CalvinBackup/claude-howto
1
0
Fork 0
mirror of https://github.com/luongnv89/claude-howto.git synced 2026-05-27 22:22:36 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: sync to Claude Code v2.1.150 (#127)

Browse Source 
* docs: sync to Claude Code v2.1.150

* fix(README): bump stale version prose to v2.1.150
This commit is contained in:
Luong NGUYEN
2026-05-26 08:58:44 +02:00
committed by GitHub
parent 46941a38fc
commit 5850da9a14
24 changed files with 150 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files
01-slash-commands/README.md
+3 -3
View File
@@ -107,7 +107,7 @@ These skills ship with Claude Code and are invoked like slash commands:
| `/claude-api` | Load Claude API reference for project language |
| `/debug [description]` | Enable debug logging |
| `/loop [interval] <prompt>` | Run prompt repeatedly on interval |
| `/simplify [focus]` | Review changed files for code quality |
| `/code-review [effort]` | Review the current diff for correctness bugs at a chosen effort level (e.g. `/code-review high`); renamed from `/simplify` in v2.1.146 |
### Deprecated Commands
@@ -620,8 +620,8 @@ If both exist with the same name, the **skill takes precedence**. Remove one or
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/slash-commands
- https://code.claude.com/docs/en/interactive-mode
02-memory/README.md
+2 -2
View File
@@ -1198,8 +1198,8 @@ For the most up-to-date information, refer to the official Claude Code documenta
- [Official Memory Docs](https://code.claude.com/docs/en/memory) - Anthropic documentation
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/memory
- https://code.claude.com/docs/en/settings
03-skills/README.md
+9 -7
View File
@@ -75,7 +75,7 @@ sequenceDiagram
Claude->>System: Check available skills (metadata)
System-->>Claude: Skill descriptions loaded at startup
Claude->>Claude: Match request to skill description
Claude->>SkillInst: Read code-review/SKILL.md
Claude->>SkillInst: Read code-review-specialist/SKILL.md
SkillInst-->>Claude: Level 2: Instructions loaded
Claude->>Claude: Determine: Need templates?
Claude->>SkillRes: Read templates/checklist.md
@@ -334,7 +334,7 @@ Research $ARGUMENTS thoroughly:
**Directory Structure:**
```
~/.claude/skills/code-review/
~/.claude/skills/code-review-specialist/
├── SKILL.md
├── templates/
│ ├── review-checklist.md
@@ -344,7 +344,7 @@ Research $ARGUMENTS thoroughly:
└── compare-complexity.py
```
**File:** `~/.claude/skills/code-review/SKILL.md`
**File:** `~/.claude/skills/code-review-specialist/SKILL.md`
```yaml
---
@@ -616,9 +616,11 @@ Can you help me review this code for security issues?
**Or invoke it directly** with the skill name:
```
/code-review src/auth/login.ts
/code-review-specialist src/auth/login.ts
```
> **Note**: This local skill is installed as `code-review-specialist` so it does **not** collide with the built-in `/code-review` command (the renamed `/simplify`, shipped in Claude Code v2.1.146). If you copy it to `~/.claude/skills/code-review/` instead, it will shadow the built-in — keep the `-specialist` suffix to avoid that.
### Updating a Skill
Edit the `SKILL.md` file directly. Changes take effect on next Claude Code startup.
@@ -805,7 +807,7 @@ Claude Code ships with nine built-in skills that are always available without in
| `/loop [interval] <prompt>` | Run prompt repeatedly on interval (e.g., `/loop 5m check the deploy`) |
| `/run` *(v2.1.145+)* | Launch this project's app to see a change running — looks for a project skill, otherwise falls back to built-in patterns per project type |
| `/run-skill-generator` *(v2.1.145+)* | Teach `/run`/`/verify` how to handle a specific project by generating a per-project skill |
| `/simplify` | Review changed files for reuse, quality, and efficiency; spawns 3 parallel review agents |
| `/code-review [effort]` | Review the current diff for correctness bugs at a chosen effort level (e.g. `/code-review high`); pass `--comment` to post findings as inline PR comments. Renamed from `/simplify` in v2.1.146 |
| `/verify` *(v2.1.145+)* | Build, run, and observe the app to confirm a fix works (not just that tests pass) |
These skills are available out-of-the-box and do not need to be installed or configured. They follow the same SKILL.md format as custom skills.
@@ -852,8 +854,8 @@ Once you start building skills seriously, two things become essential: a library
- [Hooks Guide](../06-hooks/) - Event-driven automation
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/skills
- https://code.claude.com/docs/en/settings
03-skills/code-review/SKILL.md → 03-skills/code-review-specialist/SKILL.md
View File
03-skills/code-review/scripts/analyze-metrics.py → 03-skills/code-review-specialist/scripts/analyze-metrics.py
View File
03-skills/code-review/scripts/compare-complexity.py → 03-skills/code-review-specialist/scripts/compare-complexity.py
View File
03-skills/code-review/templates/finding-template.md → 03-skills/code-review-specialist/templates/finding-template.md
View File
03-skills/code-review/templates/review-checklist.md → 03-skills/code-review-specialist/templates/review-checklist.md
View File
04-subagents/README.md
+2 -2
View File
@@ -1238,8 +1238,8 @@ See the OpenTelemetry section in [Advanced Features → Telemetry](../09-advance
---
**Last Updated**: May 19, 2026
**Claude Code Version**: 2.1.143
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/sub-agents
- https://code.claude.com/docs/en/agent-teams
05-mcp/README.md
+3 -2
View File
@@ -695,6 +695,7 @@ For enterprise deployments, IT administrators can enforce MCP server policies th
**Features:**
- `allowedMcpServers` -- whitelist of permitted servers
- `deniedMcpServers` -- blocklist of prohibited servers
- `allowAllClaudeAiMcps` -- managed setting that permits loading claude.ai cloud MCP connectors organization-wide (v2.1.149+)
- Supports matching by server name, command, and URL patterns
- Organization-wide MCP policies enforced before user configuration
- Prevents unauthorized server connections
@@ -1167,8 +1168,8 @@ export GITHUB_TOKEN="your_token"
---
**Last Updated**: May 19, 2026
**Claude Code Version**: 2.1.143
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/mcp
- https://code.claude.com/docs/en/changelog
06-hooks/README.md
+2 -8
View File
@@ -348,12 +348,6 @@ Run when Claude finishes responding (Stop) or a subagent completes (SubagentStop
**Additional input field:** Both `Stop` and `SubagentStop` hooks receive a `last_assistant_message` field in their JSON input, containing the final message from Claude or the subagent before stopping. This is useful for evaluating task completion.
**v2.1.145 additions:** The `Stop` and `SubagentStop` hook inputs now also include two arrays:
- `background_tasks` — any background tasks the session has spawned (handy for blocking stop until work finishes).
- `session_crons` — any cron jobs (`/schedule`) created during the session.
Hook authors can read these to decide whether to block stop — for example, "don't stop while a background test run or scheduled task is still pending."
**Configuration:**
```json
{
@@ -1440,8 +1434,8 @@ Edit `~/.claude/settings.json` or `.claude/settings.json` with the hook configur
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/hooks
- https://code.claude.com/docs/en/changelog
07-plugins/README.md
+2 -2
View File
@@ -1105,8 +1105,8 @@ The following Claude Code features work together with plugins:
---
**Last Updated**: May 19, 2026
**Claude Code Version**: 2.1.143
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/plugins
- https://code.claude.com/docs/en/plugin-marketplaces
08-checkpoints/README.md
+2 -2
View File
@@ -325,8 +325,8 @@ Remember: checkpoints are not a replacement for git. Use checkpoints for rapid e
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/checkpointing
- https://code.claude.com/docs/en/settings
09-advanced-features/README.md
+3 -3
View File
@@ -1649,7 +1649,7 @@ Transfer your current CLI session to the Desktop App:
| **PR monitoring** | GitHub CLI integration with auto-fix CI failures and auto-merge when checks pass |
| **Parallel sessions** | Multiple sessions in the sidebar with automatic Git worktree isolation |
| **Scheduled tasks** | Recurring tasks (hourly, daily, weekdays, weekly) that run while the app is open |
| **Rich rendering** | Code, markdown, and diagram rendering with syntax highlighting |
| **Rich rendering** | Code, markdown, and diagram rendering with syntax highlighting; GitHub-Flavored-Markdown task-list checkboxes (`- [ ]` / `- [x]`) render as checkboxes (v2.1.149+) |
### App preview configuration
@@ -2267,8 +2267,8 @@ For more information about Claude Code and related features:
---
**Last Updated**: May 19, 2026
**Claude Code Version**: 2.1.143
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/permission-modes
- https://code.claude.com/docs/en/interactive-mode
10-cli/README.md
+4 -2
View File
@@ -490,6 +490,8 @@ When you dispatch a session from the view (or via `claude --bg <prompt>`), you c
Sessions that finish their work but leave a background shell open move from "Working" to "Completed" (v2.1.141 fix). Within an attached agent session, `Shift+Tab` cycles through permission modes including auto mode (v2.1.143).
**Pin a session** — press `Ctrl+T` on a session in `claude agents` to pin it (v2.1.147). Pinned background sessions stay alive when idle, are restarted in place to apply Claude Code updates, and are shed under memory pressure only after non-pinned sessions. (This `Ctrl+T` is scoped to the Agent View; in the main session it toggles the task list view.)
---
## High-Value Use Cases
@@ -939,8 +941,8 @@ claude -p --output-format json "query"
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/cli-reference
- https://code.claude.com/docs/en/settings
CATALOG.md
+5 -5
View File
@@ -80,7 +80,7 @@ Commands are user-invoked shortcuts that execute specific actions.
| `/teleport` | Transfer session to another machine | Continue work remotely |
| `/desktop` | Open Claude Desktop app | Switch to desktop interface |
| `/theme` | Change color theme; v2.1.118 added custom named themes via `~/.claude/themes/<name>.json` (plugins can ship a `themes/` dir) | Customize appearance |
| `/usage` | Canonical command for usage/cost/stats — merged `/cost` and `/stats` into a single tabbed view (v2.1.118) | Monitor quota and costs |
| `/usage` | Canonical command for usage/cost/stats — merged `/cost` and `/stats` into a single tabbed view (v2.1.118); as of v2.1.149 the cost view breaks spending down by category (skills, subagents, plugins, per-MCP-server) | Monitor quota and costs |
| `/focus` | Toggle focus view (distraction-free output display) | Reduce visual noise during long tasks |
| `/fork` | Fork current conversation | Explore alternatives |
| `/stats` | Shortcut alias that opens the stats tab of `/usage` (v2.1.118+) | Review session metrics |
@@ -200,7 +200,7 @@ Auto-invoked capabilities with instructions, scripts, and templates.
| Skill | Description | When Auto-Invoked | Scope | Installation |
|-------|-------------|-------------------|-------|--------------|
| `code-review` | Comprehensive code review | "Review this code", "Check quality" | Project | `cp -r 03-skills/code-review .claude/skills/` |
| `code-review-specialist` | Comprehensive code review | "Review this code", "Check quality" | Project | `cp -r 03-skills/code-review-specialist .claude/skills/` |
| `brand-voice` | Brand consistency checker | Writing marketing copy | Project | `cp -r 03-skills/brand-voice .claude/skills/` |
| `doc-generator` | API documentation generator | "Generate docs", "Document API" | Project | `cp -r 03-skills/doc-generator .claude/skills/` |
| `refactor` | Systematic code refactoring (Martin Fowler) | "Refactor this", "Clean up code" | User | `cp -r 03-skills/refactor ~/.claude/skills/` |
@@ -246,7 +246,7 @@ cp -r 03-skills/* ~/.claude/skills/
| `/loop` | Run prompts on interval | Recurring tasks |
| `/run` *(v2.1.145+)* | Launch this project's app to see a change running | Verifying a change in the real app |
| `/run-skill-generator` *(v2.1.145+)* | Teach `/run`/`/verify` how to handle a specific project | First-time project setup for `/run` |
| `/simplify` | Review code for quality | After writing code |
| `/code-review` *(renamed from `/simplify` in v2.1.146)* | Review the current diff for correctness bugs at a chosen effort level (e.g. `/code-review high`); pass `--comment` to post findings as inline PR comments | After writing code, before landing a PR |
| `/verify` *(v2.1.145+)* | Build, run, and observe the app to confirm a fix works | Validating a fix end-to-end |
---
@@ -538,8 +538,8 @@ chmod +x ~/.claude/hooks/*.sh
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/overview
- https://code.claude.com/docs/en/commands
CHANGELOG.md
+71
View File
@@ -1,5 +1,76 @@
# Changelog
## [v2.1.150] — 2026-05-25
### Synced to Claude Code v2.1.150
Bumps tutorial coverage from Claude Code v2.1.145 → v2.1.150 (May 23, 2026
release). Anthropic shipped five patches (v2.1.146 through v2.1.150) since the
last sync. The headline change is the **rename of the bundled `/simplify`
skill to `/code-review`** (v2.1.146) — a pure rename with **no alias**, so the
old name no longer works. Because this repo also ships its own local
code-review skill, the directory was renamed to `code-review-specialist` to
avoid shadowing the new built-in. Other highlights: `/usage` now breaks costs
down per category, background sessions can be pinned with `Ctrl+T`, the
markdown renderer supports GFM task-list checkboxes, and a new
`allowAllClaudeAiMcps` managed setting was added. This sync also catches up
four module READMEs (`04-subagents`, `05-mcp`, `07-plugins`,
`09-advanced-features`) that were still pinned to v2.1.143.
### Behavior changes
- **`/simplify` renamed to `/code-review` (v2.1.146)**: the bundled review
skill is now invoked as `/code-review` and takes an optional effort level
(e.g. `/code-review high`); pass `--comment` to post findings as inline
GitHub PR comments (v2.1.147). The old `/simplify` name no longer works —
there is no alias. Updated in `01-slash-commands/README.md`,
`03-skills/README.md`, `CATALOG.md`, `QUICK_REFERENCE.md`, and
`claude_concepts_guide.md`.
### Changed
- **Renamed the repo's local `code-review` skill to `code-review-specialist`**
to avoid colliding with the new built-in `/code-review`. The directory
`03-skills/code-review/` → `03-skills/code-review-specialist/`, and all
install commands, directory trees, and cross-references were updated in
`README.md`, `QUICK_REFERENCE.md`, `INDEX.md`, `CATALOG.md`,
`LEARNING-ROADMAP.md`, `claude_concepts_guide.md`, and `03-skills/README.md`.
Added a note explaining the collision and how to avoid shadowing the
built-in.
### Added
- **`/usage` per-category cost breakdown (v2.1.149)** — the cost view now
breaks spending down by category (skills, subagents, plugins, and
per-MCP-server costs). Documented in `CATALOG.md` and
`claude_concepts_guide.md`.
- **Pinned background sessions — `Ctrl+T` (v2.1.147)** — pinning a session in
`claude agents` keeps it alive when idle, restarts it in place to apply
Claude Code updates, and sheds it under memory pressure only after
non-pinned sessions. Documented in `10-cli/README.md`.
- **GFM task-list checkbox rendering (v2.1.149)** — the markdown renderer now
renders `- [ ]` / `- [x]` as checkboxes. Documented in
`09-advanced-features/README.md`.
- **`allowAllClaudeAiMcps` managed setting (v2.1.149)** — permits loading
claude.ai cloud MCP connectors organization-wide. Documented in
`05-mcp/README.md`.
### Removed
- **Stop/SubagentStop hook input fields `background_tasks` and `session_crons`**
— removed from `06-hooks/README.md` and `resources.md`. These were added from
the v2.1.145 release notes but are not enumerated in the official hooks
reference page; removed to keep the docs aligned with the published
reference.
### Documentation
- Caught up four module READMEs from v2.1.143 to v2.1.150:
`04-subagents/README.md`, `05-mcp/README.md`, `07-plugins/README.md`,
`09-advanced-features/README.md`.
- Bumped every English doc's metadata footer to **v2.1.150 / May 25, 2026** for
a consistent sync.
## [v2.1.145] — 2026-05-20
### Synced to Claude Code v2.1.145
INDEX.md
+7 -7
View File
@@ -66,7 +66,7 @@ Auto-invoked capabilities with scripts and templates.
### Code Review Skill (5 files)
```
code-review/
code-review-specialist/
├── SKILL.md # Skill definition
├── scripts/
│ ├── analyze-metrics.py # Code metrics analyzer
@@ -515,7 +515,7 @@ claude-howto/
│ └── README.md
│
├── 03-skills/ # Skills
│ ├── code-review/
│ ├── code-review-specialist/
│ │ ├── SKILL.md
│ │ ├── scripts/
│ │ │ ├── analyze-metrics.py
@@ -666,7 +666,7 @@ cp 01-slash-commands/optimize.md .claude/commands/
cp 04-subagents/code-reviewer.md .claude/agents/
# Install skill
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Or install complete plugin
/plugin install pr-review
@@ -808,12 +808,12 @@ Run tests in background
### Performance
- `01-slash-commands/optimize.md` - Performance analysis
- `04-subagents/code-reviewer.md` - Performance review
- `03-skills/code-review/` - Performance metrics
- `03-skills/code-review-specialist/` - Performance metrics
- `07-plugins/pr-review/agents/performance-analyzer.md` - Performance specialist
### Security
- `04-subagents/secure-reviewer.md` - Security review
- `03-skills/code-review/` - Security analysis
- `03-skills/code-review-specialist/` - Security analysis
- `07-plugins/pr-review/` - Security checks
### Testing
@@ -874,8 +874,8 @@ Want to add more examples? Follow the structure:
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/overview
- https://code.claude.com/docs/en/hooks
LEARNING-ROADMAP.md
+4 -4
View File
@@ -244,7 +244,7 @@ Before starting Level 2, make sure you're comfortable with these Level 1 concept
```bash
# Exercise 1: Install a skill
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Exercise 2: Set up hooks
mkdir -p ~/.claude/hooks
@@ -543,7 +543,7 @@ This repository includes two interactive skills you can use anytime in Claude Co
1. **Slash commands** (15 min): Copy and test `/optimize` and `/pr`
2. **Project memory** (15 min): Create CLAUDE.md with your project standards
3. **Install a skill** (15 min): Set up code-review skill
3. **Install a skill** (15 min): Set up code-review-specialist skill
4. **Try them together** (15 min): See how they work in harmony
**Outcome**: Basic productivity boost with commands, memory, and auto-skills
@@ -738,8 +738,8 @@ Once you've completed all milestones:
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/overview
- https://code.claude.com/docs/en/hooks
QUICK_REFERENCE.md
+8 -8
View File
@@ -28,10 +28,10 @@ cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md
### Skills
```bash
# Personal skills
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Project skills
cp -r 03-skills/code-review .claude/skills/
cp -r 03-skills/code-review-specialist .claude/skills/
```
### Subagents
@@ -130,7 +130,7 @@ claude -r "session" # Resume session by name/ID
| **Git Worktrees** | Built-in | `/worktree` |
| **Auto Memory** | Built-in | Auto-saves to CLAUDE.md |
| **Task List** | Built-in | `/task list` |
| **Bundled Skills (9)** | Built-in | `/batch`, `/claude-api`, `/debug`, `/fewer-permission-prompts`, `/loop`, `/run` *(v2.1.145+)*, `/run-skill-generator` *(v2.1.145+)*, `/simplify`, `/verify` *(v2.1.145+)* |
| **Bundled Skills (9)** | Built-in | `/batch`, `/claude-api`, `/code-review` *(renamed from `/simplify` in v2.1.146)*, `/debug`, `/fewer-permission-prompts`, `/loop`, `/run` *(v2.1.145+)*, `/run-skill-generator` *(v2.1.145+)*, `/verify` *(v2.1.145+)* |
---
@@ -147,7 +147,7 @@ cp 04-subagents/code-reviewer.md .claude/agents/
# Use: Auto-delegated
# Method 3: Skill
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Use: Auto-invoked
# Method 4: Plugin (best)
@@ -363,7 +363,7 @@ cp 05-mcp/github-mcp.json .mcp.json
### Week 2
```bash
# Install skill
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Let it auto-invoke
# Just say: "Review this code for issues"
@@ -445,7 +445,7 @@ echo $GITHUB_TOKEN
|------|----------|---------|
| Quick shortcut | Slash Command (60+) | `01-slash-commands/optimize.md` |
| Team standards | Memory | `02-memory/project-CLAUDE.md` |
| Auto workflow | Skill | `03-skills/code-review/` |
| Auto workflow | Skill | `03-skills/code-review-specialist/` |
| Specialized task | Subagent | `04-subagents/code-reviewer.md` |
| External data | MCP (+ Elicitation) | `05-mcp/github-mcp.json` |
| Event automation | Hook (29 events, 5 types) | `06-hooks/pre-commit.sh` |
@@ -508,8 +508,8 @@ Getting started checklist:
**This Card**: Keep it handy for quick reference!
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/overview
- https://code.claude.com/docs/en/hooks
README.md
+11 -11
View File
@@ -102,7 +102,7 @@ Run `/lesson-quiz [topic]` after each module. The quiz pinpoints what you missed
- **GitHub stars** from developers who use Claude Code daily
- **Forks** from teams adapting this guide for their own workflows
- **Actively maintained** — synced with every Claude Code release (latest: v2.1.145, May 2026)
- **Actively maintained** — synced with every Claude Code release (latest: v2.1.150, May 2026)
- **Community-driven** — contributions from developers who share their real-world configurations
[![Star History Chart](https://api.star-history.com/svg?repos=luongnv89/claude-howto&type=Date)](https://star-history.com/#luongnv89/claude-howto&Date)
@@ -158,7 +158,7 @@ cp 01-slash-commands/optimize.md /path/to/your-project/.claude/commands/
cp 02-memory/project-CLAUDE.md /path/to/your-project/CLAUDE.md
# 5. Install a skill:
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
```
Want the full setup? Here's the **1-hour essential setup**:
@@ -171,7 +171,7 @@ cp 01-slash-commands/*.md .claude/commands/
cp 02-memory/project-CLAUDE.md ./CLAUDE.md
# Install a skill (15 min)
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Weekend goal: add hooks, subagents, MCP, and plugins
# Follow the learning path for guided setup
@@ -201,7 +201,7 @@ cp -r 03-skills/code-review ~/.claude/skills/
Yes. MIT licensed, free forever. Use it in personal projects, at work, in your team — no restrictions beyond including the license notice.
**Is this maintained?**
Actively. The guide is synced with every Claude Code release. Current version: v2.1.145 (May 2026), compatible with Claude Code 2.1+.
Actively. The guide is synced with every Claude Code release. Current version: v2.1.150 (May 2026), compatible with Claude Code 2.1+.
**How is this different from the official docs?**
The official docs are a feature reference. This guide is a tutorial with diagrams, production-ready templates, and a progressive learning path. They complement each other — start here to learn, reference the docs when you need specifics.
@@ -280,7 +280,7 @@ cp 01-slash-commands/*.md .claude/commands/
cp 02-memory/project-CLAUDE.md ./CLAUDE.md
# Skills
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Subagents
cp 04-subagents/*.md .claude/agents/
@@ -373,17 +373,17 @@ cp 02-memory/personal-CLAUDE.md ~/.claude/CLAUDE.md
**What**: Reusable, auto-invoked capabilities with instructions and scripts
**Examples**:
- `code-review/` - Comprehensive code review with scripts
- `code-review-specialist/` - Comprehensive code review with scripts
- `brand-voice/` - Brand voice consistency checker
- `doc-generator/` - API documentation generator
**Installation**:
```bash
# Personal skills
cp -r 03-skills/code-review ~/.claude/skills/
cp -r 03-skills/code-review-specialist ~/.claude/skills/
# Project skills
cp -r 03-skills/code-review /path/to/project/.claude/skills/
cp -r 03-skills/code-review-specialist /path/to/project/.claude/skills/
```
**Usage**: Automatically invoked when relevant
@@ -664,7 +664,7 @@ Claude:
│ ├── personal-CLAUDE.md
│ └── README.md
├── 03-skills/
│ ├── code-review/
│ ├── code-review-specialist/
│ │ ├── SKILL.md
│ │ ├── scripts/
│ │ └── templates/
@@ -871,8 +871,8 @@ MIT License - see [LICENSE](LICENSE). Free to use, modify, and distribute. The o
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/overview
- https://code.claude.com/docs/en/changelog
STYLE_GUIDE.md
+4 -4
View File
@@ -597,8 +597,8 @@ Lesson READMEs end with a metadata block:
```markdown
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Compatible Models**: Claude Sonnet 4.6, Claude Opus 4.7, Claude Haiku 4.5
```
@@ -631,8 +631,8 @@ Before submitting content, verify:
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/overview
- https://code.claude.com/docs/en/changelog
claude_concepts_guide.md
+6 -6
View File
@@ -1312,7 +1312,7 @@ Claude Code now includes 5 bundled skills available out of the box:
| Skill | Command | Purpose |
|-------|---------|---------|
| **Simplify** | `/simplify` | Simplify complex code or explanations |
| **Code Review** | `/code-review` | Review the current diff for correctness bugs at a chosen effort level (renamed from `/simplify` in v2.1.146) |
| **Batch** | `/batch` | Run operations across multiple files or items |
| **Debug** | `/debug` | Systematic debugging of issues with root cause analysis |
| **Loop** | `/loop` | Schedule recurring tasks on a timer |
@@ -1327,7 +1327,7 @@ These bundled skills are always available and do not require installation or con
**Directory Structure:**
```
~/.claude/skills/code-review/
~/.claude/skills/code-review-specialist/
├── SKILL.md
├── templates/
│ ├── review-checklist.md
@@ -1337,7 +1337,7 @@ These bundled skills are always available and do not require installation or con
└── compare-complexity.py
```
**File:** `~/.claude/skills/code-review/SKILL.md`
**File:** `~/.claude/skills/code-review-specialist/SKILL.md`
```yaml
---
@@ -3133,7 +3133,7 @@ Claude Code supports three models with adaptive reasoning effort:
> **Note**: v2.1.117 fixed a bug where Opus 4.7 sessions computed `/context` against 200K instead of the native 1M window — upgrade to v2.1.117 or later to actually get the 1M context on Opus 4.7.
> **Note**: `/cost` and `/stats` merged into `/usage` in v2.1.118. `/usage` is now the canonical command with tabs for cost/stats/etc.; `/cost` and `/stats` remain as shortcut aliases that open the corresponding tab.
> **Note**: `/cost` and `/stats` merged into `/usage` in v2.1.118. `/usage` is now the canonical command with tabs for cost/stats/etc.; `/cost` and `/stats` remain as shortcut aliases that open the corresponding tab. As of v2.1.149, the cost view also breaks spending down by category (skills, subagents, plugins, and per-MCP-server costs).
## Resources
@@ -3143,8 +3143,8 @@ Claude Code supports three models with adaptive reasoning effort:
- [Anthropic Cookbook](https://github.com/anthropics/anthropic-cookbook)
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/overview
- https://code.claude.com/docs/en/hooks
resources.md
+2 -3
View File
@@ -250,11 +250,10 @@ These steps capture the core recommendations for smooth workflows with Claude Co
| **/goal mode** | Register a session-level completion condition; Claude keeps working until met (v2.1.139+) | [Slash Commands](01-slash-commands/) |
| **claude agents (Agent View)** | List, inspect, and resume background agents from the terminal; `--json` for machine-readable output (v2.1.139+, `--json` added v2.1.145) | [code.claude.com/docs/en/agent-view](https://code.claude.com/docs/en/agent-view) |
| **/run, /verify, /run-skill-generator** | Bundled skills to launch your project, confirm a fix works, and generate per-project run/verify skills (v2.1.145+) | [Skills Guide](03-skills/) |
| **Stop/SubagentStop hook fields** | Stop and SubagentStop hook inputs now include `background_tasks` and `session_crons` (v2.1.145+) | [Hooks Guide](06-hooks/) |
---
**Last Updated**: May 20, 2026
**Claude Code Version**: 2.1.145
**Last Updated**: May 25, 2026
**Claude Code Version**: 2.1.150
**Sources**:
- https://code.claude.com/docs/en/overview
- https://code.claude.com/docs/en/changelog