discuss

Discuss and explore ideas before committing to an approach

Best use case

discuss is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Discuss and explore ideas before committing to an approach

Teams using discuss should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/discuss/SKILL.md --create-dirs "https://raw.githubusercontent.com/stevengonsalvez/agents-in-a-box/main/toolkit/packages/skills/discuss/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/discuss/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How discuss Compares

Feature / AgentdiscussStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Discuss and explore ideas before committing to an approach

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Discuss Phase

Capture implementation decisions BEFORE planning. Produces a CONTEXT.md
with locked decisions that /plan must honor.

## When to Use

- Before `/plan` when the phase has ambiguities
- When starting a new phase in `.planning/ROADMAP.md`
- When the team needs to agree on approach before implementation

## Process

### Step 1: Load Phase Context

1. Read `.planning/ROADMAP.md` to identify the target phase
2. Read `.planning/STATE.md` for current position
3. If a phase number is provided as argument, use that
4. If no argument, use current phase from STATE.md

### Step 2: Identify Gray Areas

Based on what the phase is building, identify 3-4 ambiguities:

| Domain | Typical Gray Areas |
|--------|-------------------|
| UI/Frontend | Layout approach, interaction patterns, responsive behavior, state management |
| API/Backend | Response formats, error handling, auth strategy, data validation |
| Data/Storage | Schema design, migration approach, indexing strategy |
| Infrastructure | Deployment target, scaling approach, monitoring |

Present them:
```
Phase [N]: [Name]

I've identified these areas that need decisions before planning:

1. **[Area 1]**: [Why this is ambiguous]
2. **[Area 2]**: [Why this is ambiguous]
3. **[Area 3]**: [Why this is ambiguous]

Which areas would you like to discuss? (or "all")
```

### Step 3: Deep-Dive Questions

For each selected area, ask 3-4 probing questions using AskUserQuestion:
- Concrete choices (not abstract preferences)
- Trade-off acknowledgment
- Edge case handling
- Prior art / references

### Step 4: Generate CONTEXT.md

Write to `.planning/phases/{phase}/CONTEXT.md`:

```markdown
# Phase [N] Context: [Phase Name]

## Scope (from Roadmap)
[Copy from ROADMAP.md]

## Implementation Decisions

### [Area 1]
- **Decision**: [Concrete choice]
- **Rationale**: [Why this choice]
- **Trade-off**: [What we're giving up]

### [Area 2]
...

## Deferred Ideas
- [Idea mentioned but deferred to later phase]

---
*Locked on [date]. /plan must honor these decisions.*
```

### Step 5: Update State

Update `.planning/STATE.md` to record that discussion is complete for this phase.

## Without .planning/

If no `.planning/` directory exists, /discuss still works:
- Ask what area/feature the user wants to discuss
- Run the same gray-area analysis and questioning
- Output to `plans/discuss_[topic]_[date].md` instead

Related Skills

workflow

8
from stevengonsalvez/agents-in-a-box

Guide through structured delivery workflow with plan, implement, validate phases

webapp-testing

8
from stevengonsalvez/agents-in-a-box

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

validate

8
from stevengonsalvez/agents-in-a-box

Verify implementation against specifications

ui-ux-pro-max

8
from stevengonsalvez/agents-in-a-box

UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, Astro, Nuxt, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

tui-style-guide

8
from stevengonsalvez/agents-in-a-box

TUI style guide for consistent terminal interface design

token-usage

8
from stevengonsalvez/agents-in-a-box

Show Claude Code token usage across sessions — daily, weekly, per-project, and per-session breakdowns. Parses {{HOME_TOOL_DIR}}/projects/**/*.jsonl for consumption data. Use when the user asks about token usage, costs, how many tokens were used, session statistics, or wants a usage report.

tmux-status

8
from stevengonsalvez/agents-in-a-box

Show status of all tmux sessions including dev environments, spawned agents, and running processes

tmux-monitor

8
from stevengonsalvez/agents-in-a-box

Monitor and report status of all tmux sessions including dev environments, spawned agents, and running processes. Uses tmuxwatch for enhanced visibility.

tmux-message

8
from stevengonsalvez/agents-in-a-box

Reliable peer-to-peer message delivery to other Claude Code instances via tmux send-keys. Use as a fallback when claude-peers MCP send_message fails to surface in the receiver's inbox (delivered server-side but receiver never picks it up — observed behaviour). Also use when sending a directive to a known Claude Code TUI session by tmux session name or fuzzy hint, or when injecting a multi-line directive into a peer's prompt and submitting it. Trigger phrases — "claude-peers fallback", "tmux send-keys", "send to peer via tmux", "inject directive", "deliver to nanoclaw/hermes peer", "peer message". Tmux-only — won't reach peers running outside tmux.

test-driven-development

8
from stevengonsalvez/agents-in-a-box

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.

test-ainb

8
from stevengonsalvez/agents-in-a-box

Run tests for the ainb (agents-in-a-box) Rust workspace via a 5-layer strategy — unit, insta snapshot, mock-plugin compositing, real-plugin spawn, vhs recording. Wraps cargo + insta + vhs into one CLI. Use when Stevie says "/test-ainb", "test ainb", "run ainb tests", "snapshot <component>", "regenerate vhs tapes", or any phrasing about validating ainb test layers. The skill autodetects which ainb-tui worktree the cwd sits in and dispatches to scripts/run.sh.

sync-learnings

8
from stevengonsalvez/agents-in-a-box

Sync user-level agent config changes back to toolkit repository (works for Claude, Codex, Copilot)