Update Claude Code config and refine skills

Author: feiskyer

.claude-plugin/marketplace.json

@@ -4,15 +4,15 @@
     "name": "Pengfei Ni"
   },
   "metadata": {
-    "version": "2.1.5",
+    "version": "2.1.6",
     "description": "Claude Code settings and skills for spec-driven development workflows"
   },
   "plugins": [
     {
       "name": "claude-code-settings",
       "source": "./",
       "description": "Claude Code settings, commands, agent and skills (all in one)",
-      "version": "2.1.5",
+      "version": "2.1.6",
       "author": {
         "name": "Pengfei Ni"
       }
@@ -21,7 +21,7 @@
       "name": "kiro-skill",
       "source": "./plugins/kiro-skill",
       "description": "Interactive feature development workflow from idea to implementation (Requirements → Design → Tasks → Execute)",
-      "version": "1.0.1",
+      "version": "1.0.2",
       "author": {
         "name": "Pengfei Ni"
       }
@@ -30,7 +30,7 @@
       "name": "spec-kit-skill",
       "source": "./plugins/spec-kit-skill",
       "description": "GitHub Spec-Kit integration for constitution-based spec-driven development (7-phase workflow)",
-      "version": "1.0.1",
+      "version": "1.0.2",
       "author": {
         "name": "Pengfei Ni"
       }
@@ -39,7 +39,7 @@
       "name": "codex-skill",
       "source": "./plugins/codex-skill",
       "description": "Leverage OpenAI Codex (GPT-5/GPT-5.1) for non-interactive automation mode and hands-off task execution",
-      "version": "1.0.1",
+      "version": "1.0.2",
       "author": {
         "name": "Pengfei Ni"
       }
@@ -48,7 +48,7 @@
       "name": "nanobanana-skill",
       "source": "./plugins/nanobanana-skill",
       "description": "Generate or edit images using Google Gemini API via nanobanana",
-      "version": "1.0.1",
+      "version": "1.0.2",
       "author": {
         "name": "Pengfei Ni"
       }
@@ -57,7 +57,7 @@
       "name": "youtube-transcribe-skill",
       "source": "./plugins/youtube-transcribe-skill",
       "description": "Extract subtitles/transcripts from YouTube videos via CLI or browser automation",
-      "version": "1.0.1",
+      "version": "1.0.2",
       "author": {
         "name": "Pengfei Ni"
       }
@@ -66,7 +66,7 @@
       "name": "autonomous-skill",
       "source": "./plugins/autonomous-skill",
       "description": "Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code headless mode with auto-continuation. Trigger phrases: autonomous, long-running task, multi-session, 自主执行, 长时任务, autonomous skill.",
-      "version": "1.0.1",
+      "version": "1.0.2",
       "author": {
         "name": "Pengfei Ni"
       }

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-settings",
-  "version": "2.1.5",
+  "version": "2.1.6",
   "description": "Claude Code settings and skills for spec-driven development workflows",
   "author": {
     "name": "Pengfei Ni",

.github/copilot-instructions.md

@@ -19,75 +19,69 @@ This repository contains Claude Code settings, configurations and guidance. The
 - Configured to use `claude-sonnet-4.5` as the primary model
 - Telemetry and non-essential traffic are disabled
 
-## Custom Commands
+## Skills
 
-Custom commands for Claude Code are organized in the `commands/` directory by category:
+Skills are reusable capabilities defined in the `skills/` directory. Each skill has a `SKILL.md` file with YAML frontmatter containing `name` and `description` fields. The description serves as both documentation and trigger condition.
 
-### Command File Structure
+### Skill File Structure
 
-All command files must include YAML frontmatter with required metadata:
+All skill files must include YAML frontmatter:
 
 ```yaml
 ---
-description: Brief description of the command
-argument-hint: [expected arguments format]
-allowed-tools: List of tools the command can use
+name: skill-name
+description: 'Comprehensive description that also serves as the trigger condition. Include keywords and phrases that should activate this skill.'
 ---
 ```
 
-**Required fields:**
-
-- `description`: Clear, concise description of command purpose
-- `argument-hint`: Format showing expected arguments (e.g., `[problem or question]`)
-- `allowed-tools`: Comma-separated list of tools (e.g., `Read, Edit, Write, Bash(*)`)
-
-### Command Documentation
-
-- Command documentation belongs in `README.md` under the Commands section
-- Use collapsible `<details>` sections with clear summaries
-- Include usage examples and key features
-- Never document commands within the command files themselves
-
 ### Directory Structure
 
 ```sh
-commands/
-├── cc/          # Claude Code commands
-│   └── create-command.md
-└── gh/          # GitHub commands
-    └── review-pr.md
+skills/
+├── reflection/          # Session analysis and CLAUDE.md improvement
+├── eureka/              # Technical breakthrough documentation
+├── translate/           # Tech article translation to Chinese
+├── command-creator/     # Create Claude Code custom commands
+├── github-fix-issue/    # Fix GitHub issues end-to-end
+├── github-review-pr/    # Review GitHub pull requests
+├── skill-creator/       # Create and benchmark agent skills
+├── codex-skill/         # Handoff tasks to Codex CLI
+├── autonomous-skill/    # Long-running task automation
+├── nanobanana-skill/    # Image generation with Gemini
+├── kiro-skill/          # Interactive feature development
+├── spec-kit-skill/      # Constitution-based development
+├── deep-research/       # Multi-agent research orchestration
+└── youtube-transcribe-skill/  # YouTube transcript extraction
 ```
 
 ### Usage
 
-Run commands using the slash syntax:
+Skills are invoked via slash syntax or triggered automatically:
 
 ```sh
-/[category:][command] [ARGUMENTS]
+/skill-name [arguments]
 ```
 
 **Examples:**
 
-- `/cc:create-command mycommand` - Create a new command
-- `/gh:review-pr 123` - Review pull request #123
-
-All available commands should be documented at README.md in the Commands section.
+- `/reflection deep` - Comprehensive session analysis
+- `/eureka "Discovered batching optimization"` - Document a breakthrough
+- `/translate [text or file]` - Translate to Chinese
 
-### Prompt Engineering Principles
+### Skill Development Principles
 
-When creating or modifying command prompts:
+When creating or modifying skills:
 
-- **Structure prompts systematically**: Use clear phases or sections (e.g., Analysis Phase, Execution Phase)
+- **Comprehensive descriptions**: The `description` field triggers the skill, so include relevant keywords and phrases
+- **Structure content clearly**: Use clear sections with step-by-step instructions
+- **No `$ARGUMENTS`**: Skills receive user input through natural conversation, not via variable substitution
 - **Define specific outputs**: Include explicit output formats and structures
-- **Provide methodical approaches**: Break complex tasks into numbered steps or bullet points
-- **Include meta-cognitive elements**: Add bias awareness, assumption checking, and uncertainty assessment
-- **Balance thoroughness with conciseness**: Aim for comprehensive analysis while maintaining clarity
-- **Use progressive complexity**: Start with simple concepts and build to more complex ones
+- **Keep skills focused**: One skill, one purpose
 
 ### Behavioral Guidelines
 
 - **Concise communication**: Provide direct answers without unnecessary preamble or elaboration
-- **Follow existing patterns**: Always check similar commands for a consistent structure and approach
+- **Follow existing patterns**: Always check similar skills for consistent structure and approach
 - **Prefer editing over creating**: Always edit existing files rather than creating new ones unless absolutely necessary
 - **Use TodoWrite for complex tasks**: Track multistep processes and ensure completion of all requirements
 

README.md

@@ -1,6 +1,6 @@
-# Claude Code Settings/Commands/Skills for Vibe Coding
+# Claude Code Settings/Skills for Vibe Coding
 
-A curated collection of Claude Code settings, custom commands, skills and sub-agents designed for enhanced development workflows. This setup includes specialized commands, skills and subagents for feature development (spec-driven workflow), code analysis, GitHub integration, and knowledge management.
+A curated collection of Claude Code settings, skills and sub-agents designed for enhanced development workflows. This setup includes specialized skills and subagents for feature development (spec-driven workflow), code analysis, GitHub integration, and knowledge management.
 
 > For OpenAI Codex settings, configurations and custom prompts, please refer [feiskyer/codex-settings](https://github.com/feiskyer/codex-settings).
 
@@ -11,10 +11,10 @@ A curated collection of Claude Code settings, custom commands, skills and sub-ag
 ```sh
 /plugin marketplace add feiskyer/claude-code-settings
 
-# Install main plugin (commands, agents and skills)
+# Install main plugin (skills and agents)
 /plugin install claude-code-settings
 
-# Alternatively, install individual skills without commands/agents
+# Alternatively, install individual skills
 /plugin install codex-skill               # Codex automation
 /plugin install autonomous-skill          # Long-running task automation
 /plugin install nanobanana-skill          # Image generation
@@ -82,55 +82,9 @@ Open the link, log in and authenticate your GitHub Copilot account.
 
    - ANTHROPIC_DEFAULT_HAIKU_MODEL: gpt-5-mini
 
-
-## Commands
-
-The `commands/` directory contains [custom slash commands](https://code.claude.com/docs/en/slash-commands) that extend Claude Code's slash commands, which could be invoked via `/<command-name> [arguments]`.
-
-<details>
-<summary>Analysis & Reflection</summary>
-
-### Analysis & Reflection
-
-- `/think-harder [problem]` - Enhanced analytical thinking
-- `/think-ultra [complex problem]` - Ultra-comprehensive analysis
-- `/reflection` - Analyze and improve Claude Code instructions
-- `/reflection-harder` - Comprehensive session analysis and learning
-- `/eureka [breakthrough]` - Document technical breakthroughs
-
-</details>
-
-<details>
-<summary>GitHub Integration</summary>
-
-### GitHub Integration
-
-- `/gh:review-pr [PR_NUMBER]` - Comprehensive PR review and comments
-- `/gh:fix-issue [issue-number]` - Complete issue resolution workflow
-
-</details>
-
-<details>
-<summary>Documentation & Knowledge</summary>
-
-### Documentation & Knowledge
-
-- `/cc:create-command [name] [description]` - Create new Claude Code commands
-
-</details>
-
-<details>
-<summary>Utilities</summary>
-
-### Utilities
-
-- `/translate [text]` - Translate English/Japanese tech content to Chinese
-
-</details>
-
 ## Skills
 
-Skills are now distributed as separate plugins for modular installation. Install only what you need:
+Skills are [reusable capabilities](https://docs.anthropic.com/en/docs/claude-code/skills) that teach Claude how to complete specific tasks. They can be invoked via `/skill-name [arguments]` or triggered automatically based on context. Install only what you need:
 
 <details>
 <summary>codex-skill - handoff task to Codex CLI</summary>
@@ -370,6 +324,86 @@ Claude: [Automatically uses spec-kit-skill, detects CLI, guides through phases]
 
 </details>
 
+<details>
+<summary>reflection - Session analysis and CLAUDE.md improvement</summary>
+
+### [reflection](./skills/reflection)
+
+Analyze development sessions, capture learnings, and improve Claude Code instructions. Supports two modes:
+
+- **Quick mode** (`/reflection`): Analyzes chat history to identify and implement CLAUDE.md improvements
+- **Deep mode** (`/reflection deep`): Comprehensive session analysis covering problems solved, patterns, user preferences, system understanding, and knowledge gaps
+
+</details>
+
+<details>
+<summary>eureka - Technical breakthrough documentation</summary>
+
+### [eureka](./skills/eureka)
+
+Capture technical breakthroughs and transform them into actionable, reusable documentation. Creates structured breakthrough files in `breakthroughs/` with problem/insight/implementation/impact sections and maintains a searchable index.
+
+**Usage:**
+
+```text
+You: "/eureka Reduced API response time from 2s to 100ms by implementing request batching"
+Claude: [Creates breakthroughs/2025-01-15-api-request-batching.md, updates INDEX.md]
+```
+
+</details>
+
+<details>
+<summary>translate - Tech article translation to Chinese</summary>
+
+### [translate](./skills/translate)
+
+Translate English or Japanese tech articles into natural, fluent Chinese using a three-step process (direct translation, issue identification, reinterpretation). Preserves Markdown formatting and keeps technical terms and brand names untranslated.
+
+**Usage:**
+
+```text
+You: "/translate [paste text or provide file path]"
+Claude: [Outputs polished Chinese translation]
+```
+
+</details>
+
+<details>
+<summary>command-creator - Create Claude Code custom commands</summary>
+
+### [command-creator](./skills/command-creator)
+
+Create Claude Code custom slash commands with proper structure, frontmatter, and best practices.
+
+</details>
+
+<details>
+<summary>github-fix-issue - Fix GitHub issues end-to-end</summary>
+
+### [github-fix-issue](./skills/github-fix-issue)
+
+Fix GitHub issues from analysis through branch creation, implementation, testing, and PR submission.
+
+</details>
+
+<details>
+<summary>github-review-pr - Review GitHub pull requests</summary>
+
+### [github-review-pr](./skills/github-review-pr)
+
+Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents with confidence scoring and false positive filtering.
+
+</details>
+
+<details>
+<summary>skill-creator - Create and benchmark agent skills</summary>
+
+### [skill-creator](./skills/skill-creator)
+
+Create, refine, and benchmark agent skills with iterative evaluation loops, quantitative metrics, and description optimization.
+
+</details>
+
 ## Agents
 
 The `agents/` directory contains specialized AI [subagents](https://docs.anthropic.com/en/docs/claude-code/sub-agents) that extend Claude Code's capabilities.
@@ -536,6 +570,7 @@ Ensure the API key you configured in `ANTHROPIC_AUTH_TOKEN` is added to approved
 
 - [Claude Code official document](https://docs.anthropic.com/en/docs/claude-code/overview) - must read official document.
 - [anthropics/skills](https://github.com/anthropics/skills) - official list of Claude Code skills that teach Claude how to complete specific tasks in a repeatable way
+- [anthropics/claude-plugins-official](https://github.com/anthropics/claude-plugins-official) - official list of Claude Code plugins managed by Anthropic
 - [hesreallyhim/awesome-claude-code](https://github.com/hesreallyhim/awesome-claude-code) - curated list of slash-commands, CLAUDE.md files, CLI tools, and other resources.
 - [wshobson/agents](https://github.com/wshobson/agents) - a comprehensive collection of specialized AI subagents for Claude Code.