Neutron

Spend fewer tokens without lowering the ceiling. Use when a task will take more than about ten tool calls, before spawning subagents or choosing a model for delegated work, when context is filling up, or on "save tokens", "token budget", "cheaper way", "which model", "optimise this prompt", "this is burning context". Tightens a multi-part ask, picks model tier, reasoning effort, execution shape and output profile, and states the choice in one line.

48 stars 6 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add frankxai/claude-skills-library

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add frankxai/claude-skills-library --skill neutron
Manual install
git clone --depth 1 https://github.com/frankxai/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/packs/starlight-neutron/skills/neutron ~/.claude/skills/neutron

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Neutron

Cut waste, never reasoning. Neutron decides how a task runs. It does not decide what the answer is, and it never trades correctness for a smaller bill.

Run the five steps in order. Skip a step when it clearly does not apply: a one-line question needs none of them. Total overhead is one short message.

## 1. Tighten the ask

Only when the request is multi-part, vague or long. Rewrite it as one block with five parts. Do not do the task yet.

1. **Goal and done-condition.** What exists or passes when this is finished.
2. **Scope.** Exact paths, repos, or systems. Name what is out of scope.
3. **Constraints.** Versions, style, things that must not change.
4. **Output shape.** Diff, file, table, one-line verdict. Length cap if one matters.
5. **Known facts.** What the user already established, so it is not re-derived.

Tightening removes repetition and ambiguity. It does not shorten sentences into fragments. Compressing the user's prompt makes answers longer and worse, because the model has to guess what was cut. Keep the user's meaning whole and their words where they carry it.

If the ask is genuinely ambiguous in a way that changes the work, ask one question. Otherwise state the assumption and go.

## 2. Pick the shape
Read the full skill on GitHub

Details

Skill name
neutron
Path
packs/starlight-neutron/skills/neutron/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Neutron skill do?

Spend fewer tokens without lowering the ceiling. Use when a task will take more than about ten tool calls, before spawning subagents or choosing a model for delegated work, when context is filling up, or on "save tokens", "token budget", "cheaper way", "which model", "optimise this prompt", "this is burning context". Tightens a multi-part ask, picks model tier, reasoning effort, execution shape and output profile, and states the choice in one line.

How do I install the Neutron skill?

Claude Code plugin: /plugin marketplace add frankxai/claude-skills-library. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Neutron popular?

It lives in frankxai/claude-skills-library, which has 48 GitHub stars and 6 forks.

Related skills

Acos Meta

48

frankxai/claude-skills-library

ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.

Software Development

Acos Visual Gen

48

frankxai/claude-skills-library

Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.

Images, Video & Audio

Agent Harness Construction

48

frankxai/claude-skills-library

Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a skill, a hook, or a worktree lane.

AI, LLMs & Agents

Openai Agentkit

48

frankxai/claude-skills-library

Build production multi-agent systems with OpenAI AgentKit and the Agents SDK — orchestration, handoffs, and routines. Use when writing agents against OpenAI's AgentKit/Agents SDK or porting an agent design to the OpenAI stack.

AI, LLMs & Agents

Model Routing

48

frankxai/claude-skills-library

Picks the Claude model tier (Haiku, Sonnet, Opus, Fable) and effort level for a task class, with current model IDs and per-token prices. Use when the user asks which Claude model to run, wants to cut API or agent spend by routing work to cheaper tiers, needs exact model IDs or prices for a routing table, or is setting the model on a subagent or Task call. Do not use for ordinary coding, ORM or database "models", ML model training, or general cost questions that do not involve choosing a Claude model.

AI, LLMs & Agents

Opus Extended Thinking

48

frankxai/claude-skills-library

Use Claude's extended/adaptive thinking for deep reasoning, complex analysis, and multi-step synthesis — both the prompt patterns that elicit deliberation and the current thinking API (adaptive thinking + the effort parameter). Use when a problem needs thorough deliberation before answering, or when configuring thinking on a Claude request.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.