Claude Code Skills

[!WARNING] Marketplace layout changed in the 2026-05-06 refactor. Skills now live only inside self-contained plugin bundles under plugins/<plugin>/skills/<skill>/. The root shared/ directory is maintainer-only source material for files reused by 2+ skills; runtime installs use the copied skill-local references/ files.

7 plugins. Two native marketplaces. Install only what you need and automate your full delivery workflow — from project bootstrap to code audit to production quality gates. Works standalone or as a complete Agile pipeline.

[!TIP] Two-Agent AI Review — Claude and Codex can review each other’s work through host-aware external advisor routing.

Plugins · Installation · Quick Start · Workflow · MCP · AI Review · FAQ · Full Skill Tree · Links

Plugins

Add the marketplace once, then install only the plugins you need. Each works independently.

# Claude Code: add the marketplace once
/plugin marketplace add levnikolaevich/claude-code-skills

# Claude Code: install any plugin you need
/plugin install agile-workflow@levnikolaevich-skills-marketplace
/plugin install documentation-pipeline@levnikolaevich-skills-marketplace
/plugin install codebase-audit-suite@levnikolaevich-skills-marketplace
/plugin install project-bootstrap@levnikolaevich-skills-marketplace
/plugin install optimization-suite@levnikolaevich-skills-marketplace
/plugin install community-engagement@levnikolaevich-skills-marketplace
/plugin install setup-environment@levnikolaevich-skills-marketplace

# Codex CLI: add the marketplace, then install from /plugins
codex plugin marketplace add levnikolaevich/claude-code-skills
codex
/plugins

Browse and discover individual skills at skills.sh.

[!NOTE] skills.sh is a showcase only. The supported install path is the Claude or Codex marketplace plugin flow above. Plugin bundles are self-contained; root shared/ is not a runtime dependency.

Installation

Prerequisites: Claude Code or OpenAI Codex CLI

# Claude Code
/plugin marketplace add levnikolaevich/claude-code-skills
/plugin install setup-environment@levnikolaevich-skills-marketplace

# Codex CLI
codex plugin marketplace add levnikolaevich/claude-code-skills
codex
/plugins

Verify: run ln-010-dev-environment-setup

Quick Start

Standalone (works immediately, no setup):

ln-010-dev-environment-setup  # Set up agents, MCP, and marketplace plugins
ln-620-codebase-auditor       # Audit your code for issues
ln-100-documents-pipeline     # Generate documentation

Full Agile workflow (Linear, GitHub Issues, or File Mode — chosen during ln-010 setup, persisted in .hex-skills/environment_state.json):

ln-200-scope-decomposer    # Scope -> Epics -> Stories
ln-1000-pipeline-orchestrator  # Artifact-driven pipeline: tasks → validation → execution → quality gate

Manual step-by-step (if you prefer control over each stage):

ln-400-story-executor      # Execute Story tasks
ln-500-story-quality-gate  # Quality gate + test planning

Workflow

ln-010-dev-environment-setup    # 0. Set up dev environment (once)
         ↓
ln-100-documents-pipeline       # 1. Documentation
         ↓
ln-200-scope-decomposer         # 2. Scope -> Epics -> Stories
         ↓
ln-1000-pipeline-orchestrator   # 3. Full artifact-driven pipeline: 300 → 310 → 400 → 500 → Done

Coordinators keep lifecycle status separate from Loop Health: status says where the run is, artifacts/checkpoints prove completion, and loop_health decides whether another retry is useful. Procedural skills use SOP/TWI-style point-of-use checklists so risky steps carry action, key point, why, evidence, exception, and guard close to the moment of use.

MCP Servers (Optional)

Bundled MCP servers extend agent capabilities — hash-verified editing, code intelligence, remote access, and research graph navigation. All skills work without MCP (fallback to built-in tools), but MCP servers improve accuracy and save tokens. MCP errors stay as status: "ERROR" and include failure_class, next_action, and recovery fields so skills can feed transport/tool/auth/rate-limit signals into Loop Health without inventing a second retry loop.

Bundled servers

Deterministic scope rule: hex-line, hex-graph, and hex-research keep path as the project anchor. In normal use the agent fills it automatically from the active file or project root, so users usually do not need to type it manually. hex-research writes its local index under .hex-skills/researchgraph/. hex-ssh runs on Windows/macOS/Linux hosts; remote shell tools stay POSIX-oriented, while SFTP transfers support platform-aware remote paths.

hex-graph-mcp quality snapshot: semantic suite, corpus manifests, provider lanes, and parser-first green status are tracked in package artifacts.

External servers

CLI setup:

# hex-line — hash-verified file editing (bundled)
claude mcp add -s user hex-line -- npx -y @levnikolaevich/hex-line-mcp

# hex-ssh — token-efficient SSH with hash verification (bundled)
claude mcp add -s user hex-ssh -- npx -y @levnikolaevich/hex-ssh-mcp

# hex-graph — code knowledge graph (bundled)
claude mcp add -s user hex-graph -- npx -y @levnikolaevich/hex-graph-mcp

# hex-research — research hypothesis graph (bundled)
claude mcp add -s user hex-research -- npx -y @levnikolaevich/hex-research-mcp

# Context7 — library documentation (HTTP, optional API key)
claude mcp add -s user --transport http --header "CONTEXT7_API_KEY: YOUR_KEY" context7 https://mcp.context7.com/mcp

# Ref — standards & best practices (HTTP, API key required)
claude mcp add -s user --transport http --header "x-ref-api-key: YOUR_KEY" Ref https://api.ref.tools/mcp

# Linear — issue tracking (HTTP, OAuth via browser)
claude mcp add -s user --transport http linear-server https://mcp.linear.app/mcp

Agent steering

MCP servers can be installed correctly and still lose to built-ins in practice. hex-line-mcp keeps Claude aligned through one output style and five Claude hook events: