diff --git a/README.md b/README.md
index d56149c..8f359cd 100644
--- a/README.md
+++ b/README.md
@@ -21,9 +21,9 @@ practice makes claude perfect
 
 | Feature | Location | Description |
 |---------|----------|-------------|
-| [**Commands**](https://code.claude.com/docs/en/slash-commands) | `.claude/commands/<name>.md` | [![Best Practice](!/tags/best-practice.svg)](best-practice/claude-commands.md) [![Implemented](!/tags/implemented.svg)](implementation/claude-commands-implementation.md) Entry-point prompts for workflows — invoke with `/command-name` |
-| [**Sub-Agents**](https://code.claude.com/docs/en/sub-agents) | `.claude/agents/<name>.md` | [![Best Practice](!/tags/best-practice.svg)](best-practice/claude-subagents.md) [![Implemented](!/tags/implemented.svg)](implementation/claude-subagents-implementation.md) Custom agents with their own name, color, tools, permissions, and model |
-| [**Skills**](https://code.claude.com/docs/en/skills) | `.claude/skills/<name>/SKILL.md` | [![Best Practice](!/tags/best-practice.svg)](best-practice/claude-skills.md) [![Implemented](!/tags/implemented.svg)](implementation/claude-skills-implementation.md) Reusable knowledge, workflows, and slash commands — load on-demand or invoke with `/skill-name` |
+| [**Commands**](https://code.claude.com/docs/en/slash-commands) | `.claude/commands/<name>.md` | [![Best Practice](!/tags/best-practice.svg)](best-practice/claude-commands.md) [![Implemented](!/tags/implemented.svg)](implementation/claude-commands-implementation.md) Knowledge injected into existing context — simple user-invoked prompt templates for workflow orchestration |
+| [**Sub-Agents**](https://code.claude.com/docs/en/sub-agents) | `.claude/agents/<name>.md` | [![Best Practice](!/tags/best-practice.svg)](best-practice/claude-subagents.md) [![Implemented](!/tags/implemented.svg)](implementation/claude-subagents-implementation.md) Autonomous actor in fresh isolated context — custom tools, permissions, model, memory, and persistent identity |
+| [**Skills**](https://code.claude.com/docs/en/skills) | `.claude/skills/<name>/SKILL.md` | [![Best Practice](!/tags/best-practice.svg)](best-practice/claude-skills.md) [![Implemented](!/tags/implemented.svg)](implementation/claude-skills-implementation.md) Knowledge injected into existing context — configurable, preloadable, auto-discoverable, with context forking and progressive disclosure · [Official Skills](https://github.com/anthropics/skills/tree/main/skills) |
 | [**Workflows**](https://code.claude.com/docs/en/common-workflows) | [`.claude/commands/weather-orchestrator.md`](.claude/commands/weather-orchestrator.md) | [![Orchestration Workflow](!/tags/orchestration-workflow.svg)](orchestration-workflow/orchestration-workflow.md) |
 | [**Hooks**](https://code.claude.com/docs/en/hooks) | `.claude/hooks/` | [![Best Practice](!/tags/best-practice.svg)](https://github.com/shanraisshan/claude-code-voice-hooks) [![Implemented](!/tags/implemented.svg)](https://github.com/shanraisshan/claude-code-voice-hooks) Deterministic scripts that run outside the agentic loop on specific events |
 | [**MCP Servers**](https://code.claude.com/docs/en/mcp) | `.claude/settings.json`, `.mcp.json` | [![Best Practice](!/tags/best-practice.svg)](best-practice/claude-mcp.md) [![Implemented](!/tags/implemented.svg)](.mcp.json) Model Context Protocol connections to external tools, databases, and APIs |