openJiuwen
Official@openjiuwen-ai · China
openJiuwen is an open-source community dedicated to building a production-ready AI Agent platform.
Agent Skills by openJiuwen
Showing 42 vetted skills indexed across 1 GitHub repositories.
skill-name-1
Analyzes delegated expert subtasks and returns evidence-backed conclusions with risks and next steps.
content-enhancement
Enhance existing drafts with citations, opening rewrites, title optimization, and text polishing.
content-drafting
Draft structured documents and chapters from scattered notes, outlines, and interview records.
content-review
Review manuscripts with paragraph-level feedback, structural diagnosis, and delivery-ready revisions.
office-document-workflow
Orchestrates parsing, conversion, editing, and redaction of PDF, Word, Excel, and PPT documents.
health-life-planning
Generates personalized diet, sleep, and stress management plans through multi-turn health profiling.
arch-review
Review architecture proposals against quality attribute checklists and produce risk-rated assessment reports.
arch-assess
Analyze existing codebases to map dependencies, draw as-is C4 diagrams, and assess architecture health.
arch-evolution
Plan architecture migrations, technical debt repayment, and governance processes with phased roadmaps.
arch-engineering
Guides full-stack engineering practices covering API design, authentication, caching, and cloud-native infrastructure.
arch-design
Guides architecture selection and design using DDD, C4 diagrams, and ADR records.
a-share-analysis
Analyzes A-share stocks, market sentiment, and sector trends using real-time market data.
fund-analysis
Analyzes mutual funds and builds portfolio allocation and dollar-cost averaging plans.
skill-creator-normal
Create, evaluate, and iteratively improve single-agent skills with benchmarked test runs.
huawei-cloud-maas-setup
Automates Huawei Cloud MaaS service purchase, API key creation, and model configuration via browser scripts.
dynamic-memory-cli
Manage atomic Pending and Built agent memory with SQLite-backed publication, search, and validation.
project-maintainer
Builds and maintains a structured in-repository project knowledge base with symbol-level coverage and health audits.
agent-creator
Creates and updates JiuwenSwarm agent template packages from natural language requirements.
ppt-creation
Generates and edits PowerPoint presentations using PptxGenJS components and template-based workflows.
plugin-creator
Creates and updates JiuwenSwarm plugin packages from natural language requirements.
harmonyos-dev-suite
Routes HarmonyOS development tasks across ArkTS, ArkUI, build, debug, testing, and device workflows.
skill-omni-creation
Generates standard Skill Markdown files from web pages or video tutorials.
aet-req-review
Enforces automated quality gates and user validation for requirement deliverables before handover.
aet-req-analysis
Transforms raw requirements into structured specifications through Socratic dialogue and staged workflows.
Frequently Asked Questions About openJiuwen
FAQPage SchemaWhat specific tasks can I perform using these capabilities?▼
You can perform kernel profiling, convert SOP documentation into executable skill structures, extract line items from financial documents, and analyze MoE phase timing using Perfetto trace data. These functions enable systematic documentation auditing and hardware-specific performance optimization for complex computational models.
Which technical personas benefit most from this platform?▼
This platform is designed for machine learning engineers, kernel developers, and technical documentation specialists. It specifically supports those working on Ascend hardware optimization, MoE architecture tuning, and enterprise-grade knowledge base management through structured document ingestion and performance benchmarking.
What are the prerequisites for running these optimization tasks?▼
Execution requires a local environment configured for the JiuwenSwarm runtime, including access to the skvm environment for profiling and JIT optimization. Users must also ensure their source data, such as SOP documents or trace files, are formatted correctly for the respective ingestion and analysis modules.