SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillslab-retro

lab-retro

Agents & models

View repository

Updated 10-15 21:53

About this skill

Claude Code Lab — Final Retrospective

This skill walks a Claude Code Lab graduate through four sequential exercises that consolidate their learning, capture their best work, plan next steps, and collect structured feedback for the organizer.

How to run

Default flow: run all four parts in order. The user can also jump to a specific part with /lab-retro 2 (or just say "part 3").

Between parts, briefly summarize what just happened and ask "ready for part N?" so the user controls the pace.

All artifacts are saved into a single folder lab-retro-output/ in the current working directory:

  • 01-progress.md
  • 02-best-prompt.md
  • 03-month-plan.md
  • 04-feedback.json + 04-feedback-report.md

Create the folder if missing.

Part 1 — Progress audit

Goal: help the participant see concrete before/after.

Use AskUserQuestion:

  1. "What could you do BEFORE the lab?" (multiSelect)

    • Worked with ChatGPT/Claude in the browser
    • Used CLI tools
    • Wrote code
    • Automated tasks
    • Worked with APIs

  2. "What can you do AFTER?" (multiSelect)

    • I work with Claude Code daily
    • Set up MCP servers
    • Created my own Skill
    • Automated a real task
    • Deployed something to the web
    • I use subagents
    • I write and read CLAUDE.md consciously

  3. "How many hours per week does Claude Code save?" (singleSelect)

    • <2
    • 2–5
    • 5–10
    • 10+

Then output a markdown table comparing before/after with skill levels (0–5) and save to lab-retro-output/01-progress.md.

Part 2 — Best prompt

Goal: turn one prompt the participant is proud of into a reusable Skill.

Ask the participant: "Copy or describe your most useful prompt from the lab."

Then AskUserQuestion:

  1. "What task was the prompt for?" (singleSelect)

    • Routine automation
    • Content/documentation creation
    • Data analysis/research
    • Prototyping/development
    • Personal workflow / PKM

  2. "What made it effective?" (multiSelect)

    • Good context in CLAUDE.md
    • Clear success criteria
    • Breaking down into steps
    • Using Skills/MCP
    • Examples in the prompt
    • Constraints and anti-criteria

Reformat the prompt as a proper Skill (frontmatter + body), suggest an description line that would trigger it, and save to lab-retro-output/02-best-prompt.md. Suggest where to put it (~/.claude/skills/<name>/SKILL.md).

Part 3 — Month plan

Goal: concrete 4-week plan so momentum doesn't die after the cohort.

AskUserQuestion:

  1. "Main work task for the month?" (singleSelect)

    • Project for a client/employer
    • Own product/startup
    • Automation of current processes
    • Learning and skill development

  2. "How much time per week are you ready to devote?" (singleSelect)

    • 15–30 minutes
    • 1–2 hours
    • 3–5 hours
    • Every day

  3. "What burnout risk do you assess for yourself?" (singleSelect)

    • Low — I have a sustainable rhythm
    • Medium — sometimes I get stuck
    • High — I already recognized myself in the red flags

If risk = high, insert a mandatory rest day into the plan and a recommendation to read the AI hygiene slide again.

Generate lab-retro-output/03-month-plan.md with:

  • 4 weekly goals
  • 1–3 concrete prompts per week
  • Success criterion per week
  • Stop-conditions (when to pause)

Part 4 — Feedback for the organizer

Goal: structured feedback that goes back to the lab organizer.

AskUserQuestion:

  1. "Rate the lab overall (NPS)" (singleSelect: 0–10)
  2. "Most valuable meeting?" (singleSelect: M01 / M03 / M05 / M07 / M09 / M11)
  3. "Most valuable topic across all 6 weeks?" (multiSelect)
    • Claude Code basics
    • Prompting and context
    • Architecture and subagents
    • MCP / Skills / Hooks
    • Agent SDK and deployment
    • Evals and quality
    • AI hygiene
  4. "What to improve?" (free text)
  5. "The main obstacle you encountered?" (free text)
  6. "Do you agree to share your feedback publicly?" (singleSelect: yes / yes-anonymously / no)

Save TWO files:

  • lab-retro-output/04-feedback.json — structured for the organizer
  • lab-retro-output/04-feedback-report.md — human-readable summary for the participant

Then submit to the public proxy (no secrets needed):

curl -sS -X POST https://lab-feedback-proxy.vercel.app/api/feedback \
  -H "Content-Type: application/json" \
  -d "$(jq -nc --arg name "<participant name>" --slurpfile notes lab-retro-output/04-feedback.json '{name:$name, notes:($notes[0]|tostring)}')"

The proxy forwards to Baserow table 746002 with a server-side token. Response is {"ok":true,"row_id":<N>}. Confirm row ID with the participant.

If the request fails, fall back to local files only and tell the participant: "submit failed — your feedback is saved locally in lab-retro-output/04-feedback.json, send it to the organizer manually."

Closing

After all four parts, print:

  1. Where the four files live
  2. One sentence: "Your framework is LOOP. Your plan is in file 03. Your next step is to open it on Monday morning."
  3. Suggest committing the lab-retro-output/ folder to a personal repo or vault.

Constraints

  • Always use AskUserQuestion for structured questions — don't ask in plain text
  • Never skip a part silently; if the user opts out, write a one-line stub in the corresponding file
  • Russian by default (audience is Russian-speaking); switch to English if the user replies in English
  • Don't be sycophantic in the feedback report — surface honest patterns