How do I install the Xiaohei Daily Query Vp skill?

Run npx skillmds@latest add vectorpeak/xiaohei-daily-query-vp 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.

Is Xiaohei Daily Query Vp safe to use?

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.

Which AI agents work with Xiaohei Daily Query Vp?

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.

Is Xiaohei Daily Query Vp free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Xiaohei Daily Query Vp?

VectorPeak (@vectorpeak) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Xiaohei Daily Query Vp by vectorpeak

Name: Xiaohei Daily Query Vp
Author: VectorPeak

Xiaohei Daily Query Vp

Query the local Xiaohei Daily Assistant HTTP service for work timelines, Markdown work reports, 24-hour heat maps, and app usage duration statistics. Use when the user asks about 小黑日报助手, 日报, 工作时间线, 工作报告, 时段热力图, 应用使用时长, app usage, or productivity records from the local service at 192.168.11.212:8088.

VectorPeak Updated Sep 17, 2026

File contents

Xiaohei Daily Query

Core Rule

Before every user request, fetch the latest API Markdown document from:

GET http://192.168.11.212:8088/

Do not rely on a memorized endpoint list. Read the live Markdown, parse the available endpoint paths, methods, parameters, request examples, and response shape, then choose the correct endpoint for the user's request.

Supported User Intents

Handle natural-language requests for:

Work timeline records for a date or date range.
Work reports for a date or date range, returned as Markdown content.
Hourly heat-map data for a date range.
App usage duration summaries for a date or date range.

If the user does not specify a date, omit startDate and endDate so the service uses its current default. For timeline, report, and app usage this normally means today; for heat-map this normally means the recent default window described in the live docs.

Use YYYY-MM-DD dates unless the user explicitly asks for a precise time range.

Recommended Script

Use the bundled helper:

& "C:\Users\ZXY\.cache\codex-runtimes\codex-primary-runtime\dependencies\python\python.exe" `
  "C:\Users\ZXY\.codex\skills\xiaohei-daily-query-vp\scripts\query_xiaohei.py" `
  --intent report --start-date 2026-06-29 --end-date 2026-06-29

The script always fetches GET / first, extracts the live GET endpoints from the Markdown, maps the requested intent to the currently documented path, calls the selected endpoint, validates the unified JSON envelope, and prints a compact Markdown summary.

Intent values:

timeline
report
heat-map
app-usage

The script also accepts --query for lightweight natural-language intent detection:

& "<python>" "<skill>\scripts\query_xiaohei.py" --query "查一下今天应用使用时长"

Response Style

Summarize the returned data directly for the user:

For reports, preserve useful Markdown report content and mention report titles/date ranges.
For timelines, group records by time and category.
For heat maps, highlight focus minutes, active period, top category, and hourly distribution if relevant.
For app usage, convert seconds into readable hours/minutes and list apps in returned order.

If the service returns code != 0, explain the error message and include the endpoint that was attempted.

---name: xiaohei-daily-query-vpdescription: Query the local Xiaohei Daily Assistant HTTP service for work timelines, Markdown work reports, 24-hour heat maps, and app usage duration statistics. Use when the user asks about 小黑日报助手, 日报, 工作时间线, 工作报告, 时段热力图, 应用使用时长, app usage, or productivity records from the local service at 192.168.11.212:8088.---# Xiaohei Daily Query## Core RuleBefore every user request, fetch the latest API Markdown document from:```textGET http://192.168.11.212:8088/```Do not rely on a memorized endpoint list. Read the live Markdown, parse the available endpoint paths, methods, parameters, request examples, and response shape, then choose the correct endpoint for the user's request.## Supported User IntentsHandle natural-language requests for:- Work timeline records for a date or date range.- Work reports for a date or date range, returned as Markdown content.- Hourly heat-map data for a date range.- App usage duration summaries for a date or date range.If the user does not specify a date, omit `startDate` and `endDate` so the service uses its current default. For timeline, report, and app usage this normally means today; for heat-map this normally means the recent default window described in the live docs.Use `YYYY-MM-DD` dates unless the user explicitly asks for a precise time range.## Recommended ScriptUse the bundled helper:```powershell& "C:\Users\ZXY\.cache\codex-runtimes\codex-primary-runtime\dependencies\python\python.exe" ` "C:\Users\ZXY\.codex\skills\xiaohei-daily-query-vp\scripts\query_xiaohei.py" ` --intent report --start-date 2026-06-29 --end-date 2026-06-29```The script always fetches `GET /` first, extracts the live GET endpoints from the Markdown, maps the requested intent to the currently documented path, calls the selected endpoint, validates the unified JSON envelope, and prints a compact Markdown summary.Intent values:- `timeline`- `report`- `heat-map`- `app-usage`The script also accepts `--query` for lightweight natural-language intent detection:```powershell& "<python>" "<skill>\scripts\query_xiaohei.py" --query "查一下今天应用使用时长"```## Response StyleSummarize the returned data directly for the user:- For reports, preserve useful Markdown report content and mention report titles/date ranges.- For timelines, group records by time and category.- For heat maps, highlight focus minutes, active period, top category, and hourly distribution if relevant.- For app usage, convert seconds into readable hours/minutes and list apps in returned order.If the service returns `code != 0`, explain the error message and include the endpoint that was attempted.

Frequently asked questions