interview

Phase 1 of building a Claude Managed Agent — interview the founder about the one job the agent should do, then produce a build sheet (CMA primitives table + v1/v2 deferrals + eval plan) WITHOUT needing their API key yet. Use when the user says "help me scope an agent", "I have an idea for an agent", "what should this agent be", or when the orchestrator routes phase=interview. Drives the six intake slots (job, trigger, inputs, actions, definition-of-done, recurrence) via AskUserQuestion, maps them to primitives with interview_planner.py, assembles build-sheet.json with build_sheet_builder.py, and validates limits with primitives_validator.py. Connectors are mockable in v0 (schema-true custom tools); real MCP servers become v1 deferrals. Distinct from stage-launch (which turns the sheet into payloads).

Quality

98%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Phase 1 — Interview → Plan

Name: interview
Rating: 77.60000000000001 (1 reviews)
Author: alirezarezvani

Open warmly with one or two examples from ../../references/examples-bank.md, then interview the founder into a build sheet. No API key needed in this phase — the output is a plan.

The six intake slots (ask one at a time; use AskUserQuestion for choices)

Slot	Question	Maps to
Job	"What one job should this agent do end-to-end?"	`agent.system` + outcome `description`
Trigger	"What kicks it off — you ask it, an event, or a schedule?"	on-demand / event / cron
Inputs	"What does it read?" (files, repo, memory, gmail/slack/github, web)	resources / MCP servers / memory
Actions	"What does it do?" (draft, write, call APIs, run code)	agent toolset / custom tools / MCP
Done	"How would you grade a good run?"	outcome `rubric` (required)
Recurrence	"Once, on request, or on a cadence?"	single-pass / grade-loop / cron-loop

See ../../references/interview-to-config.md for the full mapping.

Workflow

Interview. Walk the six slots. Capture the founder's own words — never invent specifics they didn't claim.
Map to primitives.
```
python3 scripts/interview_planner.py \
  --job "Triage overnight support email" --trigger schedule \
  --inputs "gmail,memory" --actions "label,reply" \
  --dod "one label per email, grounded reason, no invented facts" \
  --recurrence daily --out ./my-agent/plan.json
```
MCP inputs become schema-true mock custom tools in v0 and a v1 deferral to wire the real server. Irreversible actions (send/publish) become v2 deferrals behind always_ask.

Assemble the sheet.

python3 scripts/build_sheet_builder.py --plan ./my-agent/plan.json --out-dir ./my-agent

Validate limits.
```
python3 scripts/primitives_validator.py --sheet ./my-agent/build-sheet.json
```
FAIL blocks progress; fix and re-run. WARN is advisory (surface it).
Record the plan in the goal. goal_state.py set --phase stage-launch --artifact build_sheet=./my-agent/build-sheet.json, then advance.

Hard rules

v0 is the core job only. Everything else is a versioned deferral with a reason and an exact mechanism.
Their problem, their words.
No key yet. The interview produces a plan; the key is a Phase-2 concern.

Forcing-question library (recommend + cite)

"What one job — singular?" Recommend: the most-repeated task. Cite: interview-to-config.md. Two jobs → two agents.
"Real integration or v0 mock?" Recommend: mock; wire MCP as v1. Cite: interview-to-config.md rule 1.
"How do you grade it?" Recommend: 3–5 grounded rubric lines. Cite: cma-primitives.md (rubric required).
"Smarter over time?" Recommend: attach memory only if yes. Cite: cma-primitives.md (memory limits + injection).
"Once, or on a cadence?" Recommend: on-demand v0, schedule as Phase-4. Cite: loops-and-workflows.md.

Tools

scripts/interview_planner.py — answers → primitives skeleton + deferrals.
scripts/build_sheet_builder.py — assemble/normalize build-sheet.json.
scripts/primitives_validator.py — validate vs CMA limits (PASS/WARN/FAIL).

Repository: alirezarezvani/claude-skills
Path: agent-launcher/skills/interview/SKILL.md
Commit: 19392f7

Last updated: ~9 hours ago
First committed: 6 days ago

Also appears in

alirezarezvani/claude-skills

In sync

since Aug 28, 2026

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.