OpenViSTAI · Agents · Blockchain · Crypto
Menu
Agent Frameworks

Qiushi Skill

Qiushi Skill is an open-source collection of AI-agent skills that applies methods from dialectical materialism and practical philosophy to investigation, problem analysis, validation and sustained task work.

Independent OpenViST project profile, based on linked sources.

Qiushi Skill — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an agent task calls for deliberate investigation, analysis, validation or iterative improvement; the README says direct-execution tasks do not trigger downstream skills.

Who it is for

  • AI-agent builders adding reusable reasoning methods to existing assistants.
  • Users of supported agent hosts who want structured procedures for research, prioritization, feedback and self-review.

Documented uses

  • Prompt an agent to gather information before reaching a conclusion.
  • Help an agent identify a complex problem’s main contradiction and focus effort.
  • Give an agent procedures for validating plans, incorporating feedback and reviewing completed work.
  • Coordinate multiple methods through workflow combinations.
Before you choose

Requirements & limits

  • The README documents an npx installer, a Claude Code marketplace route and manual copying of skill directories.
  • The entry skill is described as automatically injected at session start after installation, with other skills loaded when appropriate.
  • Manual command files are intended for assistants that support Markdown slash commands; other assistants can open the corresponding files directly.
  • The repository specifies an MIT license and JavaScript as its primary language.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Qiushi-Skill with the npx installer

Install the skill collection for a supported host using its interactive installer.

Before you start

  • Node.js for the npx installation method.

Steps

  1. Run the command below to detect installed hosts and write the skills to the corresponding directories.

    Documented command
    npx qiushi-skill
  2. Alternatively, specify a host and scope with the command below.

    Documented command
    npx qiushi-skill install --target claude-code --scope user
  3. For multiple hosts, use the command below.

    Documented command
    npx qiushi-skill install --target cursor,codex,opencode,openclaw,hermes,nanobot --scope user
  4. Run the command below to check the installation.

    Documented command
    npx qiushi-skill validate

Expected outcome

The skills are installed for the selected host or hosts, and the documented validation command is available to check the installation.

Guide limitations

  • The repository documentation lists supported targets and their native directories in its platform guide.
  • Without Node.js, the documented alternative is to copy directories under skills/ into the host's skills directory; this recipe does not specify individual host directory paths.
Source-based practical guide

Install Qiushi-Skill through Claude Code Marketplace

Add the Qiushi-Skill marketplace and install the collection in Claude Code.

Before you start

  • Claude Code with support for its marketplace and plugin commands.

Steps

  1. Run /plugin marketplace add HughYau/qiushi-skill.

  2. Run /plugin install qiushi-skill@qiushi-skill.

  3. After installation, the entry skill is described as automatically injected at the start of each session.

Expected outcome

Qiushi-Skill is installed through Claude Code Marketplace, with its entry skill set to load at session start.

Guide limitations

  • This installation route is specifically documented for Claude Code.
  • The documented session behavior describes automatic entry-skill injection; it does not establish that every downstream skill is loaded automatically.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
HughYau/qiushi-skill · Official homepage title · retained in its source language