mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-03-11 17:21:03 +08:00
Add unit tests for various components and stores in the terminal dashboard
- Implement tests for AssociationHighlight, DashboardToolbar, QueuePanel, SessionGroupTree, and TerminalDashboardPage to ensure proper functionality and state management. - Create tests for cliSessionStore, issueQueueIntegrationStore, queueExecutionStore, queueSchedulerStore, sessionManagerStore, and terminalGridStore to validate state resets and workspace scoping. - Mock necessary dependencies and state management hooks to isolate tests and ensure accurate behavior.
This commit is contained in:
catlog22
601
.codex/skills/team-ux-improve/SKILL.md
Normal file
601
.codex/skills/team-ux-improve/SKILL.md
Normal file
@@ -0,0 +1,601 @@
|
||||
---
|
||||
name: team-ux-improve
|
||||
description: Systematic UX improvement pipeline. Discovers and fixes UI/UX interaction issues including unresponsive buttons, missing feedback, and state refresh problems using scan->diagnose->design->implement->test workflow.
|
||||
argument-hint: "[-y|--yes] [-c|--concurrency N] [--continue] \"<project-path> [--framework react|vue]\""
|
||||
allowed-tools: spawn_agents_on_csv, spawn_agent, wait, send_input, close_agent, Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion
|
||||
---
|
||||
|
||||
## Auto Mode
|
||||
|
||||
When `--yes` or `-y`: Auto-confirm task decomposition, skip interactive validation, use defaults.
|
||||
|
||||
# UX Improvement Pipeline
|
||||
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
$team-ux-improve "ccw/frontend --framework react"
|
||||
$team-ux-improve -c 4 "src/components"
|
||||
$team-ux-improve -y "app/ui --framework vue"
|
||||
$team-ux-improve --continue "ux-improve-1709856000"
|
||||
```
|
||||
|
||||
**Flags**:
|
||||
- `-y, --yes`: Skip all confirmations (auto mode)
|
||||
- `-c, --concurrency N`: Max concurrent agents within each wave (default: 4)
|
||||
- `--continue`: Resume existing session
|
||||
- `--framework react|vue`: Specify UI framework (auto-detected if omitted)
|
||||
|
||||
**Output Directory**: `.workflow/.csv-wave/{session-id}/`
|
||||
**Core Output**: `tasks.csv` (master state) + `results.csv` (final) + `discoveries.ndjson` (shared exploration) + `context.md` (human-readable report)
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Systematic UX improvement workflow that discovers UI/UX interaction issues (unresponsive buttons, missing feedback, state refresh problems) and fixes them methodically. The pipeline scans for issues, diagnoses root causes, designs solutions, implements fixes, and validates with tests.
|
||||
|
||||
**Execution Model**: Hybrid — CSV wave pipeline (primary) + individual agent spawn (secondary)
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────────┐
|
||||
│ UX IMPROVEMENT PIPELINE WORKFLOW │
|
||||
├─────────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ Phase 0: Framework Detection & Exploration (Interactive) │
|
||||
│ ├─ Detect UI framework (React/Vue/etc.) │
|
||||
│ ├─ Explore component patterns and conventions │
|
||||
│ ├─ Build component inventory │
|
||||
│ └─ Output: exploration cache for downstream tasks │
|
||||
│ │
|
||||
│ Phase 1: Requirement → CSV + Classification │
|
||||
│ ├─ Generate scan->diagnose->design->implement->test task chain │
|
||||
│ ├─ Classify tasks: csv-wave (scan/implement) | interactive (design) │
|
||||
│ ├─ Compute dependency waves (topological sort → depth grouping) │
|
||||
│ ├─ Generate tasks.csv with wave + exec_mode columns │
|
||||
│ └─ User validates task breakdown (skip if -y) │
|
||||
│ │
|
||||
│ Phase 2: Wave Execution Engine (Extended) │
|
||||
│ ├─ For each wave (1..N): │
|
||||
│ │ ├─ Execute pre-wave interactive tasks (design) │
|
||||
│ │ ├─ Build wave CSV (filter csv-wave tasks for this wave) │
|
||||
│ │ ├─ Inject previous findings into prev_context column │
|
||||
│ │ ├─ spawn_agents_on_csv(wave CSV) │
|
||||
│ │ ├─ Execute post-wave interactive tasks (testing) │
|
||||
│ │ ├─ Merge all results into master tasks.csv │
|
||||
│ │ └─ Check: any failed? → skip dependents │
|
||||
│ └─ discoveries.ndjson shared across all modes (append-only) │
|
||||
│ │
|
||||
│ Phase 3: Results Aggregation │
|
||||
│ ├─ Export final results.csv │
|
||||
│ ├─ Generate context.md with all findings │
|
||||
│ ├─ Display summary: issues found/fixed, test pass rate │
|
||||
│ └─ Offer: view results | retry failed | done │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Task Classification Rules
|
||||
|
||||
Each task is classified by `exec_mode`:
|
||||
|
||||
| exec_mode | Mechanism | Criteria |
|
||||
|-----------|-----------|----------|
|
||||
| `csv-wave` | `spawn_agents_on_csv` | One-shot, structured I/O, no multi-round interaction |
|
||||
| `interactive` | `spawn_agent`/`wait`/`send_input`/`close_agent` | Multi-round, clarification, inline utility |
|
||||
|
||||
**Classification Decision**:
|
||||
|
||||
| Task Property | Classification |
|
||||
|---------------|---------------|
|
||||
| Scanning tasks (pattern matching, issue detection) | `csv-wave` |
|
||||
| Diagnosis tasks (root cause analysis) | `csv-wave` |
|
||||
| Design tasks (solution design, user interaction) | `interactive` |
|
||||
| Implementation tasks (code fixes) | `csv-wave` |
|
||||
| Testing tasks (validation, iteration) | `interactive` |
|
||||
| Exploration tasks (framework patterns, component inventory) | `interactive` |
|
||||
|
||||
---
|
||||
|
||||
## CSV Schema
|
||||
|
||||
### tasks.csv (Master State)
|
||||
|
||||
```csv
|
||||
id,title,description,deps,context_from,exec_mode,role,component,wave,status,findings,issues_found,issues_fixed,error
|
||||
EXPLORE-001,Framework Exploration,Explore React component patterns and conventions,,,"interactive",explorer,,1,pending,"","","",""
|
||||
SCAN-001,Scan for UX issues,Scan components for unresponsive buttons and missing feedback,EXPLORE-001,EXPLORE-001,"csv-wave",scanner,Button,2,pending,"","","",""
|
||||
DIAG-001,Diagnose root causes,Analyze root causes of identified UX issues,SCAN-001,SCAN-001,"csv-wave",diagnoser,Button,3,pending,"","","",""
|
||||
DESIGN-001,Design solutions,Design fix approach for UX issues,DIAG-001,DIAG-001,"interactive",designer,Button,4,pending,"","","",""
|
||||
IMPL-001,Implement fixes,Apply fixes to Button component,DESIGN-001,DESIGN-001,"csv-wave",implementer,Button,5,pending,"","","",""
|
||||
TEST-001,Test fixes,Validate fixes and run tests,IMPL-001,IMPL-001,"interactive",tester,Button,6,pending,"","","",""
|
||||
```
|
||||
|
||||
**Columns**:
|
||||
|
||||
| Column | Phase | Description |
|
||||
|--------|-------|-------------|
|
||||
| `id` | Input | Unique task identifier (string) |
|
||||
| `title` | Input | Short task title |
|
||||
| `description` | Input | Detailed task description |
|
||||
| `deps` | Input | Semicolon-separated dependency task IDs |
|
||||
| `context_from` | Input | Semicolon-separated task IDs whose findings this task needs |
|
||||
| `exec_mode` | Input | `csv-wave` or `interactive` |
|
||||
| `role` | Input | Role name: explorer, scanner, diagnoser, designer, implementer, tester |
|
||||
| `component` | Input | Component name being processed (empty for exploration) |
|
||||
| `wave` | Computed | Wave number (computed by topological sort, 1-based) |
|
||||
| `status` | Output | `pending` → `completed` / `failed` / `skipped` |
|
||||
| `findings` | Output | Key discoveries or implementation notes (max 500 chars) |
|
||||
| `issues_found` | Output | Number of issues found (scanner/diagnoser only) |
|
||||
| `issues_fixed` | Output | Number of issues fixed (implementer only) |
|
||||
| `error` | Output | Error message if failed (empty if success) |
|
||||
|
||||
### Per-Wave CSV (Temporary)
|
||||
|
||||
Each wave generates a temporary `wave-{N}.csv` with extra `prev_context` column (csv-wave tasks only).
|
||||
|
||||
---
|
||||
|
||||
## Agent Registry (Interactive Agents)
|
||||
|
||||
| Agent | Role File | Pattern | Responsibility | Position |
|
||||
|-------|-----------|---------|----------------|----------|
|
||||
| explorer | ~/.codex/agents/ux-explorer.md | 2.3 | Explore codebase for UI component patterns | pre-wave (Phase 0) |
|
||||
| designer | ~/.codex/agents/ux-designer.md | 2.4 | Design fix approach for UX issues | pre-wave (per component) |
|
||||
| tester | ~/.codex/agents/ux-tester.md | 2.4 | Validate fixes and run tests | post-wave (per component) |
|
||||
|
||||
> **COMPACT PROTECTION**: Agent files are execution documents. When context compression occurs, **you MUST immediately `Read` the corresponding agent.md** to reload.
|
||||
|
||||
---
|
||||
|
||||
## Output Artifacts
|
||||
|
||||
| File | Purpose | Lifecycle |
|
||||
|------|---------|-----------|
|
||||
| `tasks.csv` | Master state — all tasks with status/findings | Updated after each wave |
|
||||
| `wave-{N}.csv` | Per-wave input (temporary, csv-wave tasks only) | Created before wave, deleted after |
|
||||
| `results.csv` | Final export of all task results | Created in Phase 3 |
|
||||
| `discoveries.ndjson` | Shared exploration board (all agents, both modes) | Append-only, carries across waves |
|
||||
| `context.md` | Human-readable execution report | Created in Phase 3 |
|
||||
| `interactive/{id}-result.json` | Results from interactive tasks | Created per interactive task |
|
||||
| `agents/registry.json` | Active interactive agent tracking | Updated on spawn/close |
|
||||
| `artifacts/scan-report.md` | Scanner findings | Created by scanner |
|
||||
| `artifacts/diagnosis.md` | Diagnoser analysis | Created by diagnoser |
|
||||
| `artifacts/design-guide.md` | Designer solutions | Created by designer |
|
||||
| `artifacts/fixes/` | Implementation files | Created by implementer |
|
||||
| `artifacts/test-report.md` | Tester validation | Created by tester |
|
||||
|
||||
---
|
||||
|
||||
## Session Structure
|
||||
|
||||
```
|
||||
.workflow/.csv-wave/{session-id}/
|
||||
├── tasks.csv # Master state (all tasks, both modes)
|
||||
├── results.csv # Final results export
|
||||
├── discoveries.ndjson # Shared discovery board (all agents)
|
||||
├── context.md # Human-readable report
|
||||
├── wave-{N}.csv # Temporary per-wave input (csv-wave only)
|
||||
├── interactive/ # Interactive task artifacts
|
||||
│ ├── {id}-result.json # Per-task results
|
||||
│ └── cache-index.json # Shared exploration cache
|
||||
├── agents/
|
||||
│ └── registry.json # Active interactive agent tracking
|
||||
└── artifacts/ # Role deliverables
|
||||
├── scan-report.md
|
||||
├── diagnosis.md
|
||||
├── design-guide.md
|
||||
├── fixes/
|
||||
└── test-report.md
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Implementation
|
||||
|
||||
### Session Initialization
|
||||
|
||||
```javascript
|
||||
// Parse arguments
|
||||
const args = parseArguments($ARGUMENTS)
|
||||
const autoYes = args.yes || args.y
|
||||
const concurrency = args.concurrency || args.c || 4
|
||||
const continueMode = args.continue
|
||||
const projectPath = args._[0]
|
||||
const framework = args.framework
|
||||
|
||||
// Validate project path
|
||||
if (!projectPath) {
|
||||
throw new Error("Project path required")
|
||||
}
|
||||
|
||||
// Generate session ID
|
||||
const timestamp = Math.floor(Date.now() / 1000)
|
||||
const sessionId = `ux-improve-${timestamp}`
|
||||
const sessionDir = `.workflow/.csv-wave/${sessionId}`
|
||||
|
||||
// Create session structure
|
||||
Bash(`mkdir -p "${sessionDir}/interactive" "${sessionDir}/agents" "${sessionDir}/artifacts/fixes"`)
|
||||
|
||||
// Initialize registry
|
||||
Write(`${sessionDir}/agents/registry.json`, JSON.stringify({
|
||||
active: [],
|
||||
closed: [],
|
||||
created_at: new Date().toISOString()
|
||||
}, null, 2))
|
||||
|
||||
// Initialize discoveries
|
||||
Write(`${sessionDir}/discoveries.ndjson`, '')
|
||||
|
||||
// Store session config
|
||||
Write(`${sessionDir}/config.json`, JSON.stringify({
|
||||
project_path: projectPath,
|
||||
framework: framework || "auto-detect",
|
||||
max_test_iterations: 5
|
||||
}, null, 2))
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Phase 0: Framework Detection & Exploration (Interactive)
|
||||
|
||||
**Objective**: Detect UI framework and explore component patterns.
|
||||
|
||||
```javascript
|
||||
// Spawn explorer
|
||||
const explorer = spawn_agent({
|
||||
message: `### MANDATORY FIRST STEPS
|
||||
1. Read: ~/.codex/agents/ux-explorer.md
|
||||
|
||||
---
|
||||
|
||||
## Task Assignment
|
||||
|
||||
**Goal**: Explore codebase for UI component patterns and framework conventions
|
||||
|
||||
**Project Path**: ${projectPath}
|
||||
|
||||
**Framework**: ${framework || "auto-detect"}
|
||||
|
||||
**Session Directory**: ${sessionDir}
|
||||
|
||||
**Deliverables**:
|
||||
- Framework detection (if auto-detect)
|
||||
- Component inventory with file paths
|
||||
- Pattern analysis (state management, event handling, styling)
|
||||
- Exploration cache for downstream tasks
|
||||
|
||||
**Instructions**:
|
||||
1. Detect framework if not specified (check package.json, file extensions)
|
||||
2. Scan for UI components (*.tsx, *.vue, etc.)
|
||||
3. Analyze component patterns and conventions
|
||||
4. Build component inventory
|
||||
5. Cache findings in explorations/cache-index.json
|
||||
6. Output result as JSON with framework and component list`
|
||||
})
|
||||
|
||||
// Wait for completion
|
||||
const result = wait({ ids: [explorer], timeout_ms: 600000 })
|
||||
|
||||
if (result.timed_out) {
|
||||
send_input({ id: explorer, message: "Please finalize exploration and output current findings." })
|
||||
const retry = wait({ ids: [explorer], timeout_ms: 120000 })
|
||||
}
|
||||
|
||||
// Store result
|
||||
const explorerOutput = JSON.parse(result.output)
|
||||
Write(`${sessionDir}/interactive/EXPLORE-001-result.json`, JSON.stringify({
|
||||
task_id: "EXPLORE-001",
|
||||
status: "completed",
|
||||
findings: explorerOutput.summary,
|
||||
framework: explorerOutput.framework,
|
||||
component_count: explorerOutput.components.length,
|
||||
timestamp: new Date().toISOString()
|
||||
}, null, 2))
|
||||
|
||||
close_agent({ id: explorer })
|
||||
|
||||
// Update config with detected framework
|
||||
const config = JSON.parse(Read(`${sessionDir}/config.json`))
|
||||
config.framework = explorerOutput.framework
|
||||
Write(`${sessionDir}/config.json`, JSON.stringify(config, null, 2))
|
||||
```
|
||||
|
||||
**Success Criteria**:
|
||||
- Framework detected or confirmed
|
||||
- Component inventory created
|
||||
- Exploration cache available for downstream tasks
|
||||
|
||||
---
|
||||
|
||||
### Phase 1: Requirement → CSV + Classification
|
||||
|
||||
**Objective**: Generate task breakdown for UX improvement pipeline per component.
|
||||
|
||||
```javascript
|
||||
// Load exploration results
|
||||
const explorationResult = JSON.parse(Read(`${sessionDir}/interactive/EXPLORE-001-result.json`))
|
||||
const components = explorationResult.components || []
|
||||
|
||||
// Generate tasks for each component
|
||||
const allTasks = []
|
||||
let taskCounter = 1
|
||||
|
||||
// Add exploration task (already completed)
|
||||
allTasks.push({
|
||||
id: "EXPLORE-001",
|
||||
title: "Framework Exploration",
|
||||
description: "Explore component patterns and conventions",
|
||||
deps: "",
|
||||
context_from: "",
|
||||
exec_mode: "interactive",
|
||||
role: "explorer",
|
||||
component: "",
|
||||
wave: 1,
|
||||
status: "completed",
|
||||
findings: explorationResult.findings,
|
||||
issues_found: "",
|
||||
issues_fixed: "",
|
||||
error: ""
|
||||
})
|
||||
|
||||
// For each component, create pipeline: scan -> diagnose -> design -> implement -> test
|
||||
for (const component of components) {
|
||||
const compName = component.name
|
||||
const compPath = component.path
|
||||
|
||||
// Scan task (csv-wave)
|
||||
const scanId = `SCAN-${String(taskCounter).padStart(3, '0')}`
|
||||
allTasks.push({
|
||||
id: scanId,
|
||||
title: `Scan ${compName}`,
|
||||
description: `Scan ${compName} component for UX issues: unresponsive buttons, missing feedback, state refresh problems\n\nFile: ${compPath}`,
|
||||
deps: "EXPLORE-001",
|
||||
context_from: "EXPLORE-001",
|
||||
exec_mode: "csv-wave",
|
||||
role: "scanner",
|
||||
component: compName,
|
||||
wave: 0, // Computed later
|
||||
status: "pending",
|
||||
findings: "",
|
||||
issues_found: "",
|
||||
issues_fixed: "",
|
||||
error: ""
|
||||
})
|
||||
|
||||
// Diagnose task (csv-wave)
|
||||
const diagId = `DIAG-${String(taskCounter).padStart(3, '0')}`
|
||||
allTasks.push({
|
||||
id: diagId,
|
||||
title: `Diagnose ${compName}`,
|
||||
description: `Analyze root causes of UX issues in ${compName}\n\nFile: ${compPath}`,
|
||||
deps: scanId,
|
||||
context_from: scanId,
|
||||
exec_mode: "csv-wave",
|
||||
role: "diagnoser",
|
||||
component: compName,
|
||||
wave: 0,
|
||||
status: "pending",
|
||||
findings: "",
|
||||
issues_found: "",
|
||||
issues_fixed: "",
|
||||
error: ""
|
||||
})
|
||||
|
||||
// Design task (interactive)
|
||||
const designId = `DESIGN-${String(taskCounter).padStart(3, '0')}`
|
||||
allTasks.push({
|
||||
id: designId,
|
||||
title: `Design fixes for ${compName}`,
|
||||
description: `Design fix approach for UX issues in ${compName}\n\nFile: ${compPath}`,
|
||||
deps: diagId,
|
||||
context_from: diagId,
|
||||
exec_mode: "interactive",
|
||||
role: "designer",
|
||||
component: compName,
|
||||
wave: 0,
|
||||
status: "pending",
|
||||
findings: "",
|
||||
issues_found: "",
|
||||
issues_fixed: "",
|
||||
error: ""
|
||||
})
|
||||
|
||||
// Implement task (csv-wave)
|
||||
const implId = `IMPL-${String(taskCounter).padStart(3, '0')}`
|
||||
allTasks.push({
|
||||
id: implId,
|
||||
title: `Implement fixes for ${compName}`,
|
||||
description: `Apply fixes to ${compName} component\n\nFile: ${compPath}`,
|
||||
deps: designId,
|
||||
context_from: designId,
|
||||
exec_mode: "csv-wave",
|
||||
role: "implementer",
|
||||
component: compName,
|
||||
wave: 0,
|
||||
status: "pending",
|
||||
findings: "",
|
||||
issues_found: "",
|
||||
issues_fixed: "",
|
||||
error: ""
|
||||
})
|
||||
|
||||
// Test task (interactive)
|
||||
const testId = `TEST-${String(taskCounter).padStart(3, '0')}`
|
||||
allTasks.push({
|
||||
id: testId,
|
||||
title: `Test fixes for ${compName}`,
|
||||
description: `Validate fixes and run tests for ${compName}\n\nFile: ${compPath}`,
|
||||
deps: implId,
|
||||
context_from: implId,
|
||||
exec_mode: "interactive",
|
||||
role: "tester",
|
||||
component: compName,
|
||||
wave: 0,
|
||||
status: "pending",
|
||||
findings: "",
|
||||
issues_found: "",
|
||||
issues_fixed: "",
|
||||
error: ""
|
||||
})
|
||||
|
||||
taskCounter++
|
||||
}
|
||||
|
||||
// Compute waves via topological sort
|
||||
const tasksWithWaves = computeWaves(allTasks)
|
||||
|
||||
// Write master CSV
|
||||
writeMasterCSV(`${sessionDir}/tasks.csv`, tasksWithWaves)
|
||||
|
||||
// User validation (skip if autoYes)
|
||||
if (!autoYes) {
|
||||
const approval = AskUserQuestion({
|
||||
questions: [{
|
||||
question: `Generated ${tasksWithWaves.length} tasks for ${components.length} components. Proceed?`,
|
||||
header: "Task Breakdown Validation",
|
||||
multiSelect: false,
|
||||
options: [
|
||||
{ label: "Proceed", description: "Start UX improvement pipeline" },
|
||||
{ label: "Cancel", description: "Abort workflow" }
|
||||
]
|
||||
}]
|
||||
})
|
||||
|
||||
if (approval.answers[0] !== "Proceed") {
|
||||
throw new Error("User cancelled workflow")
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Success Criteria**:
|
||||
- tasks.csv created with valid schema, wave, and exec_mode assignments
|
||||
- No circular dependencies
|
||||
- User approved (or AUTO_YES)
|
||||
|
||||
---
|
||||
|
||||
### Phase 2: Wave Execution Engine (Extended)
|
||||
|
||||
**Objective**: Execute tasks wave-by-wave with hybrid mechanism support.
|
||||
|
||||
(Implementation follows same pattern as team-roadmap-dev Phase 2, adapted for UX improvement roles)
|
||||
|
||||
---
|
||||
|
||||
### Phase 3: Results Aggregation
|
||||
|
||||
**Objective**: Generate final results and human-readable report.
|
||||
|
||||
```javascript
|
||||
// Load final master CSV
|
||||
const finalCSV = readMasterCSV(`${sessionDir}/tasks.csv`)
|
||||
|
||||
// Calculate metrics
|
||||
const completed = finalCSV.filter(t => t.status === 'completed').length
|
||||
const failed = finalCSV.filter(t => t.status === 'failed').length
|
||||
const skipped = finalCSV.filter(t => t.status === 'skipped').length
|
||||
const totalIssuesFound = finalCSV.reduce((sum, t) => sum + (parseInt(t.issues_found) || 0), 0)
|
||||
const totalIssuesFixed = finalCSV.reduce((sum, t) => sum + (parseInt(t.issues_fixed) || 0), 0)
|
||||
|
||||
// Export results.csv
|
||||
writeFinalResults(`${sessionDir}/results.csv`, finalCSV)
|
||||
|
||||
// Generate context.md
|
||||
const contextMd = generateUXContextReport(finalCSV, sessionDir, {
|
||||
totalIssuesFound,
|
||||
totalIssuesFixed
|
||||
})
|
||||
Write(`${sessionDir}/context.md`, contextMd)
|
||||
|
||||
// Cleanup active agents
|
||||
const registry = JSON.parse(Read(`${sessionDir}/agents/registry.json`))
|
||||
for (const agent of registry.active) {
|
||||
close_agent({ id: agent.id })
|
||||
}
|
||||
registry.active = []
|
||||
Write(`${sessionDir}/agents/registry.json`, JSON.stringify(registry, null, 2))
|
||||
|
||||
// Display summary
|
||||
console.log(`\n=== UX Improvement Pipeline Complete ===`)
|
||||
console.log(`Completed: ${completed}`)
|
||||
console.log(`Failed: ${failed}`)
|
||||
console.log(`Skipped: ${skipped}`)
|
||||
console.log(`Issues Found: ${totalIssuesFound}`)
|
||||
console.log(`Issues Fixed: ${totalIssuesFixed}`)
|
||||
console.log(`Fix Rate: ${totalIssuesFound > 0 ? Math.round(totalIssuesFixed / totalIssuesFound * 100) : 0}%`)
|
||||
console.log(`\nResults: ${sessionDir}/results.csv`)
|
||||
console.log(`Report: ${sessionDir}/context.md`)
|
||||
|
||||
// Offer next steps
|
||||
const nextStep = AskUserQuestion({
|
||||
questions: [{
|
||||
question: "UX Improvement pipeline complete. What would you like to do?",
|
||||
header: "Completion",
|
||||
multiSelect: false,
|
||||
options: [
|
||||
{ label: "Archive & Clean", description: "Archive session and clean up team resources" },
|
||||
{ label: "Keep Active", description: "Keep session for follow-up work" },
|
||||
{ label: "Export Results", description: "Export deliverables to specified location" }
|
||||
]
|
||||
}]
|
||||
})
|
||||
|
||||
if (nextStep.answers[0] === "Archive & Clean") {
|
||||
Bash(`tar -czf "${sessionDir}.tar.gz" "${sessionDir}" && rm -rf "${sessionDir}"`)
|
||||
console.log(`Session archived to ${sessionDir}.tar.gz`)
|
||||
}
|
||||
```
|
||||
|
||||
**Success Criteria**:
|
||||
- results.csv exported with UX metrics
|
||||
- context.md generated with issue summary
|
||||
- All interactive agents closed
|
||||
- Summary displayed to user
|
||||
|
||||
---
|
||||
|
||||
## Shared Discovery Board Protocol
|
||||
|
||||
All agents share `discoveries.ndjson` for UX findings.
|
||||
|
||||
**Discovery Types**:
|
||||
|
||||
| Type | Dedup Key | Data Schema | Description |
|
||||
|------|-----------|-------------|-------------|
|
||||
| `ux_issue` | `component+type` | `{component, type, description, severity}` | UX issues discovered |
|
||||
| `pattern` | `pattern` | `{pattern, files[], description}` | UI patterns identified |
|
||||
| `fix_approach` | `component+issue` | `{component, issue, approach, rationale}` | Fix strategies |
|
||||
| `test_result` | `component+test` | `{component, test, status, details}` | Test outcomes |
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Error | Resolution |
|
||||
|-------|------------|
|
||||
| Framework detection fails | AskUserQuestion for framework selection |
|
||||
| No components found | Complete with empty report, note in findings |
|
||||
| Circular dependency | Detect in wave computation, abort with error |
|
||||
| CSV agent timeout | Mark as failed, continue with wave |
|
||||
| Interactive agent timeout | Urge convergence via send_input |
|
||||
| Test iterations exceeded (5) | Accept current state, continue |
|
||||
| All agents in wave failed | Log error, offer retry or abort |
|
||||
| Project path invalid | Re-prompt user for valid path |
|
||||
|
||||
---
|
||||
|
||||
## Core Rules
|
||||
|
||||
1. **Start Immediately**: First action is session initialization, then Phase 0
|
||||
2. **Wave Order is Sacred**: Never execute wave N before wave N-1 completes
|
||||
3. **CSV is Source of Truth**: Master tasks.csv holds all state
|
||||
4. **CSV First**: Default to csv-wave; use interactive for design/testing
|
||||
5. **Context Propagation**: prev_context built from master CSV
|
||||
6. **Discovery Board is Append-Only**: Never clear discoveries.ndjson
|
||||
7. **Skip on Failure**: If dependency failed, skip dependent task
|
||||
8. **Lifecycle Balance**: Every spawn_agent has matching close_agent
|
||||
9. **Cleanup Temp Files**: Remove wave-{N}.csv after merge
|
||||
10. **DO NOT STOP**: Continuous execution until all waves complete
|
||||
136
.codex/skills/team-ux-improve/agents/ux-designer.md
Normal file
136
.codex/skills/team-ux-improve/agents/ux-designer.md
Normal file
@@ -0,0 +1,136 @@
|
||||
# UX Designer Agent
|
||||
|
||||
Interactive agent for designing fix approaches for identified UX issues. Proposes solutions and may interact with user for clarification.
|
||||
|
||||
## Identity
|
||||
|
||||
- **Type**: `interactive`
|
||||
- **Role File**: `~/.codex/agents/ux-designer.md`
|
||||
- **Responsibility**: Solution design for UX issues
|
||||
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
- Load role definition via MANDATORY FIRST STEPS pattern
|
||||
- Produce structured output following template
|
||||
- Design fix approaches for all identified issues
|
||||
- Consider framework patterns and conventions
|
||||
- Generate design guide for implementer
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- Skip the MANDATORY FIRST STEPS role loading
|
||||
- Execute implementation directly
|
||||
- Skip issue analysis step
|
||||
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
### Available Tools
|
||||
|
||||
| Tool | Type | Purpose |
|
||||
|------|------|---------|
|
||||
| `Read` | File I/O | Load diagnosis, exploration cache |
|
||||
| `Write` | File I/O | Generate design guide |
|
||||
| `AskUserQuestion` | Human interaction | Clarify design decisions if needed |
|
||||
|
||||
---
|
||||
|
||||
## Execution
|
||||
|
||||
### Phase 1: Issue Analysis
|
||||
|
||||
**Objective**: Analyze diagnosed issues and understand context.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Read diagnosis findings from prev_context
|
||||
2. Load exploration cache for framework patterns
|
||||
3. Read discoveries.ndjson for related findings
|
||||
4. Categorize issues by type and severity
|
||||
|
||||
**Output**: Issue analysis summary
|
||||
|
||||
---
|
||||
|
||||
### Phase 2: Solution Design
|
||||
|
||||
**Objective**: Design fix approaches for each issue.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. For each issue:
|
||||
- Identify root cause from diagnosis
|
||||
- Propose fix approach following framework patterns
|
||||
- Consider side effects and edge cases
|
||||
- Define validation criteria
|
||||
2. Prioritize fixes by severity
|
||||
3. Document rationale for each approach
|
||||
|
||||
**Output**: Fix approaches per issue
|
||||
|
||||
---
|
||||
|
||||
### Phase 3: Design Guide Generation
|
||||
|
||||
**Objective**: Generate design guide for implementer.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Format design guide:
|
||||
```markdown
|
||||
# Design Guide: {Component}
|
||||
|
||||
## Issues to Fix
|
||||
|
||||
### Issue 1: {description}
|
||||
- **Severity**: {high/medium/low}
|
||||
- **Root Cause**: {cause}
|
||||
- **Fix Approach**: {approach}
|
||||
- **Rationale**: {why this approach}
|
||||
- **Validation**: {how to verify}
|
||||
|
||||
## Implementation Notes
|
||||
- Follow {framework} patterns
|
||||
- Test cases needed: {list}
|
||||
```
|
||||
2. Write design guide to artifacts/design-guide.md
|
||||
3. Share fix approaches via discoveries.ndjson
|
||||
|
||||
**Output**: Design guide file
|
||||
|
||||
---
|
||||
|
||||
## Structured Output Template
|
||||
|
||||
```
|
||||
## Summary
|
||||
- Designed fixes for {N} issues in {component}
|
||||
|
||||
## Findings
|
||||
- Issue 1: {description} → Fix: {approach}
|
||||
- Issue 2: {description} → Fix: {approach}
|
||||
|
||||
## Deliverables
|
||||
- File: artifacts/design-guide.md
|
||||
Content: Fix approaches with rationale and validation criteria
|
||||
|
||||
## Output JSON
|
||||
{
|
||||
"design_guide_path": "artifacts/design-guide.md",
|
||||
"issues_addressed": {N},
|
||||
"summary": "Designed fixes for {N} issues"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| No issues found | Generate empty design guide, note in findings |
|
||||
| Ambiguous fix approach | Ask user for guidance via AskUserQuestion |
|
||||
| Conflicting patterns | Document trade-offs, recommend approach |
|
||||
158
.codex/skills/team-ux-improve/agents/ux-explorer.md
Normal file
158
.codex/skills/team-ux-improve/agents/ux-explorer.md
Normal file
@@ -0,0 +1,158 @@
|
||||
# UX Explorer Agent
|
||||
|
||||
Interactive agent for exploring codebase to identify UI component patterns and framework conventions.
|
||||
|
||||
## Identity
|
||||
|
||||
- **Type**: `interactive`
|
||||
- **Role File**: `~/.codex/agents/ux-explorer.md`
|
||||
- **Responsibility**: Framework detection and component inventory
|
||||
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
- Load role definition via MANDATORY FIRST STEPS pattern
|
||||
- Produce structured output following template
|
||||
- Detect UI framework (React/Vue/etc.)
|
||||
- Build component inventory with file paths
|
||||
- Cache findings for downstream tasks
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- Skip the MANDATORY FIRST STEPS role loading
|
||||
- Execute implementation or fix tasks
|
||||
- Skip framework detection step
|
||||
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
### Available Tools
|
||||
|
||||
| Tool | Type | Purpose |
|
||||
|------|------|---------|
|
||||
| `Read` | File I/O | Load package.json, component files |
|
||||
| `Write` | File I/O | Generate exploration cache |
|
||||
| `Glob` | File search | Find component files |
|
||||
| `Bash` | CLI execution | Run framework detection commands |
|
||||
|
||||
---
|
||||
|
||||
## Execution
|
||||
|
||||
### Phase 1: Framework Detection
|
||||
|
||||
**Objective**: Detect UI framework if not specified.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. If framework specified in arguments, use it
|
||||
2. Otherwise, detect from package.json:
|
||||
- Check dependencies for react, vue, angular, svelte
|
||||
- Check file extensions (*.tsx → React, *.vue → Vue)
|
||||
3. Validate framework detection
|
||||
|
||||
**Output**: Framework name (react/vue/angular/svelte)
|
||||
|
||||
---
|
||||
|
||||
### Phase 2: Component Inventory
|
||||
|
||||
**Objective**: Build inventory of UI components.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Search for component files based on framework:
|
||||
- React: `**/*.tsx`, `**/*.jsx`
|
||||
- Vue: `**/*.vue`
|
||||
- Angular: `**/*.component.ts`
|
||||
2. For each component:
|
||||
- Extract component name
|
||||
- Record file path
|
||||
- Identify component type (button, form, modal, etc.)
|
||||
3. Build component list
|
||||
|
||||
**Output**: Component inventory with paths
|
||||
|
||||
---
|
||||
|
||||
### Phase 3: Pattern Analysis
|
||||
|
||||
**Objective**: Analyze component patterns and conventions.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Sample components to identify patterns:
|
||||
- State management (useState, Vuex, etc.)
|
||||
- Event handling patterns
|
||||
- Styling approach (CSS modules, styled-components, etc.)
|
||||
2. Document conventions
|
||||
3. Identify common anti-patterns
|
||||
|
||||
**Output**: Pattern analysis summary
|
||||
|
||||
---
|
||||
|
||||
### Phase 4: Cache Generation
|
||||
|
||||
**Objective**: Generate exploration cache for downstream tasks.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Create cache structure:
|
||||
```json
|
||||
{
|
||||
"framework": "react",
|
||||
"components": [
|
||||
{"name": "Button", "path": "src/components/Button.tsx", "type": "button"},
|
||||
{"name": "Form", "path": "src/components/Form.tsx", "type": "form"}
|
||||
],
|
||||
"patterns": {
|
||||
"state_management": "React hooks",
|
||||
"event_handling": "inline handlers",
|
||||
"styling": "CSS modules"
|
||||
},
|
||||
"conventions": ["PascalCase component names", "Props interface per component"]
|
||||
}
|
||||
```
|
||||
2. Write cache to explorations/cache-index.json
|
||||
|
||||
**Output**: Exploration cache file
|
||||
|
||||
---
|
||||
|
||||
## Structured Output Template
|
||||
|
||||
```
|
||||
## Summary
|
||||
- Detected framework: {framework}
|
||||
- Found {N} components
|
||||
|
||||
## Findings
|
||||
- Component inventory: {N} components identified
|
||||
- Patterns: {state management}, {event handling}, {styling}
|
||||
- Conventions: {list}
|
||||
|
||||
## Deliverables
|
||||
- File: explorations/cache-index.json
|
||||
Content: Component inventory and pattern analysis
|
||||
|
||||
## Output JSON
|
||||
{
|
||||
"framework": "{framework}",
|
||||
"components": [{component list}],
|
||||
"component_count": {N},
|
||||
"summary": "Explored {N} components in {framework} project"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| Framework detection fails | Ask user via AskUserQuestion |
|
||||
| No components found | Return empty inventory, note in findings |
|
||||
| Invalid project path | Report error, request valid path |
|
||||
174
.codex/skills/team-ux-improve/agents/ux-tester.md
Normal file
174
.codex/skills/team-ux-improve/agents/ux-tester.md
Normal file
@@ -0,0 +1,174 @@
|
||||
# UX Tester Agent
|
||||
|
||||
Interactive agent for validating fixes and running tests. Iterates up to 5 times if tests fail.
|
||||
|
||||
## Identity
|
||||
|
||||
- **Type**: `interactive`
|
||||
- **Role File**: `~/.codex/agents/ux-tester.md`
|
||||
- **Responsibility**: Fix validation and testing
|
||||
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
- Load role definition via MANDATORY FIRST STEPS pattern
|
||||
- Produce structured output following template
|
||||
- Run tests and validate fixes
|
||||
- Iterate up to 5 times on test failures
|
||||
- Generate test report
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- Skip the MANDATORY FIRST STEPS role loading
|
||||
- Exceed 5 test iterations
|
||||
- Skip test execution step
|
||||
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
### Available Tools
|
||||
|
||||
| Tool | Type | Purpose |
|
||||
|------|------|---------|
|
||||
| `Bash` | CLI execution | Run tests, linters, build |
|
||||
| `Read` | File I/O | Load implementation findings, design guide |
|
||||
| `Write` | File I/O | Generate test report |
|
||||
|
||||
---
|
||||
|
||||
## Execution
|
||||
|
||||
### Phase 1: Test Preparation
|
||||
|
||||
**Objective**: Identify tests to run and prepare test environment.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Read implementation findings from prev_context
|
||||
2. Load design guide for validation criteria
|
||||
3. Identify test files related to component
|
||||
4. Check test framework (Jest, Vitest, etc.)
|
||||
|
||||
**Output**: Test plan
|
||||
|
||||
---
|
||||
|
||||
### Phase 2: Test Execution
|
||||
|
||||
**Objective**: Run tests and validate fixes (max 5 iterations).
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Run component tests:
|
||||
```bash
|
||||
npm test -- {component}.test
|
||||
```
|
||||
2. Run linter:
|
||||
```bash
|
||||
npm run lint
|
||||
```
|
||||
3. Check build:
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
4. Collect results
|
||||
5. If tests fail and iteration < 5:
|
||||
- Analyze failures
|
||||
- Apply quick fixes if possible
|
||||
- Re-run tests
|
||||
6. If iteration >= 5:
|
||||
- Accept current state
|
||||
- Document remaining issues
|
||||
|
||||
**Output**: Test results with pass/fail status
|
||||
|
||||
---
|
||||
|
||||
### Phase 3: Validation
|
||||
|
||||
**Objective**: Validate fixes against design guide criteria.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. For each validation criterion in design guide:
|
||||
- Check if met by implementation
|
||||
- Check if validated by tests
|
||||
- Document status
|
||||
2. Calculate fix success rate
|
||||
3. Identify remaining issues
|
||||
|
||||
**Output**: Validation summary
|
||||
|
||||
---
|
||||
|
||||
### Phase 4: Test Report Generation
|
||||
|
||||
**Objective**: Generate test report with results.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Format test report:
|
||||
```markdown
|
||||
# Test Report: {Component}
|
||||
|
||||
## Test Results
|
||||
- Tests passed: {X}/{Y}
|
||||
- Build status: {success/failed}
|
||||
- Linter warnings: {Z}
|
||||
|
||||
## Validation Status
|
||||
- Issue 1: {fixed/partial/unfixed}
|
||||
- Issue 2: {fixed/partial/unfixed}
|
||||
|
||||
## Remaining Issues
|
||||
- {list if any}
|
||||
|
||||
## Recommendation
|
||||
{approve/needs_work}
|
||||
```
|
||||
2. Write test report to artifacts/test-report.md
|
||||
3. Share test results via discoveries.ndjson
|
||||
|
||||
**Output**: Test report file
|
||||
|
||||
---
|
||||
|
||||
## Structured Output Template
|
||||
|
||||
```
|
||||
## Summary
|
||||
- Testing complete for {component}: {X}/{Y} tests passed
|
||||
|
||||
## Findings
|
||||
- Tests passed: {X}/{Y}
|
||||
- Build status: {success/failed}
|
||||
- Issues fixed: {N}
|
||||
- Remaining issues: {M}
|
||||
|
||||
## Deliverables
|
||||
- File: artifacts/test-report.md
|
||||
Content: Test results and validation status
|
||||
|
||||
## Output JSON
|
||||
{
|
||||
"test_report_path": "artifacts/test-report.md",
|
||||
"tests_passed": {X},
|
||||
"tests_total": {Y},
|
||||
"issues_fixed": {N},
|
||||
"recommendation": "approve" | "needs_work",
|
||||
"summary": "Testing complete: {X}/{Y} tests passed"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| Tests fail to run | Document as issue, continue validation |
|
||||
| Build fails | Mark as critical issue, recommend fix |
|
||||
| Test iterations exceed 5 | Accept current state, document remaining issues |
|
||||
| No test files found | Note in findings, perform manual validation |
|
||||
@@ -0,0 +1,55 @@
|
||||
## TASK ASSIGNMENT
|
||||
|
||||
### MANDATORY FIRST STEPS
|
||||
1. Read shared discoveries: {session_folder}/discoveries.ndjson (if exists, skip if not)
|
||||
2. Read project context: .workflow/project-tech.json (if exists)
|
||||
3. Read exploration cache: {session_folder}/explorations/cache-index.json (if exists)
|
||||
|
||||
---
|
||||
|
||||
## Your Task
|
||||
|
||||
**Task ID**: {id}
|
||||
**Title**: {title}
|
||||
**Description**: {description}
|
||||
**Role**: {role}
|
||||
**Component**: {component}
|
||||
|
||||
### Previous Tasks' Findings (Context)
|
||||
{prev_context}
|
||||
|
||||
---
|
||||
|
||||
## Execution Protocol
|
||||
|
||||
1. **Read discoveries**: Load {session_folder}/discoveries.ndjson for shared UX findings
|
||||
2. **Use context**: Apply previous tasks' findings from prev_context above
|
||||
3. **Execute**: Perform role-specific task
|
||||
- **Scanner**: Scan component for UX issues (unresponsive buttons, missing feedback, state refresh)
|
||||
- **Diagnoser**: Analyze root causes of identified issues
|
||||
- **Implementer**: Apply fixes following design guide
|
||||
4. **Share discoveries**: Append findings to shared board:
|
||||
```bash
|
||||
echo '{"ts":"<ISO8601>","worker":"{id}","type":"<type>","data":{...}}' >> {session_folder}/discoveries.ndjson
|
||||
```
|
||||
5. **Report result**: Return JSON via report_agent_job_result
|
||||
|
||||
### Discovery Types to Share
|
||||
- `ux_issue`: `{component, type, description, severity}` — UX issues discovered
|
||||
- `pattern`: `{pattern, files[], description}` — UI patterns identified
|
||||
- `fix_approach`: `{component, issue, approach, rationale}` — Fix strategies
|
||||
- `test_result`: `{component, test, status, details}` — Test outcomes
|
||||
|
||||
---
|
||||
|
||||
## Output (report_agent_job_result)
|
||||
|
||||
Return JSON:
|
||||
{
|
||||
"id": "{id}",
|
||||
"status": "completed" | "failed",
|
||||
"findings": "Key discoveries (max 500 chars)",
|
||||
"issues_found": "3",
|
||||
"issues_fixed": "3",
|
||||
"error": ""
|
||||
}
|
||||
87
.codex/skills/team-ux-improve/schemas/tasks-schema.md
Normal file
87
.codex/skills/team-ux-improve/schemas/tasks-schema.md
Normal file
@@ -0,0 +1,87 @@
|
||||
# UX Improvement — CSV Schema
|
||||
|
||||
## Master CSV: tasks.csv
|
||||
|
||||
### Column Definitions
|
||||
|
||||
#### Input Columns (Set by Decomposer)
|
||||
|
||||
| Column | Type | Required | Description | Example |
|
||||
|--------|------|----------|-------------|---------|
|
||||
| `id` | string | Yes | Unique task identifier | `"SCAN-001"` |
|
||||
| `title` | string | Yes | Short task title | `"Scan Button component"` |
|
||||
| `description` | string | Yes | Detailed task description (self-contained) | `"Scan Button component for UX issues..."` |
|
||||
| `deps` | string | No | Semicolon-separated dependency task IDs | `"EXPLORE-001"` |
|
||||
| `context_from` | string | No | Semicolon-separated task IDs for context | `"EXPLORE-001"` |
|
||||
| `exec_mode` | enum | Yes | Execution mechanism: `csv-wave` or `interactive` | `"csv-wave"` |
|
||||
| `role` | enum | Yes | Role name: `explorer`, `scanner`, `diagnoser`, `designer`, `implementer`, `tester` | `"scanner"` |
|
||||
| `component` | string | No | Component name being processed | `"Button"` |
|
||||
|
||||
#### Computed Columns (Set by Wave Engine)
|
||||
|
||||
| Column | Type | Description | Example |
|
||||
|--------|------|-------------|---------|
|
||||
| `wave` | integer | Wave number (1-based, from topological sort) | `2` |
|
||||
| `prev_context` | string | Aggregated findings from context_from tasks (per-wave CSV only) | `"[EXPLORE-001] Found 15 components..."` |
|
||||
|
||||
#### Output Columns (Set by Agent)
|
||||
|
||||
| Column | Type | Description | Example |
|
||||
|--------|------|-------------|---------|
|
||||
| `status` | enum | `pending` → `completed` / `failed` / `skipped` | `"completed"` |
|
||||
| `findings` | string | Key discoveries (max 500 chars) | `"Found 3 UX issues: unresponsive onClick..."` |
|
||||
| `issues_found` | string | Number of issues found (scanner/diagnoser) | `"3"` |
|
||||
| `issues_fixed` | string | Number of issues fixed (implementer) | `"3"` |
|
||||
| `error` | string | Error message if failed | `""` |
|
||||
|
||||
---
|
||||
|
||||
### exec_mode Values
|
||||
|
||||
| Value | Mechanism | Description |
|
||||
|-------|-----------|-------------|
|
||||
| `csv-wave` | `spawn_agents_on_csv` | One-shot batch execution within wave |
|
||||
| `interactive` | `spawn_agent`/`wait`/`send_input`/`close_agent` | Multi-round individual execution |
|
||||
|
||||
---
|
||||
|
||||
### Example Data
|
||||
|
||||
```csv
|
||||
id,title,description,deps,context_from,exec_mode,role,component,wave,status,findings,issues_found,issues_fixed,error
|
||||
EXPLORE-001,Framework Exploration,Explore React component patterns,,,"interactive",explorer,,1,completed,"Found 15 components using React hooks","","",""
|
||||
SCAN-001,Scan Button,Scan Button for UX issues,EXPLORE-001,EXPLORE-001,"csv-wave",scanner,Button,2,pending,"","","",""
|
||||
DIAG-001,Diagnose Button,Analyze root causes in Button,SCAN-001,SCAN-001,"csv-wave",diagnoser,Button,3,pending,"","","",""
|
||||
DESIGN-001,Design Button fixes,Design fix approach for Button,DIAG-001,DIAG-001,"interactive",designer,Button,4,pending,"","","",""
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Discovery Types
|
||||
|
||||
| Type | Dedup Key | Data Schema | Description |
|
||||
|------|-----------|-------------|-------------|
|
||||
| `ux_issue` | `component+type` | `{component, type, description, severity}` | UX issues discovered |
|
||||
| `pattern` | `pattern` | `{pattern, files[], description}` | UI patterns identified |
|
||||
| `fix_approach` | `component+issue` | `{component, issue, approach, rationale}` | Fix strategies |
|
||||
| `test_result` | `component+test` | `{component, test, status, details}` | Test outcomes |
|
||||
|
||||
### Discovery NDJSON Format
|
||||
|
||||
```jsonl
|
||||
{"ts":"2026-03-08T14:30:22Z","worker":"SCAN-001","type":"ux_issue","data":{"component":"Button","type":"unresponsive_click","description":"onClick handler not firing","severity":"high"}}
|
||||
{"ts":"2026-03-08T14:35:10Z","worker":"DIAG-001","type":"pattern","data":{"pattern":"event delegation","files":["Button.tsx"],"description":"Using event delegation pattern"}}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Validation Rules
|
||||
|
||||
| Rule | Check | Error |
|
||||
|------|-------|-------|
|
||||
| Unique IDs | No duplicate `id` values | "Duplicate task ID: {id}" |
|
||||
| Valid deps | All dep IDs exist in tasks | "Unknown dependency: {dep_id}" |
|
||||
| No self-deps | Task cannot depend on itself | "Self-dependency: {id}" |
|
||||
| No circular deps | Topological sort completes | "Circular dependency detected" |
|
||||
| exec_mode valid | Value is `csv-wave` or `interactive` | "Invalid exec_mode: {value}" |
|
||||
| Role valid | role ∈ {explorer, scanner, diagnoser, designer, implementer, tester} | "Invalid role: {role}" |
|
||||
Reference in New Issue
Block a user