Skip to main content
skill CX Codex

nba — Claude Code skill: what it does, how to install

The skill inspects project cycle state and returns a single high-priority action to resume work. It helps break paralysis when too many threads are open.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add LilMGenius/paperthin --skill nba -a claude-code
Open on GitHub

What nba does

nba acts as a re-entry point when a development cycle stalls. It inspects live repository state, checking plan gates, recent git diffs, priority notes, QA evidence, and cycle phases from FRAME to SHIP. Instead of offering a menu of options, it isolates the single cheapest move that clears the binding constraint.

Every response outlines four points: where you are, the next best action, why now, and done when. The skill operates strictly read-only and never runs edits or skills automatically, so the developer must execute the recommended step manually.

What it helps with

  • pick the single next action when progress stalls
  • diagnose the cause of project paralysis
  • determine the active cycle phase from git and notes

Example prompts for the agent

  • Check the current cycle state and tell me the next best action.
  • I am stuck between project phases, what is the single next move?

How to install nba

1Skills CLI (Vercel)

npx skills add LilMGenius/paperthin --skill nba -a claude-code

2Manually: put the files in place

~/.claude/skills/nba/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/nba/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about nba

How do I install nba in Claude Code?

Run npx skills add LilMGenius/paperthin --skill nba -a claude-code. The skill configuration installs into ~/.claude/skills/nba/SKILL.md.

What does the nba skill do?

It reads repository evidence and git changes to determine your project phase, then recommends one specific move to unblock work.

Does nba make changes to the codebase?

No, it is strictly read-only. It identifies what to do next and defines when it is done, but leaves execution to the developer.

Source text

SKILL.md · MIT
---
name: nba
description: "Read the live cycle state and return the single highest-leverage next best action, not a menu. Use when a project is between phases, the author asks what to do next, too many valid threads are open, or the work needs re-entry into frame, build, drive, re0-memo, hate, re0-work, or ship."
---

Find the next best action from state, not from vibes.

## Goal

`nba` is the manual re-entry point for a stalled cycle. It reads the current state and returns one action: the cheapest move that clears the binding constraint. It does not execute the action and it does not offer a menu, because a menu recreates the paralysis it exists to resolve.

## Workflow

1. Read the live cycle state: plan gates, re0-memo anti-patterns, priority notes, recent git/file changes, QA evidence, and the current workflow phase.
2. Locate the project in the cycle: FRAME, BUILD, DRIVE, RE0-MEMO, HATE, RE0-WORK, BUILD AGAIN, or SHIP.
3. Diagnose the blank-out cause: too many open threads, lost thread, unnamed blocker, closed-loop fatigue, avoidance of the hard step, or a phase that is already done.
4. Return one action: the cheapest move that clears the most. It may name the right skill for the human to fire, the external input needed, the first nail to test, or the phase transition that is already due.
5. Frame it as: where you are, next best action, why now, and done when.

## Rules

- One action, not a checklist.
- State-grounded, never generic. Cite the gate, doc, evidence, or file state that drives the pick.
- Return the avoided move, not the easy busywork.
- If no outside truth is entering, the next action is external input, not another internal lap.
- If the gate is already met, the action is to move phase or ship, not add another surface.
- Read-only on the project. `nba` recommends; it does not execute.
- Do not auto-invoke user-only skills. Tell the human when one is the next move.

## Verification

Before finishing:

1. The recommendation cites the state it read.
2. There is exactly one next action.
3. The action has a clear "done when" observable.
4. A reader can tell why this action beats the other visible options.

© LilMGenius · MIT · LilMGenius/paperthin

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set28

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor