Semantic agent skills for cloud operations with ontology-first design, including read-only Huawei Cloud billing skills.
SemanticSkills is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
npx skills add ontology-of-everything/SemanticSkillsRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
SemanticSkills provides ready-to-use skills for AI coding agents like Claude Code and Cursor to perform cloud operations correctly. Instead of guessing billing data, the agent uses structured semantic models to find the right facts before running commands. It includes skills for reading Huawei Cloud billing and estimating costs.
SemanticSkills (Huawei Community Edition) is a collection of open SKILL.md packages designed for AI coding agents such as Claude Code, Cursor, and Codex CLI. The project addresses common failures in cloud billing and pricing tasks by using an ontology-first approach: domain semantics are stored in structured YAML files under references/, not in a bloated SKILL.md. This ensures the agent selects the correct fact entity before executing any CLI command. Currently, two skills are available: huawei-cloud-billing-scout (read-only BSS billing queries via KooCLI) and huawei-cloud-cost-estimation (period and on-demand quotes). Each skill includes routing via catalog.yml, semantic models, command templates, and delivery protocols. The repository is community-maintained and not official Huawei Cloud. It is licensed under Apache-2.0 and has 5 stars, 1 fork, and 0 open issues.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 55 days ago.
5 GitHub stars indicate community interest.
0 open issues signal maintenance load.
Apache-2.0 license detected.
Query Huawei Cloud account balance and bills using natural language via an AI agent.
Estimate cost of period or on-demand resources before placing an order.
Reconcile billing data with evidence from read-only BSS operations.
Automate cloud cost reporting in chat platforms like Feishu or WeChat without broken tables.
Integrate semantic billing skills into custom AI agent workflows.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing.
Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Cloud operations skills may need provider credentials; prefer read-only scopes and local secret stores.
Skills are read-only but still require cloud credentials; ensure credentials are scoped minimally.
Community-maintained, not official Huawei Cloud; verify accuracy for production use.
5
Stars
1
Forks
0
Issues
Apache-2.0
License
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
Semantic agent skills for cloud operations with ontology-first design, including read-only Huawei Cloud billing skills.
Cloud engineers managing Huawei Cloud billing and FinOps., AI agent developers building custom skills for Claude Code or Cursor., DevOps teams automating cloud cost visibility and reconciliation.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing. Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Similar or complementary options to evaluate include anthropic-skills, bug-hunter, Dify.
Jun 7, 2026
5 security/trust notes recorded.
Setup difficulty is 3/5.
Open-source LLM app development platform. Build AI workflows, RAG pipelines, and agents with a visual interface.