Skip to content
Agentmart
Submit a tool

design-tree-interview

Relentless design-tree interview.

Skill by sardul3

IndexedMIT
Write a review

Chalk Labs

Need help deploying design-tree-interview?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sardul3-design-tree-interview

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Relentless design-tree interview. Use when stress-testing a plan, grilling a design, or filling a deep-ask contract. Explores the repo for facts; asks the user only for decisions.

Use cases: documents, design, testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/design-tree-interview

What's inside

Skill name
design-tree-interview
Description
Relentless design-tree interview. Use when stress-testing a plan, grilling a design, or filling a deep-ask contract. Explores the repo for facts; asks the user only for decisions.
License
MIT
Instructions
44 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Design-tree interview

Interview until shared understanding. Treat the work as a **design tree**: each decision unlocks the decisions that depend on it.

## Rounds

The **frontier** is every question whose prerequisites are already settled. Ask the **whole frontier** in one round. Number each item. Give **your recommended answer** every time. Then wait.

```
❓ **Q1** - **<title>**: <body, choices if useful>

➡️ <recommended answer>

---

❓ **Q2** - **<title>**: ...

➡️ <recommended answer>
```

After answers, recompute the frontier. A question that still depends on an open Q in this round belongs in a **later** round.

## Facts vs decisions

- **Facts** (filesystem, git, tests, types, existing APIs): look them up. Do not ask the user.
- **Decisions** (product, trade-offs, taste): ask the user. Wait.

### Prompt-enrich session (injected; no repo explore)

You cannot Glob, Grep, Explore, or spawn agents. For facts, **Read only** these files if they exist in cwd: `README.md`, `package.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`, `composer.json`. Infer stack from those. Do not ask the user whether the app is Python vs Node if `package.json` or `pyproject.toml` already says.

`AskUserQuestion` allows **at most 4 options** per question. If you need more choices, ask in numbered markdown instead.

When the frontier is empty, follow `session-handoff` (pipe to `save_handoff.py`, never Write to `/tmp`) and run `~/.claude/hooks/prompt-enrich/launch-clean-claude.sh --file <handoff-path>`. Stop after launch.

Otherwise (not an enrich session): dispatch a subagent if the search is large. A running lookup is an unsettled prerequisite only for questions that depend on it; ask the rest of the frontier now.

## Stop

The frontier is empty: every branch visited, nothing silently assumed. Do **not** implement until the user confirms shared understanding.

If this interview is feeding the prompt-enrich pipeline, also fill the nine contract slots (role, audience, goal, context, constraints, format, length/tone, success criteria, model profile) from the tree; infer slots you already know. Then follow `session-handoff`. Stop after launch.

From sardul3/dev-conductor, MIT.

More from sardul3/dev-conductor

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 30, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from sardul3

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get design-tree-interview running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying design-tree-interview?

CallGet help
Cite this page

design-tree-interview skill. Agent Mart. https://agentmart.dev/skills/sardul3-design-tree-interview (last updated 2026-10-24)