Agent skill

Retro Marimo Pair

by PhySpace in PhySpace/SimpleCADAPI

Session retrospective for improving marimo-pair and marimo.codemode.

Apache-2.0Auto-check passedProduct & Project Management

Install Retro Marimo Pair

skills CLI
$ npx skills add PhySpace/SimpleCADAPI --skill retro-marimo-pair -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install PhySpace/SimpleCADAPI retro-marimo-pair --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/PhySpace/SimpleCADAPI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/retro-marimo-pair .claude/skills/retro-marimo-pair && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
retro-marimo-pair
GitHub stars
141
Token cost
~1.6k tokens
SKILL.md length
804 words
Files
2
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Session retrospective for improving marimo-pair and marimo.codemode.

  • Works in 4 steps: Session Analysis → Root Cause Discussion → Diagnose & Capture → …
  • The user wants to analyze friction from a pairing session
  • SKILL.md covers Guard Rails, Step 1: Session Analysis, Step 2: Root Cause Discussion and Step 3: Diagnose & Capture, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Retro Marimo Pair is an agent skill from PhySpace/SimpleCADAPI. Session retrospective for improving marimo-pair and marimo.codemode. Use when the user wants to analyze friction from a pairing session, identify what went wrong, and brainstorm improvements to the skill docs or the underlying API. Trigger on: "retro", "what went wrong", "improve the skill", "session review", "friction", or /retro-marimo-pair.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `reference/code-mode-surface.md`).

It sits in Product & Project Management, covering Jupyter notebooks and Retrospectives. It works with marimo and Python. The repository describes itself as: An agent-native CAD SDK for language models to create, inspect, and reconstruct complex, editable 3D models. The licence is Apache-2.0.

When your agent uses it

  • The user wants to analyze friction from a pairing session
  • Identify what went wrong
  • Brainstorm improvements to the skill docs
  • The underlying API

Example prompts

  • “what went wrong”
  • “improve the skill”
  • “session review”
  • “/retro-marimo-pair”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Session Analysis
  2. Root Cause Discussion
  3. Diagnose & Capture
  4. File or Follow Up

What it can do on your machine

Read from SKILL.md and the folder at commit ea93070. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Retro Marimo Pair loads about 1.6k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 804 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from PhySpace/SimpleCADAPI at commit ea93070, republished under its Apache-2.0 licence (© PhySpace). 804 words, ~1,600 tokens.

Download SKILL.mdSave it as .claude/skills/retro-marimo-pair/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
retro-marimo-pair
description
Session retrospective for improving marimo-pair and marimo._code_mode. Use when the user wants to analyze friction from a pairing session, identify what went wrong, and brainstorm improvements to the skill docs or the underlying API. Trigger on: "retro", "what went wrong", "improve the skill", "session review", "friction", or /retro-marimo-pair.

Session Retrospective

You are helping a marimo team member review a pairing session to find friction and turn it into improvements. The target is always one or both of:

  1. The marimo-pair skill (github://marimo-team/marimo-pair)
  2. marimo._code_mode — the underlying notebook metaprogramming API

This is a conversation, not an automated report. You surface findings, the user steers which ones matter, and together you decide what to do about them.

Guard Rails

  • NEVER edit files in github://marimo-team/marimo-pair without explicit user approval.
  • ALWAYS start with session analysis (Step 1) — do not jump to solutions.
  • Present friction points before root causes — let the user choose which ones to dig into.
  • If the user invoked with a specific complaint, focus your analysis there but still scan for other friction in the background.

Step 1: Session Analysis

Review the current conversation and identify friction. Look for:

SignalWhat to look for
User frustrationCorrections ("no not that"), repeated attempts, backtracking, confusion, tone shifts
InefficiencyMultiple rounds for a one-step task, over-engineering, wrong API usage
ErrorsCompile-check failures, runtime errors, silent failures, wrong output
WorkaroundsUser or Claude working around a limitation instead of doing it directly
Context lossClaude forgetting instructions from earlier, re-asking things the skill covers

Present a numbered summary of friction points found. For each, note:

  • What happened (brief)
  • Where in the conversation it occurred (quote or paraphrase)
  • Initial category guess (skill structure / skill gap / API issue / etc.)

Then ask: "Which of these should we dig into? Or is there something I missed?"

Step 2: Root Cause Discussion

For each friction point the user selects, work through these lenses:

LensQuestionExample improvement
Skill structureWas the right info in the skill but hard to find? Buried in reference/ when it should be in SKILL.md?Promote to guard rail, restructure progressive disclosure
Skill gapWas information missing entirely from the skill?Add new section, example, or anti-pattern
Misleading docsDid the skill say something that led Claude astray?Correct the docs, add clarifying examples
API ergonomicsWas _code_mode clunky or unintuitive for this task?Propose API improvement (better defaults, clearer errors)
Missing APIIs there something _code_mode simply can't do that it should?Design a new API surface
API bugDid _code_mode behave incorrectly?Characterize the bug, propose fix or workaround
Context windowDid Claude forget instructions due to long context?Shorter, more prominent guard rails

Discuss each lens briefly, then converge on the most likely root cause with the user. It's okay to have multiple contributing causes.

Show full SKILL.md (390 more words)Show less

Step 3: Diagnose & Capture

The goal of a retro is diagnosis, not a contribution. Based on the root cause, write up a clear diagnosis the team can act on — don't jump to proposing or authoring a fix.

For each friction point, produce:

  • Diagnosis — What went wrong and why it was frustrating, in plain terms
  • Contributing factors — Skill structure, gap, misleading docs, API ergonomics, missing API, API bug, context window (from Step 2)
  • Considerations — Trade-offs, open questions, or things that would need to be true for a fix to make sense. Note possible directions here, but frame them as considerations rather than committed solutions.

The default next step is to capture the diagnosis as an issue or discussion so the team can weigh it — not to immediately make a contribution. Concrete code changes (skill edits, API designs) come after an issue/discussion exists and the user explicitly chooses to go further.

Present the diagnosis and ask: "Want me to draft this as an issue or discussion?"

Step 4: File or Follow Up

Default: file an issue / discussion

Write it up clearly for the marimo team to triage:

  • Problem: What happened and why it's painful
  • Current behavior: What the skill or _code_mode does today
  • Considerations: Trade-offs and open questions (not a committed solution)
  • Example: A minimal snippet or quote from the session, if helpful

Leave the actual filing to the user — do not auto-file. This is the preferred outcome: surface friction for the team rather than ship a fix from the retro.

Only if the user explicitly wants to go further

A skill edit or API change should follow an issue/discussion, not replace it. If — and only if — the user explicitly asks to draft a change now:

  1. Read the target file in github://marimo-team/marimo-pair
  2. Show the proposed diff to the user
  3. Only apply after explicit sign-off
  4. After applying, verify SKILL.md stays under 500 lines (reference/ files have no limit)
Wrapping up

After completing the cycle for the selected friction points, ask if the user wants to revisit any remaining items from Step 1, or if the retro is done.

Key Files Reference

FilePurpose
github://marimo-team/marimo-pair/SKILL.mdMain skill instructions
github://marimo-team/marimo-pair/reference/execute-code.mdScratchpad & cell operation recipes
github://marimo-team/marimo-pair/reference/rich-representations.mdWidget & display patterns
github://marimo-team/marimo-pair/scripts/Bundled discovery & execution scripts

To inspect the live _code_mode API surface during a retro, the user can run in their notebook scratchpad:

python
import marimo._code_mode as cm

async with cm.get_context() as ctx:
    # List all public methods/attributes
    print([x for x in dir(ctx) if not x.startswith('_')])
    help(ctx)

© PhySpace, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/retro-marimo-pair of PhySpace/SimpleCADAPI.

  • SKILL.md
  • reference/code-mode-surface.md

Open the folder on GitHubat commit ea93070

Compare with similar skills

Retro Marimo Pair next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Retro Marimo Pair compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Retro Marimo Pair this skillPhySpace/SimpleCADAPI141—~1.6kAutomated safety check: PassApache-2.0
Wasm Compatibilityericmjl/llamabot1822 repos~1.6kAutomated safety check: PassNone
Marimo Paircosanlab/nltools1311 repos~3kAutomated safety check: PassMIT
Marimo Notebookcosanlab/nltools1314 repos~2.1kAutomated safety check: PassMIT
Marimo Pair Vscodemarimo-team/marimo-lsp130—~2.7kAutomated safety check: PassApache-2.0
Marimobrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~2.8kAutomated safety check: PassCustom licence

Similar skills

  • Wasm Compatibility

    ericmjl/llamabot

    Check if a marimo notebook is compatible with WebAssembly (WASM) and report any issues.

    182 GitHub starsUsed in 2 repos~1.6k tokens
    Data & AnalyticsAuto-check passed
  • Marimo Pair

    cosanlab/nltools

    Work inside a running marimo notebook's kernel — execute code, create cells, and build a notebook as an artifact.

    131 GitHub starsUsed in 1 repo~3k tokens
    Data & AnalyticsAuto-check passed
  • Marimo Notebook

    cosanlab/nltools

    Write a marimo notebook in a Python file in the right format.

    131 GitHub starsUsed in 4 repos~2.1k tokens
    Data & AnalyticsAuto-check passed
  • Marimo Pair Vscode

    marimo-team/marimo-lsp

    Drive a live marimo notebook in VS Code as a workspace: run Python in the same kernel the user does, inspect and explore live notebook state and data, prototype and debug code, and commit durable…

    130 GitHub stars~2.7k tokensUpdated 2 days ago
    Data & AnalyticsAuto-check passed
  • Marimo

    brycewang-stanford/Auto-Empirical-Research-Skills

    Reactive Python notebook system. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.5k GitHub stars~2.8k tokensUpdated 2 days ago
    Data & AnalyticsAuto-check passed
  • Marimo Notebook

    minicoohei/ai-agent-camp

    marimo ノートブックを正しいフォーマットでPythonファイルに作成するスキル. An agent skill from minicoohei/ai-agent-camp.

    347 GitHub stars~1.5k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

More from PhySpace/SimpleCADAPI

  • Marimo Pair

    PhySpace/SimpleCADAPI

    Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes.

    141 GitHub stars~3k tokensUpdated 5 days ago
    Auto-check passed
  • Simplecadapi

    PhySpace/SimpleCADAPI

    Build, assemble, inspect, reconstruct, and export parametric CAD models with the SimpleCADAPI Python SDK.

    141 GitHub stars~2.5k tokensUpdated 5 days ago
    Auto-check passed

Works with

Questions about Retro Marimo Pair

What does Retro Marimo Pair do?

Session retrospective for improving marimo-pair and marimo.codemode. Retro Marimo Pair is an agent skill from PhySpace/SimpleCADAPI.codemode.

When should I use Retro Marimo Pair?

Retro Marimo Pair fits situations like: the user wants to analyze friction from a pairing session; identify what went wrong; brainstorm improvements to the skill docs; the underlying API.

How do I install Retro Marimo Pair in Claude Code?

Run `npx skills add PhySpace/SimpleCADAPI --skill retro-marimo-pair -a claude-code`. Or copy the skill folder (.agents/skills/retro-marimo-pair in PhySpace/SimpleCADAPI) into .claude/skills/retro-marimo-pair in your project. Claude Code loads it when a task matches its description.

How do I install Retro Marimo Pair in Codex?

Run `npx skills add PhySpace/SimpleCADAPI --skill retro-marimo-pair -a codex`. Or copy the skill folder (.agents/skills/retro-marimo-pair in PhySpace/SimpleCADAPI) into .agents/skills/retro-marimo-pair in your project. Codex loads it when a task matches its description.

Can I use Retro Marimo Pair in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PhySpace/SimpleCADAPI --skill retro-marimo-pair -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retro-marimo-pair, .gemini/skills/retro-marimo-pair, .github/skills/retro-marimo-pair and .opencode/skills/retro-marimo-pair in your project.

What does Retro Marimo Pair need to run?

SKILL.md names no scripts, command-line tools or credentials: Retro Marimo Pair is instructions for the agent only. Our summary lists: Python 3.

Does Retro Marimo Pair access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Retro Marimo Pair safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Retro Marimo Pair use?

Retro Marimo Pair is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Retro Marimo Pair use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Retro Marimo Pair?

Skills that share tags, products or a category with Retro Marimo Pair: Wasm Compatibility (ericmjl/llamabot, 182 stars), Marimo Pair (cosanlab/nltools, 131 stars), Marimo Notebook (cosanlab/nltools, 131 stars) and Marimo Pair Vscode (marimo-team/marimo-lsp, 130 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Retro Marimo Pair?

PhySpace (a GitHub organization) maintains it in PhySpace/SimpleCADAPI, which has 141 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 2, 2026.

Source: PhySpace/SimpleCADAPI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.