a broad topic, create 3 to 8 short search queries.
Fetch public evidence.
- Search posts with
GET /x/tweets/search?q=<query>.
- Use account or post endpoints only when they directly support the task.
- Keep request batches small and deduplicate by post ID.
Normalize findings.
- Preserve
id, text, createdAt, author username, engagement fields, and URL.
- Label missing counts as missing, not zero, unless the API response explicitly says zero.
- Keep every conclusion tied to at least one post ID, URL, or account handle.
Analyze cautiously.
- Group repeated themes.
- Mark sentiment as an interpretation unless the user provided labeled data.
- Call out sample size, query bias, language bias, and time-window limits.
Return a concise report.
- Scope and queries.
- Evidence count and deduped count.
- Top themes with cited examples.
- Risks, unknowns, and recommended next searches.
Request Examples
curl "https://xquik.com/api/v1/x/tweets/search?q=launch%20feedback" \
-H "x-api-key: $XQUIK_API_KEY"
curl "https://xquik.com/api/v1/x/users/search?q=xquik" \
-H "x-api-key: $XQUIK_API_KEY"
Output Template
## Scope
- Goal:
- Queries:
- Time window:
## Evidence
- Raw results:
- Deduped results:
- Notable examples:
## Findings
1. Theme:
Evidence:
Confidence:
## Limits
- Sample size:
- Query bias:
- Missing data:
## Next Searches
1.
2.
Quality Rules
- Do not fabricate posts, counts, links, trends, or account details.
- Do not infer demographics or intent from a single post.
- Do not expose secrets, raw credentials, or private implementation details.
- Do not claim complete coverage of X/Twitter. Say "sample" unless the user provided a complete export.
- Prefer exact IDs and URLs over vague summaries.
1---2name: xquik-social-data3description: Use when 用户需要从 Xquik 获取公开 X/Twitter 数据、搜索推文、查账号、看趋势、导出样本、整理社媒证据,或说 xquik、Xquik、X/Twitter data、tweet search、social evidence、社媒证据、推文搜索。4---56# Xquik Social Data78Use this skill when a task needs current public X/Twitter evidence through Xquik.9Keep the work evidence-first: fetch small, relevant samples, cite post IDs or URLs,10and separate direct observations from interpretation.1112## When To Use1314- Search public posts for a topic, brand, account, incident, product, or campaign.15- Look up public X/Twitter accounts or posts before writing a summary.16- Compare public conversation themes, sentiment, repeated questions, or complaints.17- Build a traceable evidence set for social listening, OSINT, marketing research, or support triage.18- Check trends or public activity before drafting a post or recommendation.1920Do not use this skill for private messages, login-gated content, credential sharing,21platform bypassing, or claims that need complete official analytics.2223## Setup2425- API base: `https://xquik.com/api/v1`26- Docs: `https://docs.xquik.com`27- Authentication: send the user's Xquik API key as `x-api-key`.2829Never print or store API keys. If no API key is available, provide the exact30request shape and ask the user to run it in their approved environment.3132## Workflow33341. Clarify scope.35 - Topic, account, date range, language, geography, and desired output.36 - If the user gives a broad topic, create 3 to 8 short search queries.37382. Fetch public evidence.39 - Search posts with `GET /x/tweets/search?q=<query>`.40 - Use account or post endpoints only when they directly support the task.41 - Keep request batches small and deduplicate by post ID.42433. Normalize findings.44 - Preserve `id`, `text`, `createdAt`, author username, engagement fields, and URL.45 - Label missing counts as missing, not zero, unless the API response explicitly says zero.46 - Keep every conclusion tied to at least one post ID, URL, or account handle.47484. Analyze cautiously.49 - Group repeated themes.50 - Mark sentiment as an interpretation unless the user provided labeled data.51 - Call out sample size, query bias, language bias, and time-window limits.52535. Return a concise report.54 - Scope and queries.55 - Evidence count and deduped count.56 - Top themes with cited examples.57 - Risks, unknowns, and recommended next searches.5859## Request Examples6061```bash62curl "https://xquik.com/api/v1/x/tweets/search?q=launch%20feedback" \63 -H "x-api-key: $XQUIK_API_KEY"64```6566```bash67curl "https://xquik.com/api/v1/x/users/search?q=xquik" \68 -H "x-api-key: $XQUIK_API_KEY"69```7071## Output Template7273```markdown74## Scope75- Goal:76- Queries:77- Time window:7879## Evidence80- Raw results:81- Deduped results:82- Notable examples:8384## Findings851. Theme:86 Evidence:87 Confidence:8889## Limits90- Sample size:91- Query bias:92- Missing data:9394## Next Searches951.962.97```9899## Quality Rules100101- Do not fabricate posts, counts, links, trends, or account details.102- Do not infer demographics or intent from a single post.103- Do not expose secrets, raw credentials, or private implementation details.104- Do not claim complete coverage of X/Twitter. Say "sample" unless the user provided a complete export.105- Prefer exact IDs and URLs over vague summaries.