// Comprehensive Claude Code knowledge base — plugins, hooks, skills, agents, MCP, channels, headless mode, permissions, settings, and all extensibility features. Use when building, configuring, debugging, or extending Claude Code.
Use when building a skill, creating a SKILL.md, packaging a workflow, making a slash command, or asked "how do I make a skill". Scaffolds the folder, generates SKILL.md from a template, validates against spec. Produces a complete ready-to-deploy skill folder: scripts, references, assets. Also use to review or improve an existing skill.
Statistical analysis, hypothesis testing, A/B testing, cohort analysis, segmentation, trend detection, business metrics, pre-delivery validation, and data visualization. Use when the user asks to "analyze this data", "run a statistical test", "compare groups", "find trends", "do A/B test analysis", "segment customers", "calculate KPIs", "validate this analysis", "check my work", "sanity check", "review my numbers", "make a chart", "create a dashboard", "plot the data", "visualize results", or mentions hypothesis testing, cohort analysis, business analytics, data validation, bar charts, line charts, heatmaps, scatter plots, or data storytelling.
Autonomous time-budget experiment loop. Modify a training script, train for a fixed wall-clock budget, evaluate, record, repeat. Inspired by karpathy/autoresearch. Use for overnight architecture search, systematic hyperparameter sweeps, or any iterative model improvement workflow.
Context engineering for building production LLM applications: context window management, degradation patterns, optimization strategies, memory system selection, multi-agent architecture, filesystem context patterns, and tool design principles. Use when building LLM apps, RAG pipelines, AI agents, multi-agent systems, or when designing memory, tool APIs, or context strategies for any language model application.
Explore, clean, and engineer datasets end-to-end: statistical profiling, distribution checks, missing value analysis, duplicate detection, outlier removal, type fixing, encoding, create features, encode categories, transform columns, add rolling windows, build interaction terms, and feature engineering. Supports pandas, polars, and PySpark. Use when the user wants to explore data, profile columns, understand a dataset, clean data, handle missing values, remove duplicates, fix data types, preprocess a dataset before modeling, create features, encode categories, transform columns, add rolling windows, build interaction terms, or do feature engineering.
Detect data drift, concept drift, and model performance degradation in production. Uses PSI, KS-test, and chi-squared for statistical drift, plus evidently and nannyml for automated reports. Use when monitoring a deployed model or comparing training vs production data distributions.
| name | claude-code |
| description | Comprehensive Claude Code knowledge base — plugins, hooks, skills, agents, MCP, channels, headless mode, permissions, settings, and all extensibility features. Use when building, configuring, debugging, or extending Claude Code. |
| argument-hint | <Claude Code feature, topic, or question> — <what to configure, understand, or troubleshoot> |
| allowed-tools | Read, Glob, Grep, WebFetch, WebSearch |
The definitive reference skill for Claude Code's entire extensibility platform. This skill covers every feature area — from plugins and hooks to channels, subagents, MCP servers, scheduled tasks, and headless automation. When a user asks how to build, configure, debug, or extend Claude Code, this skill provides authoritative guidance grounded in the official documentation.
Documentation Index
Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt Use this file to discover all available pages before exploring further.
27 reference documents covering every Claude Code feature. Read the relevant reference(s) before answering any question.
| Reference | What It Covers |
|---|---|
| plugins.md | Creating plugins — manifest, agents, skills, hooks, commands, settings |
| plugins-reference.md | Plugin spec — plugin.json schema, variable resolution, file structure |
| plugin-marketplaces.md | Creating and distributing plugin marketplaces |
| discover-plugins.md | Discovering and installing prebuilt plugins |
| skills.md | Extending Claude with skills — SKILL.md format, frontmatter, scripts |
| sub-agents.md | Creating custom subagents — agent .md files, model routing, tools |
| Reference | What It Covers |
|---|---|
| hooks-guide.md | Hooks walkthrough — setup, common patterns, prompt/agent hooks |
| hooks-ref.md | Hooks reference — all 22 events, 4 handler types, input schemas, decision control |
| scheduled-tasks.md | Running prompts on a schedule (cron-style) |
| channels.md | Pushing events into a running session |
| channels-reference.md | Channels API reference — event types, protocols |
| Reference | What It Covers |
|---|---|
| agent-teams.md | Orchestrating teams of Claude Code sessions |
| headless.md | Running Claude Code programmatically (CI, scripts, pipelines) |
| Reference | What It Covers |
|---|---|
| settings.md | All Claude Code settings — global, project, plugin scopes |
| permissions.md | Permission modes, allow/deny lists, tool-level control |
| sandboxing.md | Sandbox environments — Docker, macOS sandbox, network isolation |
| model-config.md | Model selection, routing, provider configuration |
| network-config.md | Enterprise network — proxies, certificates, firewall rules |
| llm-gateway.md | LLM gateway configuration for enterprise deployments |
| Reference | What It Covers |
|---|---|
| tools-reference.md | Built-in tools — Read, Write, Edit, Bash, Glob, Grep, Agent, etc. |
| mcp.md | Connecting Claude Code to external tools via MCP servers |
| keybindings.md | Customizing keyboard shortcuts |
| statusline.md | Customizing the status line display |
| output-styles.md | Output formatting and style configuration |
| terminal-config.md | Terminal setup optimization |
| voice-dictation.md | Voice input configuration |
| troubleshooting.md | Common issues, diagnostics, and fixes |
| User Asks About | Read These References |
|---|---|
| Building a plugin | plugins.md, plugins-reference.md |
| Publishing to marketplace | plugin-marketplaces.md, discover-plugins.md |
| Writing a skill | skills.md, plugins.md |
| Creating an agent | sub-agents.md, plugins.md |
| Setting up hooks | hooks-guide.md, hooks-ref.md |
| Hook events / types | hooks-ref.md |
| MCP servers | mcp.md |
| Permissions / security | permissions.md, sandboxing.md |
| Settings config | settings.md |
| Running headless / CI | headless.md |
| Agent teams / multi-session | agent-teams.md, channels.md |
| Channels / events | channels.md, channels-reference.md |
| Scheduled / cron tasks | scheduled-tasks.md |
| Model selection | model-config.md |
| Enterprise / network | network-config.md, llm-gateway.md |
| Keyboard shortcuts | keybindings.md |
| Status line | statusline.md |
| Output formatting | output-styles.md |
| Terminal setup | terminal-config.md |
| Voice input | voice-dictation.md |
| Something broken | troubleshooting.md |
| Built-in tools | tools-reference.md |
$ARGUMENTS to Claude for yes/no.SessionStart, UserPromptSubmit, PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure, Notification, SubagentStart, SubagentStop, Stop, StopFailure, TeammateIdle, TaskCompleted, InstructionsLoaded, ConfigChange, WorktreeCreate, WorktreeRemove, PreCompact, PostCompact, Elicitation, ElicitationResult, SessionEnd
| Variable | Resolves To |
|---|---|
${CLAUDE_PLUGIN_ROOT} | Plugin's root directory |
${CLAUDE_PLUGIN_DATA} | Plugin's data/output directory |
${CLAUDE_SKILL_DIR} | Current skill's directory |
plugin-name/
├── .claude-plugin/plugin.json ← Manifest (required)
├── agents/*.md ← Role definitions
├── skills/*/SKILL.md ← Workflow definitions
├── commands/*.md ← Entry points
├── context/*.md ← Shared context
├── hooks/hooks.json ← Hook definitions
└── settings.json ← Plugin settings