panel

name	panel
description	Convene a panel of reviewers to analyze a draft from multiple perspectives, then synthesize their feedback into consensus findings, productive tensions, and prioritized recommendations.
user_invocable	true

Panel Review

Convene multiple reviewer agents to analyze a piece, then synthesize their perspectives into a unified analysis that surfaces consensus, tensions, and priorities.

When to Use

• Before publishing something high-stakes
• When you want multiple perspectives without running reviewers manually
• When you suspect different aspects need different kinds of attention
• When you're too close to the work to know what feedback you need

The Flow

1. Load Context

Read the draft and its .status.yaml to understand:

• piece_type — essay, argument, explainer, narrative, etc.
• audience — general, specialist, insider
• stage — early draft, revision, near-final
• goals — if stated

This informs panel selection and later synthesis.

2. Propose Panel

Based on piece context, propose 4-6 reviewers.

Selection heuristics:

Signal	Suggests Including
Personal/reflective content	sedaris, mom
Argumentative content	asshole, vonnegut
Technical or jargon-heavy	mom, hemingway
Narrative structure	vonnegut, hitchcock, sorkin
Feels slow or wandering	sorkin
Feels bloated	hemingway
High-stakes / pre-publish	asshole, hemingway
General audience	mom
Early stage	vonnegut (fundamentals)
Late stage	hemingway, asshole (polish, stress-test)

Check TASTE.md for:

• Preferred reviewers
• Reviewers to exclude
• Past patterns

Present the proposal:

## Proposed Panel

**Draft:** [title or slug]
**Context:** [piece_type] for [audience], currently at [stage]

Based on this context, I recommend:

| Reviewer | Why |
|----------|-----|
| **[name]** | [One-line rationale tied to piece context] |
| **[name]** | [Rationale] |
| **[name]** | [Rationale] |
| **[name]** | [Rationale] |

**Not including:**
- **[name]** — [Why not relevant for this piece]
- **[name]** — [Why not]

Proceed with this panel, or adjust?

Wait for user confirmation or modification.

3. Run Reviewers in Parallel

Once confirmed:

1. Spawn all selected reviewer agents in parallel using the Task tool
   • Use subagent_type matching the reviewer (e.g., "compound-writing:review:asshole-reviewer")
   • Each receives the full draft
   • Each produces their standard prose output
2. Collect all outputs

Example spawning pattern:

[Spawn in parallel:]
- Task: asshole-reviewer with draft
- Task: mom-reviewer with draft
- Task: hemingway-reviewer with draft
- Task: sorkin-reviewer with draft

4. Run Synthesizer

Spawn panel-synthesizer agent with:

• The draft
• Draft context from .status.yaml
• All reviewer outputs (full prose)

Synthesizer prompt should include:

## Draft

[full draft text]

## Context

piece_type: [from .status.yaml]
audience: [from .status.yaml]
stage: [from .status.yaml]
goals: [from .status.yaml if present]

## Reviewer Outputs

### asshole-reviewer
[full output]

### mom-reviewer
[full output]

### hemingway-reviewer
[full output]

[etc.]

5. Return Synthesis

Present the synthesizer's output to the user.

Panel Size

• Minimum: 3 reviewers (fewer than this, just run them individually)
• Recommended: 4-5 reviewers (good coverage without redundancy)
• Maximum: 7 reviewers (all of them—full stress test)

Available Reviewers

Reviewer	Subagent Type	Focus
asshole	compound-writing:review:asshole-reviewer	Logical rigor, unsupported claims
mom	compound-writing:review:mom-reviewer	Accessibility, jargon, general reader
hemingway	compound-writing:review:hemingway-reviewer	Economy, cutting, word-level
sedaris	compound-writing:review:sedaris-reviewer	Specificity, humor, voice
sorkin	compound-writing:review:sorkin-reviewer	Pacing, momentum, forward motion
vonnegut	compound-writing:review:vonnegut-reviewer	Story fundamentals, structure
hitchcock	compound-writing:review:hitchcock-reviewer	Tension, suspense, stakes

Default Panels by Piece Type

If .status.yaml has piece_type, use as starting point:

piece_type	Default Panel
essay / personal	mom, sedaris, vonnegut, sorkin
argument / opinion	asshole, vonnegut, hemingway, mom
explainer / technical	mom, hemingway, sorkin
narrative / story	vonnegut, hitchcock, sorkin, sedaris
newsletter	mom, sorkin, hemingway

Always adjust based on specific signals in the draft.

Example Session

User: /panel

Agent: I'll convene a panel to review your draft. Let me read it and check the status.

[Reads draft]
[Reads .status.yaml: piece_type: essay, audience: general, stage: revision,
 goals: "make it land emotionally without being sappy"]

## Proposed Panel

**Draft:** father-and-the-sea
**Context:** essay for general audience, revision stage

Based on the context—personal essay aiming for emotional impact without
sentimentality—I recommend:

| Reviewer | Why |
|----------|-----|
| **mom** | General audience check. Will flag where you lose non-insiders. |
| **sedaris** | Personal material that might benefit from more specificity or humor. |
| **sorkin** | Revision stage—check if pacing is tight. |
| **asshole** | The emotional claims need to be earned, not asserted. |

**Not including:**
- **hemingway** — The prose reads clean; economy isn't the issue here
- **hitchcock** — Not a tension-driven piece
- **vonnegut** — Structure is solid; this needs polish not fundamentals

Proceed with this panel, or adjust?

User: Add hemingway actually, I think it might be overwritten

Agent: Adding hemingway. Running the panel now.

[Spawns 5 reviewer agents in parallel]
[Collects outputs]
[Spawns panel-synthesizer with draft + context + all outputs]

## Panel Synthesis

**Panel:** asshole, hemingway, mom, sedaris, sorkin
**Piece context:** essay for general audience, revision stage, goal: emotional
impact without sappiness

---

### Consensus Findings

| Issue | Flagged By | Recommendation |
|-------|------------|----------------|
| Opening two paragraphs are slow | sorkin, hemingway, asshole | Cut or restructure—start closer to the boat |
| "He taught me everything" is unearned | asshole, sedaris | Show what he taught, don't declare it |
| Section 3 gets abstract | mom, sorkin | Ground it in a specific moment |

---

### Productive Tensions

**Tension: The fishing gear paragraph**

> "His tackle box was a museum of failures—rusted lures from the '70s, a reel
> that hadn't worked since Reagan, hooks that had never caught anything but
> his own thumb."

| Cut it | Keep it |
|--------|---------|
| **hemingway:** 47 words that could be 15. "His tackle box held decades of failure" does the job. | **sedaris:** This is the most alive moment in the piece. The specific details are doing real work. |

**What's at stake:** The piece aims for emotional impact without sappiness.
Specific, wry details (sedaris) might be the path there. But if they slow
momentum, they work against the goal.

---

### Unique Insights

- **sedaris:** "There's a joke hiding in the part about him never admitting he
  was wrong. You're circling it but won't commit."
- **asshole:** "Your ending asks the reader to feel something you haven't set
  up. The 'I finally understood' move is unearned."

---

### Recommended Priorities

1. **Restructure the opening** — Three reviewers flagged this. Start on the
   boat, not before it.
2. **Earn the ending** — The emotional payoff needs setup. Show what you
   finally understood through a scene, not a declaration.
3. **Decide on the tackle box** — Genuine tension. Your call based on what
   you're optimizing for.

---

### The Hard Question

> What specifically did you learn from him that you couldn't have learned from
> anyone else? Multiple reviewers noted you assert the relationship's importance
> without showing what made it irreplaceable.

Error Handling

If a reviewer fails to spawn:

• Note which reviewer is missing
• Proceed with available outputs
• Mention the gap in synthesis

If draft has no .status.yaml:

• Infer what you can from the draft itself
• Note that context is limited
• Make reasonable assumptions about piece type

If user provides no draft:

• Ask for the draft path or slug to load
• Or ask them to paste the draft

Future: Debate Mode

The synthesizer identifies tensions but doesn't resolve them. A future evolution:

1. Synthesizer flags tensions
2. Tensions sent back to involved reviewers: "Hemingway, sedaris said X. Respond?"
3. Reviewers can concede, hold, or propose compromise
4. Multiple rounds until resolution or acknowledged stalemate

For now, tensions surface for the writer to resolve.

Lessons

[Skill-specific lessons will be added here as they're captured]