Skills for Real Engineers. Straight from my .agents directory.
interview
Agent skill fromalirezarezvani/claude-skills
Use when someone has an agent idea to scope before launch ('help me scope an agent'). Interviews them about the one job and writes a build sheet with build_sheet_builder.py, checked by primitives_validator.py; no API key needed.
How to install interview
npx skills add alirezarezvani/claude-skills# or add only this skill to Claude Code: copy the folder
agent-launcher/skills/interview/
# into
~/.claude/skills/interview/ (all projects)
.claude/skills/interview/ (one project)
1# Phase 1 — Interview → Plan23Open warmly with one or two examples from4[`../../references/examples-bank.md`](../../references/examples-bank.md), then interview5the founder into a **build sheet**. No API key needed in this phase — the output6is a plan.78## The six intake slots (ask one at a time; use AskUserQuestion for choices)910| Slot | Question | Maps to |11|---|---|---|12| **Job** | "What one job should this agent do end-to-end?" | `agent.system` + outcome `description` |13| **Trigger** | "What kicks it off — you ask it, an event, or a schedule?" | on-demand / event / cron |14| **Inputs** | "What does it read?" (files, repo, memory, gmail/slack/github, web) | resources / MCP servers / memory |15| **Actions** | "What does it do?" (draft, write, call APIs, run code) | agent toolset / custom tools / MCP |16| **Done** | "How would you grade a good run?" | outcome `rubric` (required) |17| **Recurrence** | "Once, on request, or on a cadence?" | single-pass / grade-loop / cron-loop |1819See [`../../references/interview-to-config.md`](../../references/interview-to-config.md)20for the full mapping.2122## Workflow23241. **Interview.** Walk the six slots. Capture the founder's own words — never25 invent specifics they didn't claim.262. **Map to primitives.**27 ```bash28 python3 scripts/interview_planner.py \29 --job "Triage overnight support email" --trigger schedule \30 --inputs "gmail,memory" --actions "label,reply" \31…
Excerpt shown under the repository's MIT license.
More skills in claude-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
