review-priorities
Conversational session to review and assign delta priorities
What this skill does
# Review Priorities
A conversational discovery session to assess and assign delta priorities holistically.
## Purpose
When you have multiple deltas and need to determine what to work on, this command helps you:
- Assess current priorities against your goals
- Identify priority inconsistencies
- Assign or reassign priorities based on current context
- Get recommendations for what to focus on
## Context
**You must load the following skills and read the following files before proceeding.**
### Skills
- `katachi:framework-core` - Workflow principles and priority tracking
### Delta inventory
- `docs/planning/DELTAS.md` - All deltas with current status and priority
## Pre-Check
Verify framework is initialized:
- If `docs/planning/` doesn't exist, suggest `/katachi:init-framework` first
- If DELTAS.md missing, explain what's needed
## Process
### 1. Load Current State
Gather the full picture:
```bash
# Get summary of all deltas
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py summary
# Get priority breakdown
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py priority list
# Get ready deltas
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py ready
```
### 2. Present Initial Analysis
Summarize the current state for the user. Always refer to deltas by their title with the ID in parentheses — never by bare ID.
```
"Here's your current delta landscape:
**Status:**
- X ready to work on
- Y in progress
- Z blocked by dependencies
**Priority Distribution:**
- Critical (1): N deltas
- High (2): N deltas
- Medium (3): N deltas [includes X at default]
- Low (4): N deltas
- Backlog (5): N deltas
**Observations:**
- [High-impact blockers: deltas that block many others, referenced by title (ID)]
- [Deltas without explicit priority: still at default 3, referenced by title (ID)]
- [Any obvious inconsistencies]
Let's discuss your current priorities."
```
### 3. Discovery Questions
Ask about the user's current context. Ask ONE question at a time and wait for the answer.
**Goal-oriented questions:**
- "What are you trying to achieve this week/sprint?"
- "Are there any external deadlines or commitments?"
- "Which part of the system needs the most attention right now?"
**Constraint-oriented questions:**
- "Is there anything blocking you from working on certain areas?"
- "Are there any deltas you want to explicitly defer?"
- "Any dependencies on external factors (other teams, APIs, etc.)?"
**Clarification questions (as needed):**
- "You mentioned [X] - does that mean [specific deltas] should be higher priority?"
- "How urgent is [specific capability]?"
### 4. Propose Priority Assignments
Based on the conversation, draft a priority proposal:
```
"Based on our discussion, I suggest:
**Critical (1):**
- User authentication (DLT-015) - blocks 5 other deltas, aligns with your deadline
**High (2):**
- API refactor (DLT-008) - needed before auth, currently blocking
- Error handling (DLT-012) - you mentioned reliability focus
**Medium (3):** (unchanged)
- Email validation (DLT-003), Session management (DLT-007)
**Low (4):**
- UI polish (DLT-001) - nice to have, no urgency
**Backlog (5):**
- Advanced analytics (DLT-002) - explicitly deferred
Does this align with your thinking? Any adjustments?"
```
### 5. Validate Priorities
Dispatch the priority-reviewer agent to check for inconsistencies:
```python
Task(
subagent_type="katachi:priority-reviewer",
prompt=f"""
Review these priority assignments for consistency.
## Proposed Priorities
{priority_assignments}
## Dependency Matrix
{dependency_info}
## User Goals
{stated_goals}
Check for:
- Priority inversions (high priority blocked by low priority)
- Bottlenecks (high-impact deltas with low priority)
- Goal alignment
"""
)
```
If the reviewer finds issues, present them to the user and iterate.
### 6. Iterate Based on Feedback
- Apply user corrections
- Re-validate if significant changes
- Repeat until user approves
### 7. Apply Priority Updates
Once confirmed, apply the changes:
```bash
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py priority set DLT-015 1
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py priority set DLT-008 2
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py priority set DLT-012 2
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py priority set DLT-001 4
python ${CLAUDE_PLUGIN_ROOT}/scripts/deltas.py priority set DLT-002 5
```
### 8. Summary
Present the final state:
```
"Priorities updated:
**Changes made:**
- User authentication (DLT-015): 3 → 1 (Critical)
- API refactor (DLT-008): 3 → 2 (High)
- Error handling (DLT-012): 3 → 2 (High)
- UI polish (DLT-001): 3 → 4 (Low)
- Advanced analytics (DLT-002): 3 → 5 (Backlog)
**Suggested next delta:**
[Run `next` command and show result]
**Next actions:**
- Start work: /katachi:spec-delta [suggested delta]
- Review later: /katachi:review-priorities
"
```
## Workflow Principles
**This is a discovery session, not a checklist:**
- One question at a time
- Let the user's answers guide the conversation
- Don't go delta-by-delta; work at a strategic level
- Agent proposes, user confirms
- Always refer to deltas by their title with the ID in parentheses (e.g., "User authentication (DLT-015)"), never by bare ID
**Focus on understanding context:**
- Goals and deadlines matter more than individual deltas
- Dependencies create implicit priorities
- Bottlenecks deserve attention
**Validate before applying:**
- Use priority-reviewer agent to catch inconsistencies
- Present issues to user, don't auto-fix
- User has final say on all assignments
## Error Handling
**No deltas exist:**
- Explain that priorities require deltas
- Suggest `/katachi:init-framework` or `/katachi:add-delta`
**User is unsure about goals:**
- That's OK - help them think through it
- Ask concrete questions: "What would success look like next week?"
- Suggest deferring explicit priority assignment until clearer
**Too many changes:**
- If adjusting 10+ priorities, confirm user wants to proceed
- Offer to focus on top-priority changes first
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.