@kolbo/kolbo-code-linux-arm64-musl 0.0.0-dev-202604161628

package/skills/sound-design/SKILL.md

@@ -0,0 +1,154 @@
+---
+name: sound-design
+description: >
+  Audio production rules for video: dialogue levels, music ducking, SFX placement and timing,
+  BPM selection by content type, platform loudness targets (LUFS), voice EQ and compression,
+  audio ducking levels. Use when mixing audio for video, choosing background music, or placing
+  sound effects.
+  Keywords: audio, sound design, ducking, LUFS, loudness, music, sfx, sound effects, mixing,
+  dialogue, voice, EQ, compression, BPM, volume, audio levels
+---
+
+# Sound Design for Video Production
+
+## Quick Reference
+
+```
+DIALOGUE:       -12 dB peak  |  -16 to -14 LUFS integrated
+MUSIC BED:      -30 to -20 dB (18-20 dB below dialogue)
+SFX:            -18 to -12 dB (6 dB below dialogue minimum)
+WHOOSH TIMING:  Start 10-20ms before visual, duration 400-500ms
+MUSIC BPM:      Calm 60-80 | Standard 90-110 | Upbeat 120-140
+TRUE PEAK:      Never exceed -1.5 dBTP
+VOICE EQ:       HPF 80Hz, cut 500Hz, boost 2-5kHz, cut 6-8kHz
+VOICE COMP:     3:1 ratio, 1-5ms attack, 10-20ms release
+TARGET LUFS:    -14 LUFS (YouTube/TikTok/IG) | -16 LUFS (podcasts)
+```
+
+## Audio Ducking Levels
+
+| Element | Peak Level | Notes |
+|---------|-----------|-------|
+| Dialogue / Narration | -6 dB to -12 dB | Primary element |
+| Background music (during speech) | -18 dB to -20 dB | 18-20 dB below dialogue |
+| Sound effects | -12 dB to -18 dB | Between dialogue and music |
+| Final mix | -10 dB to -20 dB | Never exceed 0 dB |
+
+**Ducking rules:**
+- W3C accessibility: music must be **20 dB lower** than foreground speech
+- BBC guideline: lower music by an additional **4 dB** from where you think it sounds right
+- Duck music **6-12 dB** when narration is active
+- EQ trick: cut **2-4 kHz** on background music to clear the speech intelligibility band
+- When testing, adjust in **1 dB increments** from a -20 dB baseline upward
+
+## Music Selection by Content Type
+
+| Content Type | BPM Range | Mood |
+|-------------|-----------|------|
+| Calm explainer / tutorial | 60-80 | Contemplative, focused |
+| Corporate / testimonial | 60-100 | Professional, calm |
+| Standard explainer | 90-110 | Steady, engaging |
+| Upbeat promo | 110-130 | Enthusiastic |
+| High-energy / demo | 120-140 | Exciting, dynamic |
+| Action / fast-paced | 140-200 | Adrenaline |
+
+**Genre recommendations for explainers:**
+- Lo-fi (steady, non-distracting, modern feel)
+- Ambient (atmospheric, stays in background)
+- Light acoustic guitar instrumentals (warm, approachable)
+- Inspiring soundtrack / cinematic light (builds emotion without overwhelming)
+
+**Key rules:**
+- Always use **instrumental** tracks when voiceover is present
+- Choose dynamically **even** tracks — avoid dramatic crescendos or beat drops
+- Match energy to the content: upbeat for "exciting new concept," gentle for serious topics
+
+## Sound Effects (SFX) Placement
+
+| SFX Type | Use Case | Duration | Level |
+|----------|----------|----------|-------|
+| Whoosh / Swish | Scene transitions | 400-500ms | -18 to -12 dB |
+| Pop / Pluck | Text appearing, bullet points | <200ms | -15 to -12 dB |
+| Click / Tap | UI interactions | <100ms | -20 to -15 dB |
+| Riser / Swell | Building to a reveal | 1-3s | -18 to -12 dB |
+| Impact / Hit | Key reveal, stat | <300ms | -12 to -6 dB |
+| Subtle whoosh | Element sliding in/out | 200-400ms | -20 to -15 dB |
+
+### Timing Rules
+- Start whoosh **10-20ms before** the visual transition (brain processes audio faster)
+- Peak of whoosh energy = **moment of greatest visual change**
+- Fine-tune in **1-frame increments** for sync
+- When stacking whooshes, keep them in different frequency bands
+
+## Platform Loudness Targets
+
+| Platform | Integrated LUFS | True Peak |
+|----------|----------------|-----------|
+| YouTube | -14 LUFS | -1 dBTP |
+| TikTok | -14 LUFS | -1 dBTP |
+| Instagram Reels | -14 LUFS | -1 dBTP |
+| Spotify (podcast) | -14 LUFS | -1 dBTP |
+| Apple Podcasts | -16 LUFS | -1 dBTP |
+| Broadcast TV | -24 LUFS | -2 dBTP |
+
+## Voice Processing Chain
+
+Apply in this order:
+1. **High-pass filter** at 80 Hz (removes rumble)
+2. **Cut 500 Hz** by 2-3 dB (removes muddiness)
+3. **Boost 2-5 kHz** by 2-3 dB (presence and clarity)
+4. **Cut 6-8 kHz** by 1-2 dB (reduces sibilance)
+5. **Compress** at 3:1 ratio, 1-5ms attack, 10-20ms release
+6. **Normalize** to target LUFS
+
+## FFmpeg Audio Commands
+
+### Loudness Normalization
+```bash
+ffmpeg -i input.mp4 -af loudnorm=I=-14:LRA=11:TP=-1 -c:v copy output.mp4
+```
+
+### Audio Ducking with Sidechain
+```bash
+ffmpeg -i narration.wav -i music.wav -filter_complex \
+  "[1:a]asplit=2[music1][music2]; \
+   [0:a][music2]sidechaincompress=threshold=0.02:ratio=9:attack=200:release=500[ducked]; \
+   [music1][ducked]amix=inputs=2:weights='1 0.15'" \
+  -c:a aac output.m4a
+```
+
+### Measure Loudness
+```bash
+ffmpeg -i input.mp4 -af loudnorm=print_format=json -f null - 2>&1 | grep -A 20 "Parsed_loudnorm"
+```
+
+---
+
+## Kolbo MCP Integration
+
+| Task | Kolbo MCP Tool | Notes |
+|------|---------------|-------|
+| Generate narration | `generate_speech` | See `list_voices` for voice options |
+| Generate music | `generate_music` | Use BPM tables above, always instrumental=true |
+| Generate SFX | `generate_sound` | Describe physically: "door slam in stone hallway" |
+| Transcribe audio | `transcribe_audio` | Word-level timestamps for sync |
+| Voice discovery | `list_voices` | Filter by language, gender, provider |
+
+**Full audio production workflow:**
+1. `generate_speech` → narration track
+2. `generate_music` instrumental=true → background music
+3. `generate_sound` → individual SFX (whooshes, impacts)
+4. Mix with FFmpeg using the ducking commands above
+5. Normalize to -14 LUFS for social platforms
+
+---
+
+## Local / Free Options
+
+> **IMPORTANT:** Always use Kolbo MCP tools by default. Only mention these if the user explicitly asks for free/offline options. Always confirm before installing anything.
+
+**TTS:** `edge-tts` (free Microsoft voices, no GPU, `pip install edge-tts`) or `piper-tts` (fully offline, CPU-only). Both are safe, lightweight installs.
+
+**SFX libraries (no install needed):** Freesound.org, Pixabay Sound Effects, BBC Sound Effects — all free, browser-based.
+
+**FFmpeg** is the only tool you should use without asking — it's standard and safe. All the mixing/ducking/normalization commands in this skill use FFmpeg.

package/skills/storytelling/SKILL.md

@@ -0,0 +1,139 @@
+---
+name: storytelling
+description: >
+  Narrative structure and storytelling for video content. Explainer arc templates, hook types,
+  the 30-second retention rule, pacing by duration, the "but-therefore" method, concept
+  introduction patterns. Use when scripting explainer videos, educational content, or any
+  narrative-driven video.
+  Keywords: storytelling, narrative, script, explainer, hook, arc, structure, pacing, retention,
+  educational, concept, story, writing, script structure
+---
+
+# Storytelling & Narrative Structure for Video
+
+## The Explainer Arc Template (3 minutes)
+
+Scale proportionally for other lengths.
+
+```
+[0:00 - 0:08]  HOOK
+               Pattern interrupt or counterintuitive claim. 1-2 sentences max.
+               Visual: striking image or animation that creates curiosity.
+
+[0:08 - 0:30]  TENSION / INFORMATION GAP
+               "Here's what most people think... but that's not quite right."
+               Establish stakes: why should I care?
+
+[0:30 - 0:50]  CONCEPT 1 (Foundation)
+               Simplest building block needed. ONE idea, ONE visual.
+               End with a "but" or "therefore" transition.
+
+[0:50 - 1:15]  CONCEPT 2 (Complication)
+               Build on Concept 1. Introduce the wrinkle.
+               Visual: transform/evolve the previous visual.
+
+[1:15 - 1:20]  PALETTE CLEANSER
+               Brief pause, visual gag, or "let that sink in" moment.
+               Gives working memory a beat to consolidate.
+
+[1:20 - 1:50]  CONCEPT 3 (Key Insight)
+               The "aha" moment. Core of the video.
+               1-3 seconds of deliberate silence after the reveal.
+               Visual: the most polished animation in the video.
+
+[1:50 - 2:20]  PROOF / EXAMPLE
+               Concrete demonstration: "Watch what happens when..."
+               Show the insight working in a specific case.
+
+[2:20 - 2:45]  IMPLICATIONS / "SO WHAT?"
+               Connect back to the real world. "This means that..."
+               Scale from specific back to general.
+
+[2:45 - 3:00]  REFRAME + CLOSE
+               Callback to the hook. Restate core insight in one sentence.
+               Optional: open a new curiosity gap.
+```
+
+## Scaling by Duration
+
+| Length | Concepts | Hook | Tension | Core | Proof | Close |
+|--------|----------|------|---------|------|-------|-------|
+| 1 min | 1-2 | 5s | 10s | 30s | 10s | 5s |
+| 2 min | 2-3 | 8s | 15s | 60s | 25s | 12s |
+| 3 min | 3-5 | 8s | 22s | 100s | 30s | 15s |
+| 5 min | 5-8 | 10s | 30s | 180s | 50s | 20s |
+
+## Hook Types
+
+| Type | Pattern | Best For |
+|------|---------|----------|
+| **Contrarian** | "Everything you've been told about X is wrong." | Science/myth-busting |
+| **Outcome** | "By the end of this video, you'll understand X." | Math/concept explainers |
+| **Mystery** | "In 1987, something impossible happened..." | Story-driven content |
+| **Stakes** | "This one mistake costs people X every year." | Practical/how-to |
+
+## The 30-Second Rule
+
+50% of viewer drop-off happens in the first 30 seconds. The hook + tension setup MUST be complete by second 30. Retention curves that survive the 30-second cliff typically retain 40-60% through the full video.
+
+## The "But-Therefore" Method
+
+Never connect sections with "and then." Always use **"but"** or **"therefore."**
+
+**Bad:** "Atoms have electrons, AND THEN those electrons have energy levels, AND THEN..."
+
+**Good:** "Atoms have electrons. BUT those electrons can only exist at specific energy levels. THEREFORE, when they jump between levels, they release light at exact frequencies."
+
+Each "but" creates tension. Each "therefore" resolves it. This is the engine of narrative momentum.
+
+## Concept Introduction Pattern
+
+For each new concept in the video:
+
+1. **Name it** — give the concept a label the viewer can hold onto
+2. **Show it** — visual representation (never just explain with words)
+3. **Contrast it** — "unlike X, this works by..."
+4. **Apply it** — concrete example in the real world
+5. **Connect it** — link to the previous concept with "but" or "therefore"
+
+## Pacing by Content Energy
+
+| Energy Level | Pacing | Visual Change Rate |
+|-------------|--------|-------------------|
+| High (promo, action) | Fast cuts, 1-2s per shot | Every 1-2 seconds |
+| Medium (tutorial, explainer) | Balanced, 3-5s per shot | Every 3-4 seconds |
+| Low (meditation, documentary) | Let scenes breathe, 5-10s | Every 5-8 seconds |
+
+## Common Mistakes
+
+- **Info dump at the start** — frontload curiosity, not information
+- **No stakes** — "here's a cool fact" vs "this changes how you should think about X"
+- **Too many concepts** — one concept per minute is the maximum for retention
+- **Missing the "aha"** — every video needs ONE clear revelation moment
+- **Symmetric structure** — the most important concept should be at 60-70% through the video, not in the middle
+- **No callback** — the close should reference the hook, creating a satisfying loop
+
+---
+
+## Kolbo MCP Integration
+
+Use storytelling structure to guide Kolbo generation workflows:
+
+**Scripted Explainer Workflow:**
+1. Write script using the arc template above
+2. `generate_speech` → narrate each section
+3. `generate_image` or `generate_video` per scene (with visual direction from script)
+4. `generate_music` → background track matching the energy arc
+5. Compose in Remotion or FFmpeg following the timing structure
+6. `transcribe_audio` → generate captions for accessibility
+
+**AI-Assisted Scripting:**
+Use `chat_send_message` with a video-capable model to brainstorm scripts. Feed the arc template as context and ask the AI to fill in each section for your topic.
+
+**Creative Director for Visual Storyboarding:**
+`generate_creative_director` with 4-8 scenes mapped to the arc sections:
+- Scene 1: Hook visual
+- Scene 2-3: Concept visuals
+- Scene 4: Key insight / "aha" visual
+- Scene 5-6: Proof / example
+- Scene 7-8: Close / callback

package/skills/subagent-driven-development/SKILL.md

@@ -0,0 +1,277 @@
+---
+name: subagent-driven-development
+description: Use when executing implementation plans with independent tasks in the current session
+---
+
+# Subagent-Driven Development
+
+Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
+
+**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
+
+**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
+
+## When to Use
+
+```dot
+digraph when_to_use {
+    "Have implementation plan?" [shape=diamond];
+    "Tasks mostly independent?" [shape=diamond];
+    "Stay in this session?" [shape=diamond];
+    "subagent-driven-development" [shape=box];
+    "executing-plans" [shape=box];
+    "Manual execution or brainstorm first" [shape=box];
+
+    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
+    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
+    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
+    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
+    "Stay in this session?" -> "subagent-driven-development" [label="yes"];
+    "Stay in this session?" -> "executing-plans" [label="no - parallel session"];
+}
+```
+
+**vs. Executing Plans (parallel session):**
+- Same session (no context switch)
+- Fresh subagent per task (no context pollution)
+- Two-stage review after each task: spec compliance first, then code quality
+- Faster iteration (no human-in-loop between tasks)
+
+## The Process
+
+```dot
+digraph process {
+    rankdir=TB;
+
+    subgraph cluster_per_task {
+        label="Per Task";
+        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
+        "Implementer subagent asks questions?" [shape=diamond];
+        "Answer questions, provide context" [shape=box];
+        "Implementer subagent implements, tests, commits, self-reviews" [shape=box];
+        "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [shape=box];
+        "Spec reviewer subagent confirms code matches spec?" [shape=diamond];
+        "Implementer subagent fixes spec gaps" [shape=box];
+        "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [shape=box];
+        "Code quality reviewer subagent approves?" [shape=diamond];
+        "Implementer subagent fixes quality issues" [shape=box];
+        "Mark task complete in TodoWrite" [shape=box];
+    }
+
+    "Read plan, extract all tasks with full text, note context, create TodoWrite" [shape=box];
+    "More tasks remain?" [shape=diamond];
+    "Dispatch final code reviewer subagent for entire implementation" [shape=box];
+    "Use superpowers:finishing-a-development-branch" [shape=box style=filled fillcolor=lightgreen];
+
+    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer subagent (./implementer-prompt.md)";
+    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?";
+    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
+    "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)";
+    "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"];
+    "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)";
+    "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?";
+    "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"];
+    "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [label="re-review"];
+    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="yes"];
+    "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?";
+    "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"];
+    "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="re-review"];
+    "Code quality reviewer subagent approves?" -> "Mark task complete in TodoWrite" [label="yes"];
+    "Mark task complete in TodoWrite" -> "More tasks remain?";
+    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
+    "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"];
+    "Dispatch final code reviewer subagent for entire implementation" -> "Use superpowers:finishing-a-development-branch";
+}
+```
+
+## Model Selection
+
+Use the least powerful model that can handle each role to conserve cost and increase speed.
+
+**Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.
+
+**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
+
+**Architecture, design, and review tasks**: use the most capable available model.
+
+**Task complexity signals:**
+- Touches 1-2 files with a complete spec → cheap model
+- Touches multiple files with integration concerns → standard model
+- Requires design judgment or broad codebase understanding → most capable model
+
+## Handling Implementer Status
+
+Implementer subagents report one of four statuses. Handle each appropriately:
+
+**DONE:** Proceed to spec compliance review.
+
+**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.
+
+**NEEDS_CONTEXT:** The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.
+
+**BLOCKED:** The implementer cannot complete the task. Assess the blocker:
+1. If it's a context problem, provide more context and re-dispatch with the same model
+2. If the task requires more reasoning, re-dispatch with a more capable model
+3. If the task is too large, break it into smaller pieces
+4. If the plan itself is wrong, escalate to the human
+
+**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
+
+## Prompt Templates
+
+- `./implementer-prompt.md` - Dispatch implementer subagent
+- `./spec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent
+- `./code-quality-reviewer-prompt.md` - Dispatch code quality reviewer subagent
+
+## Example Workflow
+
+```
+You: I'm using Subagent-Driven Development to execute this plan.
+
+[Read plan file once: docs/superpowers/plans/feature-plan.md]
+[Extract all 5 tasks with full text and context]
+[Create TodoWrite with all tasks]
+
+Task 1: Hook installation script
+
+[Get Task 1 text and context (already extracted)]
+[Dispatch implementation subagent with full task text + context]
+
+Implementer: "Before I begin - should the hook be installed at user or system level?"
+
+You: "User level (~/.config/superpowers/hooks/)"
+
+Implementer: "Got it. Implementing now..."
+[Later] Implementer:
+  - Implemented install-hook command
+  - Added tests, 5/5 passing
+  - Self-review: Found I missed --force flag, added it
+  - Committed
+
+[Dispatch spec compliance reviewer]
+Spec reviewer: ✅ Spec compliant - all requirements met, nothing extra
+
+[Get git SHAs, dispatch code quality reviewer]
+Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.
+
+[Mark Task 1 complete]
+
+Task 2: Recovery modes
+
+[Get Task 2 text and context (already extracted)]
+[Dispatch implementation subagent with full task text + context]
+
+Implementer: [No questions, proceeds]
+Implementer:
+  - Added verify/repair modes
+  - 8/8 tests passing
+  - Self-review: All good
+  - Committed
+
+[Dispatch spec compliance reviewer]
+Spec reviewer: ❌ Issues:
+  - Missing: Progress reporting (spec says "report every 100 items")
+  - Extra: Added --json flag (not requested)
+
+[Implementer fixes issues]
+Implementer: Removed --json flag, added progress reporting
+
+[Spec reviewer reviews again]
+Spec reviewer: ✅ Spec compliant now
+
+[Dispatch code quality reviewer]
+Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)
+
+[Implementer fixes]
+Implementer: Extracted PROGRESS_INTERVAL constant
+
+[Code reviewer reviews again]
+Code reviewer: ✅ Approved
+
+[Mark Task 2 complete]
+
+...
+
+[After all tasks]
+[Dispatch final code-reviewer]
+Final reviewer: All requirements met, ready to merge
+
+Done!
+```
+
+## Advantages
+
+**vs. Manual execution:**
+- Subagents follow TDD naturally
+- Fresh context per task (no confusion)
+- Parallel-safe (subagents don't interfere)
+- Subagent can ask questions (before AND during work)
+
+**vs. Executing Plans:**
+- Same session (no handoff)
+- Continuous progress (no waiting)
+- Review checkpoints automatic
+
+**Efficiency gains:**
+- No file reading overhead (controller provides full text)
+- Controller curates exactly what context is needed
+- Subagent gets complete information upfront
+- Questions surfaced before work begins (not after)
+
+**Quality gates:**
+- Self-review catches issues before handoff
+- Two-stage review: spec compliance, then code quality
+- Review loops ensure fixes actually work
+- Spec compliance prevents over/under-building
+- Code quality ensures implementation is well-built
+
+**Cost:**
+- More subagent invocations (implementer + 2 reviewers per task)
+- Controller does more prep work (extracting all tasks upfront)
+- Review loops add iterations
+- But catches issues early (cheaper than debugging later)
+
+## Red Flags
+
+**Never:**
+- Start implementation on main/master branch without explicit user consent
+- Skip reviews (spec compliance OR code quality)
+- Proceed with unfixed issues
+- Dispatch multiple implementation subagents in parallel (conflicts)
+- Make subagent read plan file (provide full text instead)
+- Skip scene-setting context (subagent needs to understand where task fits)
+- Ignore subagent questions (answer before letting them proceed)
+- Accept "close enough" on spec compliance (spec reviewer found issues = not done)
+- Skip review loops (reviewer found issues = implementer fixes = review again)
+- Let implementer self-review replace actual review (both are needed)
+- **Start code quality review before spec compliance is ✅** (wrong order)
+- Move to next task while either review has open issues
+
+**If subagent asks questions:**
+- Answer clearly and completely
+- Provide additional context if needed
+- Don't rush them into implementation
+
+**If reviewer finds issues:**
+- Implementer (same subagent) fixes them
+- Reviewer reviews again
+- Repeat until approved
+- Don't skip the re-review
+
+**If subagent fails task:**
+- Dispatch fix subagent with specific instructions
+- Don't try to fix manually (context pollution)
+
+## Integration
+
+**Required workflow skills:**
+- **superpowers:using-git-worktrees** - REQUIRED: Set up isolated workspace before starting
+- **superpowers:writing-plans** - Creates the plan this skill executes
+- **superpowers:requesting-code-review** - Code review template for reviewer subagents
+- **superpowers:finishing-a-development-branch** - Complete development after all tasks
+
+**Subagents should use:**
+- **superpowers:test-driven-development** - Subagents follow TDD for each task
+
+**Alternative workflow:**
+- **superpowers:executing-plans** - Use for parallel session instead of same-session execution

package/skills/subagent-driven-development/code-quality-reviewer-prompt.md

@@ -0,0 +1,26 @@
+# Code Quality Reviewer Prompt Template
+
+Use this template when dispatching a code quality reviewer subagent.
+
+**Purpose:** Verify implementation is well-built (clean, tested, maintainable)
+
+**Only dispatch after spec compliance review passes.**
+
+```
+Task tool (superpowers:code-reviewer):
+  Use template at requesting-code-review/code-reviewer.md
+
+  WHAT_WAS_IMPLEMENTED: [from implementer's report]
+  PLAN_OR_REQUIREMENTS: Task N from [plan-file]
+  BASE_SHA: [commit before task]
+  HEAD_SHA: [current commit]
+  DESCRIPTION: [task summary]
+```
+
+**In addition to standard code quality concerns, the reviewer should check:**
+- Does each file have one clear responsibility with a well-defined interface?
+- Are units decomposed so they can be understood and tested independently?
+- Is the implementation following the file structure from the plan?
+- Did this implementation create new files that are already large, or significantly grow existing files? (Don't flag pre-existing file sizes — focus on what this change contributed.)
+
+**Code reviewer returns:** Strengths, Issues (Critical/Important/Minor), Assessment