Plugin suite + bundled MCP servers for Claude Code. Full delivery lifecycle: Agile pipeline with multi-model AI review, project bootstrap, documentation generation, codebase audits, performance optimization, community workflows. Includes hex-line (hash-verified editing), hex-graph (code knowledge graph), and hex-ssh (remote SSH) MCP servers.
# Add to your Claude Code skills
git clone https://github.com/levnikolaevich/claude-code-skillsGuides for using ai agents skills like claude-code-skills.
Last scanned: 5/18/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-18T08:03:46.777Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}claude-code-skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by levnikolaevich. Plugin suite + bundled MCP servers for Claude Code. Full delivery lifecycle: Agile pipeline with multi-model AI review, project bootstrap, documentation generation, codebase audits, performance optimization, community workflows. Includes hex-line (hash-verified editing), hex-graph (code knowledge graph), and hex-ssh (remote SSH) MCP servers. It has 515 GitHub stars.
Yes. claude-code-skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/levnikolaevich/claude-code-skills" and add it to your Claude Code skills directory (see the Installation section above).
claude-code-skills is primarily written in HTML. It is open-source under levnikolaevich on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh claude-code-skills against similar tools.
No comments yet. Be the first to share your thoughts!
A compact marketplace of standalone engineering skills for Claude Code and Codex.
Browse the Skills v2 catalog or install only the plugins you need below.
The repository intentionally contains only the skills, minimal plugin manifests, two host-specific marketplace catalogs, documentation, and a static catalog site. It has no MCP servers, orchestration hierarchy, distributed shared resources, generated skill copies, or evaluation harness.
| Index | Skill | Purpose |
|---|---|---|
| 11 | Plan Reviewer | Validate an implementation plan against repository evidence before execution. |
| 12 | Delivery Reviewer | Review completed code through independent risk-selected perspectives. |
| Index | Skill | Purpose |
|---|---|---|
| 21 | Documentation Auditor | Audit documentation trust, coverage, structure, and factual accuracy. |
| 22 | Codebase Auditor | Audit cross-cutting code health, security, delivery, and maintainability. |
| 23 | Test Suite Auditor | Audit test value, coverage, isolation, and oracle strength. |
| 24 | Architecture Auditor | Audit system boundaries, ownership, contracts, and dependency topology. |
| 25 | Persistence Auditor | Audit queries, transactions, consistency, and resource lifecycle. |
| Index | Skill | Purpose |
|---|---|---|
| 31 | Performance Optimizer | Profile, experiment, and keep only measured improvements. |
| 32 | Dependency Upgrader | Upgrade dependencies in reversible, verified batches. |
| 33 | Code Modernizer | Replace or simplify bounded capabilities when net value is proven. |
| 34 | Benchmark Comparator | Compare alternatives with a frozen, reproducible experiment contract. |
| Index | Skill | Purpose |
|---|---|---|
| 41 | Test Strategy Planner | Design a risk-based, decision-complete test strategy without changing code. |
| 42 | Acceptance Test Builder | Create reproducible acceptance tests through observable product boundaries. |
| Index | Skill | Purpose |
|---|---|---|
| 51 | Opportunity Evaluator | Compare product opportunities using current evidence and a low-cost validation path. |
Add the marketplace and install only the suites you need:
/plugin marketplace add levnikolaevich/claude-code-skills
/plugin install review-suite@levnikolaevich-skills-marketplace
/plugin install codebase-audit-suite@levnikolaevich-skills-marketplace
/plugin install optimization-suite@levnikolaevich-skills-marketplace
/plugin install testing-suite@levnikolaevich-skills-marketplace
/plugin install product-discovery-suite@levnikolaevich-skills-marketplace
For local development, load one plugin directly:
claude --plugin-dir ./plugins/review-suite
codex plugin marketplace add levnikolaevich/claude-code-skills
codex plugin add review-suite@levnikolaevich-skills-marketplace
codex plugin add codebase-audit-suite@levnikolaevich-skills-marketplace
codex plugin add optimization-suite@levnikolaevich-skills-marketplace
codex plugin add testing-suite@levnikolaevich-skills-marketplace
codex plugin add product-discovery-suite@levnikolaevich-skills-marketplace
.
├── .agents/plugins/marketplace.json # Codex catalog
├── .claude-plugin/marketplace.json # Claude Code catalog
└── plugins/
├── review-suite/
├── codebase-audit-suite/
├── optimization-suite/
├── testing-suite/
└── product-discovery-suite/
Each plugin contains .codex-plugin/plugin.json for Codex and a shared skills/<skill>/SKILL.md tree used by both hosts.
This is the smallest practical shared layout for distributed plugins:
skills/<name>/SKILL.md, so each skill has one canonical copy..codex-plugin/plugin.json for a plugin.skills/ directory from the marketplace entry, so duplicate per-plugin Claude manifests are unnecessary here.agents/openai.yaml, references, scripts, assets, hooks, agents, and MCP configuration are optional and omitted until a concrete need appears.The structure follows the current official Codex skill guide, Codex plugin guide, Claude Code skill guide, and Claude Code plugin reference.
Skills v2 replaces the broad workflow framework with small, standalone capabilities. Existing cached installations are not removed automatically: reinstall the desired v2 plugins and start a new Claude Code or Codex session after updating the marketplace.
| Previous plugin | v2 status |
|---|---|
agile-workflow |
Retired. Plan and delivery review moved to review-suite; focused audit, testing, optimization, and discovery work moved to their respective suites. Backlog orchestration and task execution are intentionally not retained. |
documentation-pipeline |
Retired. Read-only documentation assessment is covered by ln-21-documentation-auditor; document-generation pipelines are not retained. |
project-bootstrap |
Retired without replacement; use project-native setup and host-native tools. |
community-engagement |
Retired without replacement; it is outside the engineering-skill catalog. |
setup-environment |
Retired without replacement; host setup and MCP installation are no longer managed by these skills. |
Every published version of @levnikolaevich/hex-line-mcp, @levnikolaevich/hex-graph-mcp, @levnikolaevich/hex-research-mcp, and @levnikolaevich/hex-ssh-mcp is deprecated on npm. Their source and publishing infrastructure were removed from the active tree. The packages receive no updates or support and must not be used for new Skills v2 workflows; historical source remains in Git history and release tags.
The first digit identifies the plugin and the second identifies the skill within it: 1x review, 2x audit, 3x optimization, 4x testing, and 5x product discovery. See the canonical allocation and overflow rules in AGENTS.md.