Claude Skills by borghei
Claude Skills
An installable skill library for teams: engineering, product, marketing, compliance, finance, with ready Python tools and agents
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- Some skills ship Python tools that run code and may access the network
- Compliance and legal material requires review by a specialist
Install
Manual install
npx @borghei/claude-skills add senior-fullstackThe installer detects your agent and drops the skill into the right directory. Replace the skill name as needed.
This is third-party code. Review the repository files before installing.
What it does
The set gives the agent skills across twenty domains, from engineering and project management to marketing, compliance, legal and finance work. Each skill describes a concrete workflow rather than just a prompt template, and many ship Python tools built on the standard library that you can run in CI or via MCP. It also includes pre-built expert personas and role bundles, plus slash commands for common tasks. It covers regulated industries: SOC 2, ISO 13485, MDR, FDA, EU AI Act, GDPR, HIPAA and other frameworks with checklists and audit-oriented material. The library installs through its own CLI, as a Claude Code plugin or manually, and works with several agents.
Who it is for. For teams and individuals who need ready agent workflows beyond engineering: product, marketing, compliance, operations.
Good fit when
- You need a ready workflow for a role: product, marketing, engineering, compliance
- You need regulated-industry audit material and checklists
- You need to install a set of skills across several agents through one CLI
Not a fit when
- You need one narrow skill rather than a large multi-domain library
- The compliance material cannot be used without review by a lawyer or domain specialist
Example request
Help me prepare a SOC 2 audit plan: build a checklist and find gaps in our processesLimitations
The author states the material is built with AI tools and may contain errors, and that compliance, legal, financial and safety-critical decisions must be verified independently. The license is MIT with a Commons Clause: free for open-source, personal, education and internal business use, but it cannot be sold or repackaged as a paid product. The installer needs Node 18+, and the Python tools rely on the standard library.
How to disable. Remove the domain plugins via /plugin or delete the installed skill folders from the agent's skills directory, for example ~/.claude/skills.
Security check
- Some skills ship Python tools that run code and may access the network
- Compliance and legal material requires review by a specialist
README in short
The README describes an open-source skill library for every team, not just engineering, with domains from project management and marketing to compliance and finance. It advertises hundreds of skills, expert agents, standard-library Python tools, slash commands, role bundles and multi-agent orchestration patterns. Installation runs through the npx CLI, the Claude Code plugin marketplace, an MCP server or manual copy, with support for many agents. It highlights regulated-industry material. The license is MIT with a Commons Clause, and the author warns about possible AI-content errors.
FAQ
Which agents does it support?
The installer detects Claude Code, Cursor, Codex, Gemini CLI, Copilot, Windsurf, Cline, Goose and others and drops the skill into the right directory. The material can also be pasted into Claude.ai or ChatGPT chats.
Can I install only part of the library?
Yes. The CLI installs individual skills by name, and in Claude Code domains connect as separate plugins.
Related
A self-hosted knowledge base with block-level references and a built-in MCP server for connecting AI agents to your notes
A CLI for every Google Workspace API with JSON output and agent skills: Drive, Gmail, Calendar, Sheets and more
Local search over Markdown notes, docs and meeting transcripts: keywords, semantic search and reranking, with an MCP server
A task manager for AI-driven development: breaks a PRD into dependent tasks and guides the agent through them via MCP or CLI