lite-kits 0.1.1__py3-none-any.whl → 0.3.1__py3-none-any.whl

lite_kits/kits/project/claude/commands/review.md

@@ -1,112 +0,0 @@
----
-description: Analyze code quality for uncommitted changes or recent commits
----
-
-# Code Review Helper
-
-**Purpose**: Provide quick code quality analysis and actionable suggestions for AI agents before committing.
-
-## Execution Steps
-
-Execute the following steps to analyze code changes:
-
-### 1. Check for Uncommitted Changes
-
-```bash
-# Get status of modified and staged files
-git status --short
-```
-
-**Analyze the output**:
-- Lines starting with `M ` or `A ` = Staged files
-- Lines starting with ` M` = Modified but not staged
-- Lines starting with `??` = Untracked files
-- Lines starting with `MM` = Staged and modified again
-
-### 2. Analyze Changes
-
-If changes exist:
-```bash
-# Show unstaged changes
-git diff
-
-# Show staged changes
-git diff --cached
-```
-
-**Review each file**:
-- Check for code quality issues
-- Look for potential bugs or edge cases
-- Verify naming conventions
-- Check for TODO/FIXME comments
-
-If no changes:
-```bash
-# Suggest reviewing recent commit
-git log -1 --stat
-```
-
-### 3. Check for Linting Configuration
-
-```bash
-# Look for common linting config files
-ls .ruff.toml .pylintrc pyproject.toml .eslintrc* 2>/dev/null
-```
-
-**If linting configs found**:
-- Python: Suggest `ruff check .` or `pylint <files>`
-- JavaScript: Suggest `eslint <files>`
-- TypeScript: Suggest `tsc --noEmit`
-
-### 4. Generate Concise Output
-
-Provide analysis in this format (~150 words max):
-
-```markdown
-## Code Review
-
-**Changes**: N files modified (M staged, K unstaged)
-
-- **file1.py**: Brief assessment of changes
-- **file2.ts**: Brief assessment of changes
-- **file3.md**: Brief assessment of changes
-
-**Suggestions**:
-- Actionable suggestion 1
-- Actionable suggestion 2
-- Actionable suggestion 3
-
-**Next Action**: [Run linter / Commit changes / Review specific pattern]
-```
-
-## Important Notes
-
-- **Be concise**: Target <150 words total output
-- **Be actionable**: Every suggestion should be specific and doable
-- **Handle edge cases gracefully**:
-  - No changes → Suggest reviewing recent commits or starting new work
-  - Too many files (>20) → Sample most recently modified, note total count
-  - Binary files → Skip analysis, just report count
-  - Linter not installed → Suggest installation but don't error
-
-- **Cross-platform**: Use git commands (available everywhere)
-- **Focus on quick wins**: Highlight obvious improvements, not deep analysis
-
-## Example Output
-
-```markdown
-## Code Review
-
-**Changes**: 3 files modified (2 staged, 1 unstaged)
-
-- **src/commands/review.md**: New command template, follows /orient pattern well
-- **src/prompts/review.prompt.md**: Copilot version, mirrors Claude structure
-- **README.md**: Added /review to command list (unstaged)
-
-**Suggestions**:
-- Add example output section to both templates
-- Stage README.md with the template changes
-- Consider running spell check on documentation
-
-**Next Action**: Add examples, stage all files, then run /commit
-```

lite_kits/kits/project/github/prompts/orient.prompt.md

@@ -1,150 +0,0 @@
----
-description: Quickly orient to project context, installed kits, and current state
----
-
-# Agent Orientation Protocol
-
-**Purpose**: Provide concise project orientation for AI agents at start of work session.
-
-## Execution Steps
-
-Execute the following steps to gather orientation information:
-
-### 1. Detect Installed Kits
-
-Check for kit marker files to determine what's installed:
-
-```powershell
-# Check all kits in one efficient operation
-$KITS_INSTALLED = @()
-if (Test-Path .github/prompts/orient.prompt.md) { $KITS_INSTALLED += "project" }
-if (Test-Path .github/prompts/commit.prompt.md) { $KITS_INSTALLED += "git" }
-if (Test-Path .specify/memory/pr-workflow-guide.md) { $KITS_INSTALLED += "multiagent" }
-$KITS_LIST = if ($KITS_INSTALLED.Count -gt 0) { $KITS_INSTALLED -join ", " } else { "vanilla only" }
-```
-
-### 2. Determine Agent Role
-
-Identify which agent you are and your role:
-
-```powershell
-# Detect model and interface
-$MODEL = "Grok Code Fast 1"  # Default Grok model for GitHub Copilot, adjust based on actual model used
-$INTERFACE = "GitHub Copilot"
-$AGENT_ROLE = "$MODEL @ $INTERFACE (Specialist)"
-```
-
-### 3. Read Primary Documentation
-
-Read these files in order (if they exist):
-
-1. **`.github/copilot-instructions.md`** - Project overview, stack, conventions
-2. **`.specify/memory/constitution.md`** - Project philosophy and principles
-3. **`README.md`** - General project information
-
-Extract:
-- Project name and description
-- Technology stack
-- Key architectural decisions
-- Development conventions
-
-### 4. Check Git State
-
-```powershell
-# Efficient single-command git status check
-# Get branch, recent commits, and changes in one go
-$CURRENT_BRANCH = git branch --show-current 2>$null
-if (-not $CURRENT_BRANCH) { $CURRENT_BRANCH = "not in git repo" }
-$RECENT_COMMITS = (git log --oneline -3 2>$null | Select-Object -First 1)
-$CHANGES = (git status --short 2>$null | Measure-Object).Count
-```
-
-### 5. Check Active Work
-
-Look for active feature work:
-
-```powershell
-# Check if current branch matches a spec directory
-if ($CURRENT_BRANCH -match '^\d+' -or $CURRENT_BRANCH -match '^dev/\d+') {
-  # Extract spec number from branch name
-  $SPEC_NUM = if ($CURRENT_BRANCH -match '\d+') { $Matches[0] } else { $null }
-  if ($SPEC_NUM) {
-    $SPEC_DIR = Get-ChildItem -Path "specs/$SPEC_NUM-*" -Directory -ErrorAction SilentlyContinue | Select-Object -First 1
-    if ($SPEC_DIR) {
-      $SPEC_FILES = @("spec.md", "plan.md", "tasks.md") | Where-Object { Test-Path "$($SPEC_DIR.FullName)/$_" }
-    }
-  }
-}
-```
-
-### 6. Check Multi-Agent Coordination (if multiagent-kit installed)
-
-```powershell
-# Only check if multiagent kit is installed
-if ($KITS_INSTALLED -contains "multiagent") {
-  # Efficient check for collaboration activity
-  $ACTIVE_SESSIONS = (Get-ChildItem -Path specs/*/collaboration/active/sessions/ -Filter *.md -Recurse -ErrorAction SilentlyContinue).Count
-  $PENDING_HANDOFF = Get-ChildItem -Path specs/*/collaboration/active/decisions/ -Filter handoff-*.md -Recurse -ErrorAction SilentlyContinue | Select-Object -First 1
-}
-```
-
-### 7. Generate Concise Output
-
-Provide a **concise summary** (~150 words max) in this format:
-
-```
-## Orientation Complete
-
-**Installed Kits**: [$KITS_LIST]
-
-**I am**: [$AGENT_ROLE from step 2]
-**Project**: [project name from docs]
-**Stack**: [main technologies]
-**Branch**: [$CURRENT_BRANCH]
-**Recent work**: [$RECENT_COMMITS - just the message]
-**Uncommitted changes**: [$CHANGES count]
-**Active feature**: [current spec if $SPEC_FILES exists]
-**Coordination**: [solo work / handoff pending / etc]
-
-**Next suggested action**: [based on state analysis below]
-```
-
-### 8. Suggest Next Action
-
-Based on the state you discovered, suggest the next logical action:
-
-**Decision logic**:
-
-- **No spec on current branch** → "Run `/specify` to start a new feature"
-- **Spec exists, no plan** → "Run `/plan` to create implementation plan"
-- **Plan exists, no tasks** → "Run `/tasks` to break down into tasks"
-- **Tasks exist** → "Run `/implement` to start coding"
-- **Handoff detected** (multiagent) → "Review handoff in `specs/[feature]/collaboration/active/decisions/`"
-- **Uncommitted changes** → "Review changes and consider running `/commit`" (if git-kit installed)
-
-## Important Notes
-
-- Keep output **concise** - this is an orientation, not a full analysis
-- Focus on **actionable context** - what the agent needs to know right now
-- **Don't modify any files** - this is read-only orientation
-- If documentation is missing, note it briefly and continue
-- Gracefully handle missing files (don't error if docs don't exist)
-
-## Example Output
-
-```
-## Orientation Complete
-
-**Installed Kits**: project, git
-
-**I am**: Grok Code Fast 1 @ GitHub Copilot (Specialist)
-**Project**: Blog Platform API (TypeScript/Node.js)
-**Stack**: Node.js, Express, PostgreSQL, TypeScript
-**Branch**: dev/003-user-authentication
-**Recent work**: Added JWT token validation (2 commits today)
-**Uncommitted changes**: 3 modified files
-**Active feature**: specs/003-user-authentication/ (spec + plan complete)
-**Coordination**: Solo work
-
-**Next suggested action**: Run `/tasks` to break down the implementation plan into actionable tasks.
-```

lite_kits/kits/project/github/prompts/review.prompt.md

@@ -1,112 +0,0 @@
----
-description: Analyze code quality for uncommitted changes or recent commits
----
-
-# Code Review Helper
-
-**Purpose**: Provide quick code quality analysis and actionable suggestions for AI agents before committing.
-
-## Execution Steps
-
-Execute the following steps to analyze code changes:
-
-### 1. Check for Uncommitted Changes
-
-```powershell
-# Get status of modified and staged files
-git status --short
-```
-
-**Analyze the output**:
-- Lines starting with `M ` or `A ` = Staged files
-- Lines starting with ` M` = Modified but not staged
-- Lines starting with `??` = Untracked files
-- Lines starting with `MM` = Staged and modified again
-
-### 2. Analyze Changes
-
-If changes exist:
-```powershell
-# Show unstaged changes
-git diff
-
-# Show staged changes
-git diff --cached
-```
-
-**Review each file**:
-- Check for code quality issues
-- Look for potential bugs or edge cases
-- Verify naming conventions
-- Check for TODO/FIXME comments
-
-If no changes:
-```powershell
-# Suggest reviewing recent commit
-git log -1 --stat
-```
-
-### 3. Check for Linting Configuration
-
-```powershell
-# Look for common linting config files
-Get-ChildItem -Path . -Include .ruff.toml,.pylintrc,pyproject.toml,.eslintrc* -Recurse -ErrorAction SilentlyContinue
-```
-
-**If linting configs found**:
-- Python: Suggest `ruff check .` or `pylint <files>`
-- JavaScript: Suggest `eslint <files>`
-- TypeScript: Suggest `tsc --noEmit`
-
-### 4. Generate Concise Output
-
-Provide analysis in this format (~150 words max):
-
-```markdown
-## Code Review
-
-**Changes**: N files modified (M staged, K unstaged)
-
-- **file1.py**: Brief assessment of changes
-- **file2.ts**: Brief assessment of changes
-- **file3.md**: Brief assessment of changes
-
-**Suggestions**:
-- Actionable suggestion 1
-- Actionable suggestion 2
-- Actionable suggestion 3
-
-**Next Action**: [Run linter / Commit changes / Review specific pattern]
-```
-
-## Important Notes
-
-- **Be concise**: Target <150 words total output
-- **Be actionable**: Every suggestion should be specific and doable
-- **Handle edge cases gracefully**:
-  - No changes → Suggest reviewing recent commits or starting new work
-  - Too many files (>20) → Sample most recently modified, note total count
-  - Binary files → Skip analysis, just report count
-  - Linter not installed → Suggest installation but don't error
-
-- **Cross-platform**: Use git commands (available everywhere)
-- **Focus on quick wins**: Highlight obvious improvements, not deep analysis
-
-## Example Output
-
-```markdown
-## Code Review
-
-**Changes**: 3 files modified (2 staged, 1 unstaged)
-
-- **src/commands/review.md**: New command template, follows /orient pattern well
-- **src/prompts/review.prompt.md**: Copilot version, mirrors Claude structure
-- **README.md**: Added /review to command list (unstaged)
-
-**Suggestions**:
-- Add example output section to both templates
-- Stage README.md with the template changes
-- Consider running spell check on documentation
-
-**Next Action**: Add examples, stage all files, then run /commit
-```

lite_kits/kits/project/github/prompts/stats.prompt.md

@@ -1,163 +0,0 @@
----
-description: Generate concise project metrics for AI agent orientation
----
-
-# Project Statistics
-
-**Purpose**: Provide quick project overview metrics for AI agents joining a project or assessing scope.
-
-## Execution Steps
-
-Execute the following steps to gather project statistics:
-
-### 1. Count Lines of Code
-
-**Preferred method** (if tokei installed):
-```powershell
-# Check if tokei is available
-Get-Command tokei -ErrorAction SilentlyContinue
-
-# If available, use tokei for fast, accurate counts
-tokei --output json
-```
-
-**Fallback method** (if tokei not available):
-```powershell
-# Python
-(Get-ChildItem -Recurse -Filter *.py | Get-Content | Measure-Object -Line).Lines
-
-# JavaScript/TypeScript
-(Get-ChildItem -Recurse -Include *.js,*.ts | Get-Content | Measure-Object -Line).Lines
-
-# Markdown
-(Get-ChildItem -Recurse -Filter *.md | Get-Content | Measure-Object -Line).Lines
-
-# All files combined
-(Get-ChildItem -Recurse -File | Get-Content | Measure-Object -Line).Lines
-```
-
-### 2. Count Files and Directories
-
-```powershell
-# Count files (excluding hidden)
-(Get-ChildItem -Recurse -File | Where-Object { -not $_.FullName.Contains('\.') }).Count
-
-# Count directories (excluding hidden)
-(Get-ChildItem -Recurse -Directory | Where-Object { -not $_.FullName.Contains('\.') }).Count
-```
-
-### 3. Get Git History Summary
-
-```powershell
-# Total commits
-(git log --oneline | Measure-Object).Count
-
-# Contributor count
-(git log --format='%aN' | Sort-Object -Unique).Count
-
-# Recent activity
-git log --oneline -5
-```
-
-If not a git repository, skip this section.
-
-### 4. Check for Test Coverage
-
-Look for common coverage report files:
-```powershell
-# Python coverage files
-Get-ChildItem -Path . -Include .coverage,coverage.xml -Recurse -ErrorAction SilentlyContinue
-Get-ChildItem -Path htmlcov -Directory -ErrorAction SilentlyContinue
-
-# JavaScript coverage
-Get-ChildItem -Path coverage,.nyc_output -Directory -ErrorAction SilentlyContinue
-
-# If coverage files exist, try to extract percentage
-# Python: coverage report | Select-String TOTAL
-# JavaScript: Get-Content coverage/coverage-summary.json | ConvertFrom-Json
-```
-
-### 5. Generate Concise Table Output
-
-Provide stats in this format (~20 lines max):
-
-```markdown
-## Project Statistics
-
-**Code**:
-- Language1: X,XXX LOC (NN%)
-- Language2: XXX LOC (NN%)
-- Language3: XX LOC (NN%)
-
-**Structure**:
-- NN files, NN directories
-- NNN commits, N contributors
-
-**Testing**:
-- Coverage: NN% (or N/A)
-- Tests: NN files (or N/A)
-
-**Next Action**: [Explore src/ / Review tests / Check docs]
-```
-
-## Important Notes
-
-- **Be concise**: Keep output under 20 lines
-- **Use tables**: Well-formatted markdown tables or lists
-- **Handle missing tools**:
-  - No tokei → Use Get-ChildItem/Measure-Object fallback, note "Basic LOC count"
-  - Not a git repo → Skip git section, note "No git history"
-  - No coverage → Show "N/A" gracefully
-
-- **Percentages**: Calculate language percentages from total LOC
-- **Large repos**: If >100k LOC, note "Large project" and consider sampling
-- **Speed**: Target <5 second execution time
-
-## Edge Cases
-
-- **No git repository**: Skip git section, show file/LOC stats only
-- **No test coverage reports**: Show "Coverage: N/A"
-- **Tokei not installed**: Use PowerShell fallback, note in output
-- **Very large repo (1M+ LOC)**: Sample or provide high-level summary only
-- **No code files**: "Appears to be a documentation-only or data project"
-
-## Example Output
-
-```markdown
-## Project Statistics
-
-**Code**:
-- Python: 2,453 LOC (87%)
-- Markdown: 342 LOC (12%)
-- YAML: 28 LOC (1%)
-- Total: 2,823 LOC
-
-**Structure**:
-- 45 files, 12 directories
-- 127 commits, 3 contributors
-
-**Testing**:
-- Coverage: 78% (via pytest-cov)
-- Tests: 23 test files
-
-**Next Action**: Explore src/ directory to understand core modules
-```
-
-```markdown
-## Project Statistics
-
-**Code** (tokei not available, using basic count):
-- Python: ~1,200 lines
-- Markdown: ~400 lines
-- Total: ~1,600 lines (approximate)
-
-**Structure**:
-- 32 files, 8 directories
-- Not a git repository
-
-**Testing**:
-- Coverage: N/A
-- Tests: N/A
-
-**Next Action**: Check if this is a standalone library or tool
-```