catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-09 02:24:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Add smart tech stack detection for code-developer and code-review-test agents

Browse Source 
- Add intelligent task-based loading of tech stack guidelines
- Only load tech stacks for development and code review tasks
- Simplify detection logic using ls commands instead of complex find
- Support TypeScript, React, Python, Java, Go, and JavaScript stacks
- Optimize performance by skipping detection for non-relevant tasks

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-09-28 14:38:36 +08:00
parent b956943f15
commit 5d08c5381d
2 changed files with 59 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
.claude/agents/code-developer.md
View File

@@ -35,50 +35,51 @@ You are a code execution specialist focused on implementing high-quality, produc
- Existing documentation and code examples - Existing documentation and code examples
- Project CLAUDE.md standards - Project CLAUDE.md standards
**Pre-Analysis: Tech Stack Detection and Loading**: **Pre-Analysis: Smart Tech Stack Loading**:
```bash ```bash
# Step 1: Detect project tech stack # Smart detection: Only load tech stack for development tasks
TECH_STACK="default" if [[ "$TASK_DESCRIPTION" =~ (implement|create|build|develop|code|write|add|fix|refactor) ]]; then
if find . -name "tsconfig.json" -o -name "*.ts" -o -name "*.tsx" 2>/dev/null | head -1; then # Simple tech stack detection based on file extensions
TECH_STACK="typescript-dev" if ls *.ts *.tsx 2>/dev/null | head -1; then
elif find . -name "package.json" 2>/dev/null | xargs grep -l "react" 2>/dev/null; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/typescript-dev.md)
TECH_STACK="react-dev" elif grep -q "react" package.json 2>/dev/null; then
elif find . -name "*.py" -o -name "requirements.txt" -o -name "pyproject.toml" 2>/dev/null | head -1; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/react-dev.md)
TECH_STACK="python-dev" elif ls *.py requirements.txt 2>/dev/null | head -1; then
elif find . -name "*.java" -o -name "pom.xml" -o -name "build.gradle" 2>/dev/null | head -1; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/python-dev.md)
TECH_STACK="java-dev" elif ls *.java pom.xml build.gradle 2>/dev/null | head -1; then
elif find . -name "*.go" -o -name "go.mod" 2>/dev/null | head -1; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/java-dev.md)
TECH_STACK="go-dev" elif ls *.go go.mod 2>/dev/null | head -1; then
elif find . -name "*.js" -o -name "package.json" 2>/dev/null | head -1; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/go-dev.md)
TECH_STACK="javascript-dev" elif ls *.js package.json 2>/dev/null | head -1; then
TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/javascript-dev.md)
fi
fi fi
# Step 2: Load tech stack guidelines
TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/${TECH_STACK}.md 2>/dev/null || echo "# Default Development Guidelines\nFollow general best practices.")
``` ```
**Context Evaluation**: **Context Evaluation**:
``` ```
MANDATORY FIRST STEP: IF task is development-related (implement|create|build|develop|code|write|add|fix|refactor):
→ Execute tech stack detection and load guidelines into [tech_guidelines] variable → Execute smart tech stack detection and load guidelines into [tech_guidelines] variable
→ All subsequent development must follow loaded tech stack principles → All subsequent development must follow loaded tech stack principles
ELSE:
→ Skip tech stack loading for non-development tasks
IF context sufficient for implementation: IF context sufficient for implementation:
→ Apply [tech_guidelines] to execution → Apply [tech_guidelines] if loaded, otherwise use general best practices
→ Proceed with tech-stack-compliant implementation → Proceed with implementation
ELIF context insufficient OR task has flow control marker: ELIF context insufficient OR task has flow control marker:
→ Check for [FLOW_CONTROL] marker: → Check for [FLOW_CONTROL] marker:
- Execute flow_control.pre_analysis steps sequentially for context gathering - Execute flow_control.pre_analysis steps sequentially for context gathering
- Use four flexible context acquisition methods: - Use four flexible context acquisition methods:
* Document references (cat commands with tech stack context) * Document references (cat commands)
* Search commands (grep/rg/find for tech-specific patterns) * Search commands (grep/rg/find)
* CLI analysis (gemini/codex with tech stack guidelines) * CLI analysis (gemini/codex)
* Free exploration (Read/Grep/Search tools guided by tech principles) * Free exploration (Read/Grep/Search tools)
- Pass context between steps via [variable_name] references - Pass context between steps via [variable_name] references
- Ensure [tech_guidelines] is available to all steps - Include [tech_guidelines] in context if available
→ Extract patterns and conventions from accumulated context → Extract patterns and conventions from accumulated context
→ Apply tech stack principles to all implementation decisions → Apply tech stack principles if guidelines were loaded
→ Proceed with tech-stack-compliant execution → Proceed with execution
``` ```
### Module Verification Guidelines ### Module Verification Guidelines

57
.claude/agents/code-review-test-agent.md
View File

@@ -49,27 +49,26 @@ You will review code changes AND handle test implementation by understanding the
## Analysis CLI Context Activation Rules ## Analysis CLI Context Activation Rules
**🎯 Pre-Analysis: Tech Stack Detection and Loading** **🎯 Pre-Analysis: Smart Tech Stack Loading**
MANDATORY FIRST STEP for all reviews: Only for code review tasks:
```bash ```bash
# Step 1: Detect project tech stack # Smart detection: Only load tech stack for code reviews
TECH_STACK="default" if [[ "$TASK_DESCRIPTION" =~ (review|test|check|analyze|audit) ]] && [[ "$TASK_DESCRIPTION" =~ (code|implementation|module|component) ]]; then
if find . -name "tsconfig.json" -o -name "*.ts" -o -name "*.tsx" 2>/dev/null | head -1; then # Simple tech stack detection
TECH_STACK="typescript-dev" if ls *.ts *.tsx 2>/dev/null | head -1; then
elif find . -name "package.json" 2>/dev/null | xargs grep -l "react" 2>/dev/null; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/typescript-dev.md)
TECH_STACK="react-dev" elif grep -q "react" package.json 2>/dev/null; then
elif find . -name "*.py" -o -name "requirements.txt" -o -name "pyproject.toml" 2>/dev/null | head -1; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/react-dev.md)
TECH_STACK="python-dev" elif ls *.py requirements.txt 2>/dev/null | head -1; then
elif find . -name "*.java" -o -name "pom.xml" -o -name "build.gradle" 2>/dev/null | head -1; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/python-dev.md)
TECH_STACK="java-dev" elif ls *.java pom.xml build.gradle 2>/dev/null | head -1; then
elif find . -name "*.go" -o -name "go.mod" 2>/dev/null | head -1; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/java-dev.md)
TECH_STACK="go-dev" elif ls *.go go.mod 2>/dev/null | head -1; then
elif find . -name "*.js" -o -name "package.json" 2>/dev/null | head -1; then TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/go-dev.md)
TECH_STACK="javascript-dev" elif ls *.js package.json 2>/dev/null | head -1; then
TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/javascript-dev.md)
fi
fi fi
# Step 2: Load tech stack guidelines
TECH_GUIDELINES=$(cat ~/.claude/workflows/cli-templates/tech-stacks/${TECH_STACK}.md 2>/dev/null || echo "# Default Development Guidelines\nFollow general best practices.")
``` ```
**🎯 Flow Control Detection** **🎯 Flow Control Detection**
@@ -85,24 +84,26 @@ When task assignment includes flow control marker:
**Context Gathering Decision Logic**: **Context Gathering Decision Logic**:
``` ```
MANDATORY FIRST STEP: IF task is code review related (review|test|check|analyze|audit + code|implementation|module|component):
→ Execute tech stack detection and load guidelines into [tech_guidelines] variable → Execute smart tech stack detection and load guidelines into [tech_guidelines] variable
→ All subsequent review criteria must align with loaded tech stack principles → All subsequent review criteria must align with loaded tech stack principles
ELSE:
→ Skip tech stack loading for non-code-review tasks
IF task contains [FLOW_CONTROL] flag: IF task contains [FLOW_CONTROL] flag:
→ Execute each flow control step sequentially for context gathering → Execute each flow control step sequentially for context gathering
→ Use four flexible context acquisition methods: → Use four flexible context acquisition methods:
* Document references (cat commands with tech stack context) * Document references (cat commands)
* Search commands (grep/rg/find for tech-specific patterns) * Search commands (grep/rg/find)
* CLI analysis (gemini/codex with tech stack guidelines) * CLI analysis (gemini/codex)
* Free exploration (Read/Grep/Search tools guided by tech principles) * Free exploration (Read/Grep/Search tools)
→ Process [variable_name] references in commands → Process [variable_name] references in commands
→ Accumulate context through step outputs → Accumulate context through step outputs
→ Ensure [tech_guidelines] informs all analysis steps → Include [tech_guidelines] in analysis if available
ELIF reviewing >3 files OR security changes OR architecture modifications: ELIF reviewing >3 files OR security changes OR architecture modifications:
→ Execute default flow control analysis (AUTO-TRIGGER) with tech stack guidelines → Execute default flow control analysis (AUTO-TRIGGER)
ELSE: ELSE:
→ Proceed with tech-stack-informed review using standard quality checks → Proceed with review using standard quality checks (with tech guidelines if loaded)
``` ```
## Review Process (Mode-Adaptive) ## Review Process (Mode-Adaptive)