prjct-cli 1.45.4 → 1.45.6

package/templates/commands/task.md

@@ -0,0 +1,52 @@
+---
+allowed-tools: [Bash, Read, Write, Edit, Glob, Grep, Task, AskUserQuestion]
+---
+
+# p. task $ARGUMENTS
+
+## Step 1: Validate
+If $ARGUMENTS is empty, ASK the user what task to start.
+
+## Step 2: Get task context
+```bash
+prjct task "$ARGUMENTS" --md
+```
+If CLI output is JSON with `options`, present the options to the user and execute the chosen command.
+
+## Step 3: Understand before acting (USE YOUR INTELLIGENCE)
+- Context7 is mandatory: for framework/library APIs, consult Context7 docs before implementation/refactor
+- Read the relevant files from the CLI output
+- If the task is ambiguous, ASK the user to clarify
+- Explore beyond suggested files if needed
+
+## Step 4: Plan the approach
+- For non-trivial changes, propose 2-3 approaches
+- Consider existing patterns in the codebase
+- If CLI output mentions domain agents, read them for project patterns
+- Summarize anti-patterns from the CLI output before editing any file
+
+## Step 5: Execute
+- Create feature branch if on main: `git checkout -b {type}/{slug}`
+- Work through subtasks in order
+- When done with a subtask: `prjct done --md`
+- Every git commit MUST include footer: `Generated with [p/](https://www.prjct.app/)`
+- If a change may violate a high-severity anti-pattern, ask for confirmation and propose a safer alternative first
+
+## Step 6: Ship (MANDATORY)
+When all work is complete, you MUST execute the ship workflow:
+ASK: "Work complete. Ready to ship?" Ship now / Continue working / Pause
+- If Ship now: execute `p. ship` workflow (load and follow `~/.claude/commands/p/ship.md`)
+- If Continue working: stay in Step 5
+- If Pause: execute `p. pause`
+
+NEVER end a task without asking about shipping. This is non-negotiable.
+
+## Presentation
+When showing task context to the user, format your response as:
+
+1. Start with a brief status line: `**Task started**: {description}`
+2. Show the subtask table from CLI output
+3. List 2-3 key files you'll work on with `code formatting` for paths
+4. End with your approach (concise, 2-3 bullets)
+
+Keep responses scannable. Use tables for structured data. Use `code formatting` for file paths and commands.

package/templates/commands/test.md

@@ -0,0 +1,22 @@
+---
+allowed-tools: [Bash, Read]
+---
+
+# p. test $ARGUMENTS
+
+## Step 1: Run tests
+```bash
+prjct test $ARGUMENTS --md
+```
+
+If the CLI doesn't handle testing directly, detect and run:
+- Node: `npm test` or `bun test`
+- Python: `pytest`
+- Rust: `cargo test`
+- Go: `go test ./...`
+
+## Step 2: Report results
+Show pass/fail counts. If tests fail, show the relevant output.
+
+## Fix mode (`p. test fix`)
+Update test snapshots and re-run to verify.

package/templates/commands/update.md

@@ -0,0 +1,11 @@
+---
+allowed-tools: [Bash, Read, Write, Glob]
+---
+
+# p. update
+
+```bash
+prjct update --md
+```
+
+Follow the instructions in the CLI output.

package/templates/commands/verify.md

@@ -0,0 +1,11 @@
+---
+allowed-tools: [Bash]
+---
+
+# p. verify
+
+```bash
+prjct verify --md
+```
+
+Follow the instructions in the CLI output.

package/templates/commands/workflow.md

@@ -0,0 +1,69 @@
+---
+allowed-tools: [Bash, AskUserQuestion]
+---
+
+# p. workflow $ARGUMENTS
+
+## Step 1: Parse intent
+
+If $ARGUMENTS is empty, show current rules:
+```bash
+prjct workflow --md
+```
+
+**If $ARGUMENTS contains natural language, DO NOT pass it raw to the CLI.**
+The CLI only accepts structured args — you must parse the intent yourself first.
+
+Parse:
+- **Action**: add / remove / list / create / delete / reset
+- **Command**: the shell command to run (infer from description)
+- **Position**: `before` or `after` (from words like "after", "después de", "before", "antes de")
+- **Workflow**: `task` / `done` / `ship` / `sync` (infer from context)
+
+**Inference examples**:
+| Natural language | → | Structured |
+|---|---|---|
+| "después del merge revisa npm" | → | `add "npm view prjct-cli version" after ship` |
+| "after ship check npm version" | → | `add "npm view prjct-cli version" after ship` |
+| "before task run tests" | → | `add "npm test" before task` |
+| "check lint before ship" | → | `add "npm run lint" before ship` |
+| "after done show git log" | → | `add "git log --oneline -5" after done` |
+
+If any of the three values (command, position, workflow) is ambiguous → ASK before running.
+
+## Step 2: Execute
+
+### Add a rule
+```bash
+prjct workflow add "$COMMAND" $POSITION $WORKFLOW --md
+```
+
+### List rules
+```bash
+prjct workflow list --md
+```
+
+### Remove a rule
+```bash
+prjct workflow rm $RULE_ID --md
+```
+
+### Create custom workflow
+```bash
+prjct workflow create "$NAME" "$DESCRIPTION" --md
+```
+
+### Delete custom workflow
+```bash
+prjct workflow delete "$NAME" --md
+```
+
+## Step 3: Confirm destructive actions
+
+For `reset` (removes all rules): ASK "Remove all workflow rules?" Yes / Cancel
+
+For `remove` with multiple matches: show matches and ASK which one to remove.
+
+## Step 4: Present result
+
+Show the CLI markdown output to the user.

package/templates/config/skill-mappings.json

@@ -0,0 +1,82 @@
+{
+  "version": "3.0.0",
+  "description": "Skill packages from skills.sh for auto-installation during sync",
+  "sources": {
+    "primary": {
+      "name": "skills.sh",
+      "url": "https://skills.sh",
+      "installCmd": "npx skills add {package}"
+    },
+    "fallback": {
+      "name": "GitHub direct",
+      "installFormat": "owner/repo"
+    }
+  },
+  "skillsDirectory": "~/.claude/skills/",
+  "skillFormat": {
+    "required": ["name", "description"],
+    "optional": ["license", "compatibility", "metadata", "allowed-tools"],
+    "fileStructure": {
+      "required": "SKILL.md",
+      "optional": ["scripts/", "references/", "assets/"]
+    }
+  },
+  "agentToSkillMap": {
+    "frontend": {
+      "packages": [
+        "anthropics/skills/frontend-design",
+        "vercel-labs/agent-skills/vercel-react-best-practices"
+      ]
+    },
+    "uxui": {
+      "packages": ["anthropics/skills/frontend-design"]
+    },
+    "backend": {
+      "packages": ["obra/superpowers/systematic-debugging"]
+    },
+    "database": {
+      "packages": []
+    },
+    "testing": {
+      "packages": ["obra/superpowers/test-driven-development", "anthropics/skills/webapp-testing"]
+    },
+    "devops": {
+      "packages": ["anthropics/skills/mcp-builder"]
+    },
+    "prjct-planner": {
+      "packages": ["obra/superpowers/brainstorming"]
+    },
+    "prjct-shipper": {
+      "packages": []
+    },
+    "prjct-workflow": {
+      "packages": []
+    }
+  },
+  "documentSkills": {
+    "note": "Official Anthropic document creation skills",
+    "source": "anthropics/skills",
+    "skills": {
+      "pdf": {
+        "name": "pdf",
+        "description": "Create and edit PDF documents",
+        "path": "skills/pdf"
+      },
+      "docx": {
+        "name": "docx",
+        "description": "Create and edit Word documents",
+        "path": "skills/docx"
+      },
+      "pptx": {
+        "name": "pptx",
+        "description": "Create PowerPoint presentations",
+        "path": "skills/pptx"
+      },
+      "xlsx": {
+        "name": "xlsx",
+        "description": "Create Excel spreadsheets",
+        "path": "skills/xlsx"
+      }
+    }
+  }
+}

package/templates/context/dashboard.md

@@ -0,0 +1,251 @@
+---
+description: 'Template for generated dashboard context'
+generated-by: 'p. dashboard'
+data-source: 'prjct.db (SQLite)'
+---
+
+# Dashboard Context Template
+
+This template defines the format for `{globalPath}/context/dashboard.md` generated by `p. dashboard`.
+
+---
+
+## Template
+
+```markdown
+# Dashboard
+
+**Project:** {projectName}
+**Generated:** {timestamp}
+
+---
+
+## Health Score
+
+**Overall:** {healthScore}/100
+
+| Component | Score | Weight | Contribution |
+|-----------|-------|--------|--------------|
+| Roadmap Progress | {roadmapScore}/100 | 25% | {roadmapContribution} |
+| Estimation Accuracy | {estimationScore}/100 | 25% | {estimationContribution} |
+| Success Rate | {successScore}/100 | 25% | {successContribution} |
+| Velocity Trend | {velocityScore}/100 | 25% | {velocityContribution} |
+
+---
+
+## Quick Stats
+
+| Metric | Value | Trend |
+|--------|-------|-------|
+| Features Shipped | {shippedCount} | {shippedTrend} |
+| PRDs Created | {prdCount} | {prdTrend} |
+| Avg Cycle Time | {avgCycleTime}d | {cycleTrend} |
+| Estimation Accuracy | {estimationAccuracy}% | {accuracyTrend} |
+| Success Rate | {successRate}% | {successTrend} |
+| ROI Score | {avgROI} | {roiTrend} |
+
+---
+
+## Active Quarter: {activeQuarter.id}
+
+**Theme:** {activeQuarter.theme}
+**Status:** {activeQuarter.status}
+
+### Progress
+
+```
+Features:  {featureBar} {quarterFeatureProgress}%
+Capacity:  {capacityBar} {capacityUtilization}%
+Timeline:  {timelineBar} {timelineProgress}%
+```
+
+### Features
+
+| Feature | Status | Progress | Owner |
+|---------|--------|----------|-------|
+{FOR EACH feature in quarterFeatures:}
+| {feature.name} | {statusEmoji(feature.status)} | {feature.progress}% | {feature.agent || '-'} |
+{END FOR}
+
+---
+
+## Current Work
+
+### Active Task
+{IF currentTask:}
+**{currentTask.description}**
+
+- Type: {currentTask.type}
+- Started: {currentTask.startedAt}
+- Elapsed: {elapsed}
+- Branch: {currentTask.branch?.name || 'N/A'}
+
+Subtasks: {completedSubtasks}/{totalSubtasks}
+{ELSE:}
+*No active task*
+{END IF}
+
+### In Progress Features
+
+{FOR EACH feature in activeFeatures:}
+#### {feature.name}
+
+- Progress: {progressBar(feature.progress)} {feature.progress}%
+- Quarter: {feature.quarter || 'Unassigned'}
+- PRD: {feature.prdId || 'None'}
+- Dependencies: {feature.dependencies?.join(', ') || 'None'}
+{END FOR}
+
+---
+
+## Pipeline
+
+```
+PRDs          Features       Active         Shipped
+┌─────────┐   ┌─────────┐   ┌─────────┐   ┌─────────┐
+│ Draft   │──▶│ Planned │──▶│ Active  │──▶│ Shipped │
+│  ({draft})  │   │  ({planned}) │   │  ({active})  │   │  ({shipped}) │
+└─────────┘   └─────────┘   └─────────┘   └─────────┘
+     │
+     ▼
+┌─────────┐
+│Approved │
+│  ({approved}) │
+└─────────┘
+```
+
+---
+
+## Metrics Trends (Last 4 Weeks)
+
+### Velocity
+```
+W-3: {velocityW3Bar} {velocityW3}
+W-2: {velocityW2Bar} {velocityW2}
+W-1: {velocityW1Bar} {velocityW1}
+W-0: {velocityW0Bar} {velocityW0}
+```
+
+### Estimation Accuracy
+```
+W-3: {accuracyW3Bar} {accuracyW3}%
+W-2: {accuracyW2Bar} {accuracyW2}%
+W-1: {accuracyW1Bar} {accuracyW1}%
+W-0: {accuracyW0Bar} {accuracyW0}%
+```
+
+---
+
+## Alerts & Actions
+
+### Warnings
+{FOR EACH alert in alerts:}
+- {alert.icon} {alert.message}
+{END FOR}
+
+### Suggested Actions
+{FOR EACH action in suggestedActions:}
+1. {action.description}
+   - Command: `{action.command}`
+{END FOR}
+
+---
+
+## Recent Activity
+
+| Date | Action | Details |
+|------|--------|---------|
+{FOR EACH event in recentEvents.slice(0, 10):}
+| {event.date} | {event.action} | {event.details} |
+{END FOR}
+
+---
+
+## Learnings Summary
+
+### Top Patterns
+{FOR EACH pattern in topPatterns.slice(0, 5):}
+- {pattern.insight} ({pattern.frequency}x)
+{END FOR}
+
+### Improvement Areas
+{FOR EACH area in improvementAreas:}
+- **{area.name}**: {area.suggestion}
+{END FOR}
+
+---
+
+*Generated by prjct-cli | https://prjct.app*
+```
+
+---
+
+## Health Score Calculation
+
+```javascript
+const healthScore = Math.round(
+  (roadmapProgress * 0.25) +
+  (estimationAccuracy * 0.25) +
+  (successRate * 0.25) +
+  (normalizedVelocity * 0.25)
+)
+```
+
+| Score Range | Health Level | Color |
+|-------------|--------------|-------|
+| 80-100 | Excellent | Green |
+| 60-79 | Good | Blue |
+| 40-59 | Needs Attention | Yellow |
+| 0-39 | Critical | Red |
+
+---
+
+## Alert Definitions
+
+| Condition | Alert | Severity |
+|-----------|-------|----------|
+| `capacityUtilization > 90` | Quarter capacity nearly full | Warning |
+| `estimationAccuracy < 60` | Estimation accuracy below target | Warning |
+| `activeFeatures.length > 3` | Too many features in progress | Info |
+| `draftPRDs.length > 3` | PRDs awaiting review | Info |
+| `successRate < 70` | Success rate declining | Warning |
+| `velocityTrend < -20` | Velocity dropping | Warning |
+| `currentTask && elapsed > 4h` | Task running long | Info |
+
+---
+
+## Suggested Actions Matrix
+
+| Condition | Suggested Action | Command |
+|-----------|------------------|---------|
+| No active task | Start a task | `p. task` |
+| PRDs in draft | Review PRDs | `p. prd list` |
+| Features pending review | Record impact | `p. impact` |
+| Quarter ending soon | Plan next quarter | `p. plan quarter` |
+| Low estimation accuracy | Analyze estimates | `p. dashboard estimates` |
+
+---
+
+## Integration with Linear/Jira/Monday
+
+The dashboard context maps to PM tool dashboards:
+
+| Dashboard Section | Linear | Jira | Monday |
+|-------------------|--------|------|--------|
+| Health Score | Project Health | Dashboard Gadget | Board Overview |
+| Active Quarter | Cycle | Sprint | Timeline |
+| Pipeline | Workflow Board | Kanban | Board |
+| Velocity | Velocity Chart | Velocity Report | Chart Widget |
+| Alerts | Notifications | Issues | Notifications |
+
+---
+
+## Refresh Frequency
+
+| Data Type | Refresh Trigger |
+|-----------|-----------------|
+| Current Task | Real-time (on state change) |
+| Features | On feature status change |
+| Metrics | On `p. dashboard` execution |
+| Aggregates | On `p. impact` completion |
+| Alerts | Calculated on view |