1. Conduid
  2. Agents
  3. Claude Skills
MCP server · Agents

Claude Skills

by · github.com/borghei/Claude-Skills

385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.

Unclaimed agentic-codingagileai-agentsai-skillsbusiness-operationsclaude-codeclaude-skillscompliance-automationcursordeveloper-toolsgemini-cligithub-copilotjiramarketingmcp-servernotionproduct-managementproject-managementresearch-opstechnical-writing
InstallView source
59Fair

Scored 3 hours ago · breakdown

About Claude Skills

Claude Skills is an MCP server published by borghei in the Agents category: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.

The repository has 940 stars and 173 forks, with the last commit 10 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/borghei/Claude-Skills

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Claude Skills

Powered by Claude · Grounded in docs

I know everything about Claude Skills. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 1 hours ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • !Dependencies pinnedNo lockfile. Installs can pull different code over time.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.

1 check has not been run yet.

Releases

v4.13.0v4.13.0 · 7 Oct 2026Added New `tools/` domain with a 12-skill LinkedIn suite under `tools/linkedin/`, installable as the `tools-skills` plugin. The skills cover the whole loop: `linkedin-story-interviewer` (find what you have to say and keep it in a local…
v4.12.0v4.12.0 — 2026 refresh: AI-era marketing & PM, security hardening · 21 Sep 2026372 skills · 20 domains · 867 Python tools. Added 4 AI-era skills (8 stdlib Python tools, all with the 0 / 1 / 2 exit-code contract): `marketing/ai-content-disclosure` — disclosure checks for AI-generated or AI-assisted content and…
v4.8.0v4.8.0 — 43 new skills (Tiers 1-3), new research/ domain, 5 new C-suite advisors · 27 May 2026Highlights 43 new skills across 3 tiers, 1 new domain (`research/`), and 5 new C-suite advisors. Skill count: 294 → 338 (+44 incl. previous) Domain count: 15 → 16 Python tools: 720+ → 784+ (stdlib only) Tier 1 — 17 deep…
v4.7.0v4.7.0 — PM becomes a production toolkit (54 skills, ~30k lines added) · 22 May 2026TL;DR Project Management is now the deepest domain in Claude Skills. 54 skills spanning discovery → delivery → career growth, with worked examples for every skill, anti-pattern libraries, runnable pipelines, live data adapters, MCP…
v4.2.0v4.2.0 — 3 new domains, 41 new agents, 21 new skills · 4 May 2026Highlights 3 new skill domains: `personal-productivity/` (10 skills), `documents/` (4 skills, stdlib OOXML), `vertical-advisors/` (7 strategic founder advisors) 41 new `cs-*` agents across engineering (21), c-level (9), marketing (4),…

README

Try it now

No setup, any AI chat. Browse the skill library, click Try it now on any skill, and paste the prompt into Claude.ai, ChatGPT, or Gemini.

Save it to your AI. Click Save to my AI to install as a Claude Project or Custom GPT. Guided setup, no terminal.

Install in Claude Cowork (Claude desktop app)

In the Claude desktop app:

  1. Open Customize (bottom-left)
  2. Go to Browse plugins
  3. Enter: borghei/Claude-Skills

All 385 skills become available across your Claude conversations.

For developers

npx @borghei/claude-skills add senior-fullstack

Auto-detects Claude Code, Cursor, Codex, Gemini CLI, Copilot, Windsurf, Cline, Aider, and Goose. Drops the skill into the right directory for your assistant. Node 18+, no Python required.

See docs/INSTALLATION.md for the Claude Code plugin, MCP server, manual install, and CLI tooling.

What you get

Ship a SOC 2 audit. Run a sprint retro. Draft a board update. Spin up a fintech compliance program. Real workflows you can finish today, not prompt templates that need a prompt engineer to drive them.

  • The only OSS skills library covering regulated industries. SOC 2, ISO 13485, MDR, FDA, EU AI Act, NIS2, DORA, HIPAA, GDPR. 18 compliance frameworks with checklists, gap analyses, and audit-ready outputs.
  • Scripts that actually run, not just prompt templates. 900 Python tools you can pipe into CI, MCP servers, or your own scripts. Standard library only, no pip cliffs.
  • Call one persona, get a stack of skills behind it. startup-cto, growth-marketer, solo-founder, cs-cto-advisor, cs-fintech-advisor, and more. 77 expert identities ready out of the box.
  • Works with your AI assistant. Claude Code, Cursor, Codex, Gemini CLI, Copilot, Windsurf, Cline, Aider, Goose, OpenCode, and ChatGPT / Claude.ai.
  • Discovery → delivery → career for product teams. Project Management is the deepest domain — 70 skills, and every one ships with a worked example, an anti-pattern library, and a deterministic scoring rubric. 15 PM skills callable as MCP tools. 5 chain pipelines, 3 live data adapters. Jira / Linear / Notion / Productboard / Confluence. Tier 3 adds strategy frameworks (BMC, Lean Canvas, SWOT, Porter's, Ansoff) and GTM (gtm-strategy, ICP).
  • Current with 2026 marketing and product practice. AI search (AI Overviews, AI Mode, AI crawlers), ads in ChatGPT and AI search, EU AI Act and FTC disclosure checks, AI prototyping, and running delivery when AI agents take tickets. Fast-moving facts are checked against official sources and dated.
  • Runs the business, not just the codebase. Business operations (capacity planning, process mapping, vendor and procurement management), applied research ops (market, product, clinical study design, research finance), and a stdlib-only markdown→HTML publishing pipeline with a CI-ready review gate.
  • Audits your code and runs your LinkedIn. A multi-agent source security audit (security-audit + the cs-security-auditor agent) that verifies every finding with a second agent and reports confirmed, needs-validation and rejected separately. And a 12-skill LinkedIn suite in tools/: story interviews, planning, post writing, humanizing, comments and replies, profile, team advocacy and engagement analysis. Offline tools, nothing is posted for you.

Supporting evidence: 385 skills · 900 Python tools · 77 agents · 18 compliance frameworks · 21 domains · 11 platforms.

Browse skills by domain

Project Management (70) ★ (most-visited domain. Discovery, delivery, career growth, strategy frameworks, GTM, Jira / Linear / Notion / Confluence.)

Engineering (92) · Marketing (41) · C-Level (31) · Compliance (27) · Business & Growth (20) · Legal (17) · Product Team (13) · Personal Productivity (13) · Vertical Advisors (7) · Business Operations (6) · Data (6) · Sales (5) · HR (4) · Documents (4) · Research (4) · Research Ops (4) · Tools — LinkedIn (12) · Markdown-HTML (4) · Finance (3) · Workflow (2) · All skills →

How it works

Pre-built expert identities

8 cross-domain personas that combine skills from multiple domains into a single expert:

startup-cto · growth-marketer · solo-founder · content-strategist · devops-engineer · finance-lead · product-manager · skill-creator

Activate with /persona startup-cto or just mention it in conversation. Add the 69 single-domain cs-* agents (e.g. cs-cto-advisor, cs-fintech-advisor, cs-scrum-master) for narrower expertise.

Deep-dive skill packs

Three multi-skill packs go deeper on a single topic: Playwright Pro (browser automation, 8 sub-skills), Self-Improving Agent (agents that evaluate their own outputs, 6 sub-skills), and AgentHub (multi-agent orchestration, 7 sub-skills). See standards/.

Slash commands

26 commands for common workflows: /tdd, /rice, /prd, /retro, /tech-debt, /security-scan, /sprint-plan, /changelog and more. Run /README in Claude Code for the full list, or see docs/commands/.

Ready-made kits by role

Pre-configured skill bundles for common roles:

SaaS Founder Kit · DevOps Kit · Compliance Kit · Growth Kit · Product Kit · Data Kit · Security Kit · Finance Kit · PM Starter Pack · PM Career Track

Install one bundle and the right set of skills lands in your project. See bundles.json.

Orchestration patterns

4 multi-agent patterns for complex workflows: sequential pipeline, parallel fan-out, supervisor delegation, and consensus voting. Defined in the Orchestration Protocol standard.

Works with your AI assistant

Platform Status
Claude Code Native
OpenAI Codex Native
Gemini CLI Native
Cursor Native
GitHub Copilot Native
Windsurf Native
Cline Native
Goose Native
Aider Compatible
Jules Compatible
RooCode Compatible

See docs/INSTALLATION.md for per-platform setup.

Documentation

Contributing

Contributions welcome. See CONTRIBUTING.md for guidelines. Fork the repo, create a skill following the Skill Authoring Standard, include Python tools and YAML frontmatter, and submit a PR.

Contributors

Contributor GitHub
Alan Pope @popey
Izzy @weemax
Rohan (Tessl) @rohan-tessl

Security acknowledgments

Thanks to @rishaankgupta for responsibly disclosing a shell-injection vulnerability (CWE-78) in the claude-code-review.yml workflow template. The fix hardened every workflow template against the same pattern.

Disclaimer

This project is built with the assistance of AI tools (Claude, GPT, etc.). While every effort is made to ensure accuracy, AI-generated content (including skill definitions, reference guides, Python tools, frameworks, and documentation) may contain errors, inaccuracies, or outdated information. Always verify critical information independently before using it in production, compliance, legal, financial, or safety-critical contexts. The authors accept no liability for decisions made based on the content in this repository. Use at your own risk.

License

MIT + Commons Clause. Free for open-source, personal, education, and internal business use. Cannot be sold or repackaged as a paid product. See LICENSE for full terms.

README fetched from the repository 1 hours ago. The original is authoritative.

Questions

About Claude Skills

How do I install Claude Skills?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Claude Skills safe to use with an AI agent?

Its trust score is 59 out of 100 (fair). It passes 4 of the 5 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Claude Skills still maintained?

Yes — the latest release is v4.13.0 (7 Oct 2026), and the last commit was 10 days ago. The repository has 940 stars and 2 open issues.