# best-prompts

通用高质量 Prompt 合集🔥

Repository: https://github.com/xstongxue/best-prompts
Canonical: https://ross.abutalabs.com/products/best-prompts
License: Apache-2.0
License Family: permissive
Topics: prompt-engineering, vibe-coding
Last push: 2026-05-06T06:39:57+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 81, release rhythm 35, longevity 13
- inputs: {"age_days": 187, "days_push": 119, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1318, forks 123 (observed 2026-08-28T04:04:21.222609+00:00)

## What it is
A curated collection of high-quality Agent skills (SKILL.md files) installable into AI coding agents like Cursor, Claude Code, Codex, and OpenClaw. Unlike chat prompts, these skills are auto-triggered by the agent based on description keywords, covering tasks like diagram generation, PPT creation, and article writing.

## Use cases
- generate drawio architecture diagrams with an ai agent
- create powerpoint presentations from paper content
- write wechat article covers automatically
- find quality skills for claude code
- draw uml sequence diagrams via agent
- make excalidraw diagrams with ai
- auto-trigger skills in cursor or codex

## When to choose
- you use agent tools like Claude Code, Cursor, Codex, or OpenClaw and want reusable auto-triggered skills
- you need polished templates for diagrams, slides, or article covers generated by AI

## When to avoid
- you want simple copy-paste chat prompts rather than agent skills (use best-prompts instead)
- you need a standalone application rather than skill files

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, agent-framework, data-visualization, documentation
- domain: artificial-intelligence, developer-tools, education
- platform: cross-platform, cli
- tags: skills-collection, claude-code, cursor, vibe-coding, diagram-generation, ppt-generation, wechat-article, ai-agents

## Member repositories
- xstongxue/best-prompts (main) score 51
- xstongxue/best-skills (plugin) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:21.222609+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:19:02.336550+00:00, confidence not recorded.
  - readme: https://github.com/xstongxue/best-prompts (fetched 2026-08-28T04:04:21.222609+00:00, sha 30ab0bf3ea2c)
- Data as of 2026-08-30T08:39:29.467469+00:00.