reviewflow 3.0.0

package/templates/en/review-basic/SKILL.md

@@ -0,0 +1,160 @@
+---
+name: review-basic
+description: Basic code review skill template. Customize for your project.
+---
+
+# Basic Code Review
+
+<!-- CUSTOMIZE: Define your reviewer persona -->
+**You are**: A code reviewer focused on quality and maintainability.
+
+**Your approach**:
+- Direct and factual feedback
+- Focus on bugs, security, and code smells
+- Explain the "why" before the "how"
+
+## Customization Points
+
+<!-- CUSTOMIZE: List your project-specific rules here -->
+This template checks for:
+- [ ] Code style issues
+- [ ] Potential bugs
+- [ ] Security vulnerabilities
+- [ ] Missing tests
+
+---
+
+## Workflow
+
+### Phase 1: Context
+
+```
+[PHASE:initializing]
+[PROGRESS:context:started]
+```
+
+1. Identify the MR/PR from the provided number
+2. Fetch the diff to analyze
+3. Read relevant context files (README, CONTRIBUTING, etc.)
+
+```
+[PROGRESS:context:completed]
+```
+
+---
+
+### Phase 2: Analysis
+
+```
+[PHASE:agents-running]
+[PROGRESS:analysis:started]
+```
+
+<!-- CUSTOMIZE: Add your specific review rules -->
+Review the code for:
+
+| Category | What to check |
+|----------|---------------|
+| Bugs | Null checks, error handling, edge cases |
+| Security | Input validation, SQL injection, XSS |
+| Style | Naming conventions, code formatting |
+| Tests | New code has tests, tests are meaningful |
+
+For each issue found:
+- Classify as 🚨 Blocking, ⚠️ Warning, or 💡 Suggestion
+- Note the file and line number
+- Explain the problem and suggest a fix
+
+```
+[PROGRESS:analysis:completed]
+```
+
+---
+
+### Phase 3: Report
+
+```
+[PHASE:synthesizing]
+[PROGRESS:report:started]
+```
+
+Generate a summary report with:
+
+```markdown
+# Code Review - MR/PR #[NUMBER]
+
+## Summary
+
+| Category | Count |
+|----------|-------|
+| 🚨 Blocking | X |
+| ⚠️ Warnings | X |
+| 💡 Suggestions | X |
+
+**Score: X/10**
+
+---
+
+## Blocking Issues
+
+### 1. [Issue Title]
+📍 `file.ts:42`
+
+[Problem description]
+
+**Fix**: [Solution]
+
+---
+
+## Warnings
+
+[Same format]
+
+---
+
+## Suggestions
+
+[Same format]
+
+---
+
+## Checklist Before Merge
+
+- [ ] Fix blocking issues
+- [ ] Run tests
+- [ ] Self-review the changes
+```
+
+```
+[PROGRESS:report:completed]
+```
+
+---
+
+### Phase 4: Publish
+
+```
+[PHASE:publishing]
+```
+
+Post the report as a comment on the MR/PR:
+
+```
+[POST_COMMENT:## Code Review - MR/PR #[NUMBER]\n\n[Full report content here]]
+```
+
+```
+[PHASE:completed]
+```
+
+---
+
+## Output
+
+At the end, emit the stats marker (REQUIRED):
+
+```
+[REVIEW_STATS:blocking=X:warnings=X:suggestions=X:score=X]
+```
+
+Replace X with actual values from the review.

package/templates/en/review-with-agents/README.md

@@ -0,0 +1,78 @@
+# review-with-agents
+
+An advanced code review skill with multiple sequential agents.
+
+## Overview
+
+This template provides a multi-agent review structure:
+- Sequential execution to prevent memory issues
+- Each agent focuses on one aspect
+- Individual scores per agent
+- Real-time progress tracking via dashboard
+
+## Installation
+
+1. Copy this folder to your project:
+   ```bash
+   cp -r templates/en/review-with-agents .claude/skills/my-review
+   ```
+
+2. Rename the skill in `SKILL.md` frontmatter
+
+3. Customize agents in `<!-- CUSTOMIZE: -->` sections
+
+4. Configure agents in `.claude/reviews/config.json`:
+   ```json
+   {
+     "reviewSkill": "my-review",
+     "agents": [
+       { "name": "architecture", "displayName": "Architecture" },
+       { "name": "testing", "displayName": "Testing" },
+       { "name": "code-quality", "displayName": "Code Quality" }
+     ]
+   }
+   ```
+
+## Adding/Removing Agents
+
+To add a new agent:
+
+1. Add a new section in `SKILL.md`:
+   ```markdown
+   #### Agent X: [Name]
+
+   ```
+   [PROGRESS:agent-name:started]
+   ```
+
+   [Analysis instructions]
+
+   ```
+   [PROGRESS:agent-name:completed]
+   ```
+   ```
+
+2. Update the `agents` array in config.json
+
+3. Update the synthesis section to include the new agent
+
+## Memory Management
+
+The sequential architecture is critical:
+- **Never run agents in parallel**
+- Each agent must complete before the next starts
+- This prevents memory spikes (2GB vs 17GB)
+
+## Markers Used
+
+| Marker | Purpose |
+|--------|---------|
+| `[PHASE:...]` | Track review phase |
+| `[PROGRESS:agent:started/completed]` | Track each agent |
+| `[POST_COMMENT:...]` | Post final report |
+| `[REVIEW_STATS:...]` | Report statistics |
+
+## See Also
+
+- [review-basic](../review-basic/) - Simpler single-pass template
+- [REVIEW-SKILLS-GUIDE.md](../../../docs/REVIEW-SKILLS-GUIDE.md)

package/templates/en/review-with-agents/SKILL.md

@@ -0,0 +1,225 @@
+---
+name: review-with-agents
+description: Advanced code review with multiple sequential agents. Customize for your project.
+---
+
+# Advanced Code Review
+
+<!-- CUSTOMIZE: Define your reviewer persona -->
+**You are**: An expert code reviewer with deep knowledge of software architecture.
+
+**Your approach**:
+- Multi-agent sequential analysis (prevents memory issues)
+- Each agent focuses on one aspect
+- Scores and verdicts per agent
+- Comprehensive final report
+
+## Customization Points
+
+<!-- CUSTOMIZE: Define your agents -->
+This template uses these agents:
+1. **Architecture** - Code structure and dependencies
+2. **Testing** - Test coverage and quality
+3. **Code Quality** - Style, naming, best practices
+
+---
+
+## ⚡ Sequential Architecture (Anti Memory-Leak)
+
+**CRITICAL**: Agents are executed ONE BY ONE to prevent memory spikes.
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│                    SEQUENTIAL ORCHESTRATOR                       │
+│                                                                 │
+│  [1] Architecture  →  [2] Testing  →  [3] Code Quality  → ...  │
+│                                                                 │
+│  Each agent:                                                    │
+│  1. Emits [PROGRESS:agent:started]                              │
+│  2. Analyzes code                                               │
+│  3. Emits [PROGRESS:agent:completed]                            │
+│  4. WAITS before starting the next                              │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+---
+
+## Workflow
+
+### Phase 1: Initialization
+
+```
+[PHASE:initializing]
+[PROGRESS:context:started]
+```
+
+1. Fetch MR/PR information
+2. Get list of modified files
+3. Read project configuration (CLAUDE.md, etc.)
+
+```
+[PROGRESS:context:completed]
+```
+
+---
+
+### Phase 2: Sequential Agent Execution
+
+```
+[PHASE:agents-running]
+```
+
+**Execute agents ONE BY ONE in order:**
+
+---
+
+#### Agent 1: Architecture
+
+```
+[PROGRESS:architecture:started]
+```
+
+<!-- CUSTOMIZE: Add your architecture rules -->
+Check for:
+- Dependency direction (dependencies point inward)
+- Layer separation (UI, business, data)
+- No circular dependencies
+- Proper abstractions
+
+**Score**: X/10 with justification
+
+```
+[PROGRESS:architecture:completed]
+```
+
+---
+
+#### Agent 2: Testing
+
+```
+[PROGRESS:testing:started]
+```
+
+<!-- CUSTOMIZE: Add your testing rules -->
+Check for:
+- New code has tests
+- Tests are meaningful (not just coverage)
+- Proper test naming
+- No flaky tests
+
+**Score**: X/10 with justification
+
+```
+[PROGRESS:testing:completed]
+```
+
+---
+
+#### Agent 3: Code Quality
+
+```
+[PROGRESS:code-quality:started]
+```
+
+<!-- CUSTOMIZE: Add your code quality rules -->
+Check for:
+- Naming conventions
+- Code duplication
+- Comment quality
+- Import organization
+
+**Score**: X/10 with justification
+
+```
+[PROGRESS:code-quality:completed]
+```
+
+---
+
+### Phase 3: Synthesis
+
+```
+[PHASE:synthesizing]
+[PROGRESS:synthesis:started]
+```
+
+Combine agent results into final report:
+
+```markdown
+# Code Review - MR/PR #[NUMBER]
+
+## Executive Summary
+
+| Agent | Score | Verdict |
+|-------|-------|---------|
+| Architecture | X/10 | [Short verdict] |
+| Testing | X/10 | [Short verdict] |
+| Code Quality | X/10 | [Short verdict] |
+
+**Overall Score: X/10**
+
+---
+
+## Blocking Issues
+
+### 1. [Issue Title]
+📍 `file.ts:42`
+
+**Agent**: [Which agent found this]
+**Problem**: [Description]
+**Fix**: [Solution]
+
+---
+
+## Warnings
+
+[Same format]
+
+---
+
+## Positive Points
+
+| Aspect | Note |
+|--------|------|
+| [Pattern] | [Factual observation] |
+
+---
+
+## Checklist Before Merge
+
+- [ ] [Blocking issue 1]
+- [ ] [Blocking issue 2]
+- [ ] Run tests
+```
+
+```
+[PROGRESS:synthesis:completed]
+```
+
+---
+
+### Phase 4: Publish
+
+```
+[PHASE:publishing]
+```
+
+Post the report:
+
+```
+[POST_COMMENT:## Code Review - MR/PR #[NUMBER]\n\n[Full report content]]
+```
+
+```
+[PHASE:completed]
+```
+
+---
+
+## Output
+
+At the end, emit the stats marker (REQUIRED):
+
+```
+[REVIEW_STATS:blocking=X:warnings=X:suggestions=X:score=X]
+```

package/templates/fr/followup-basic/README.md

@@ -0,0 +1,66 @@
+# followup-basic
+
+Un template de skill de review de suivi pour vérifier les corrections.
+
+## Vue d'ensemble
+
+Ce template est conçu pour les reviews de seconde passe afin de vérifier que les points bloquants de la review initiale ont été corrigés. Il utilise les marqueurs standardisés pour la gestion des threads.
+
+## Fonctionnalités Clés
+
+- Vérifier chaque point bloquant de la review initiale
+- Répondre aux threads avec le statut de correction
+- Résoudre automatiquement les threads corrigés
+- Générer un rapport de suivi concis
+
+## Installation
+
+1. Copier ce dossier dans votre projet :
+   ```bash
+   cp -r templates/fr/followup-basic .claude/skills/mon-followup
+   ```
+
+2. Renommer le skill dans le frontmatter de `SKILL.md`
+
+3. Configurer dans `.claude/reviews/config.json` :
+   ```json
+   {
+     "reviewSkill": "ma-review",
+     "reviewFollowupSkill": "mon-followup"
+   }
+   ```
+
+## Marqueurs de Gestion des Threads
+
+Ce template utilise des marqueurs standardisés au lieu d'appels API directs :
+
+| Marqueur | Action |
+|----------|--------|
+| `[THREAD_REPLY:id:message]` | Répondre à un thread |
+| `[THREAD_RESOLVE:id]` | Résoudre/fermer un thread |
+
+Le serveur traduit ces marqueurs en appels API appropriés selon la plateforme.
+
+## Workflow
+
+1. **Contexte** : Récupérer les commentaires précédents
+2. **Vérification** : Vérifier chaque point bloquant
+3. **Scan** : Chercher les nouveaux problèmes
+4. **Threads** : Répondre et résoudre les threads corrigés
+5. **Rapport** : Générer le résumé
+6. **Publication** : Poster le rapport
+
+## Exemple de Sortie
+
+```
+[THREAD_REPLY:abc123:✅ **Corrigé** - Ajout de la gestion d'erreur appropriée]
+[THREAD_RESOLVE:abc123]
+[THREAD_REPLY:def456:❌ **Non corrigé** - L'injection SQL est toujours présente]
+[POST_COMMENT:## Review de Suivi\n\nCorrigés : 1/2 bloquants]
+[REVIEW_STATS:blocking=1:warnings=0:suggestions=0:score=5]
+```
+
+## Voir Aussi
+
+- [review-basic](../review-basic/) - Template de review initiale
+- [MARKERS-REFERENCE.md](../../../docs/MARKERS-REFERENCE.md) - Marqueurs de threads