agentleFS
FuDesign2008FuDesign2008/open-skills/skills/xquik-social-data/SKILL.md

xquik-social-data

Skill6 starsChanged 10 days agoMITView on GitHub

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。

  • Reads credentials

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. 0 are common, 17 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 17

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when a task needs current public X/Twitter evidence through Xquik.

    line 10
  2. Distinctive:

    Keep the work evidence-first: fetch small, relevant samples, cite post IDs or URLs, and separate direct observations from interpretation.

    line 11
  3. Distinctive:

    Search public posts for a topic, brand, account, incident, product, or campaign.

    line 16
  4. Distinctive:

    Look up public X/Twitter accounts or posts before writing a summary.

    line 17
  5. Distinctive:

    Check trends or public activity before drafting a post or recommendation.

    line 20
  6. Distinctive:

    Do not use this skill for private messages, login-gated content, credential sharing, platform bypassing, or claims that need complete …

    line 22
  7. Distinctive:

    Never print or store API keys.

    line 31
  8. Distinctive:

    If the user gives a broad topic, create 3 to 8 short search queries.

    line 38
  9. Very specific:

    Search posts with GET /x/tweets/search?q=<query>.

    line 41
  10. Distinctive:

    Use account or post endpoints only when they directly support the task.

    line 42
  11. Distinctive:

    Keep request batches small and deduplicate by post ID.

    line 43
  12. Distinctive:

    Keep every conclusion tied to at least one post ID, URL, or account handle.

    line 48
  13. Distinctive:

    Call out sample size, query bias, language bias, and time-window limits.

    line 53
  14. Distinctive:

    Do not fabricate posts, counts, links, trends, or account details.

    line 103
  15. Distinctive:

    Do not infer demographics or intent from a single post.

    line 104
  16. Distinctive:

    Do not expose secrets, raw credentials, or private implementation details.

    line 105
  17. Distinctive:

    Do not claim complete coverage of X/Twitter.

    line 106
  18. Distinctive:

    Prefer exact IDs and URLs over vague summaries.

    line 107

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.