Skip to main content
prompt GP ChatGPT

weak_proposer — Claude Code prompt for Megatron-Core tuning

The weak_proposer Claude Code prompt tunes Megatron-Core training for speed. It proposes config changes, runs trials and identifies the fastest valid candidate.

no license ★ 99 updated 2026-11-12

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/weak_proposer.md
Open on GitHub

What weak_proposer does

The prompt guides a Megatron-Core 0.18.2 training job through speed-focused changes, one proposal at a time. It starts with configuration keys, allowing up to six L0 changes per proposal. Patches become available after the config options are exhausted, and the initial candidate is c0.

It rules out edits to batch size, sequence length, data, loss, learning rate, optimizer, precision, router and model. A trial can run only against a candidate the prompt proposed; its receipt must be read once the run ends. When memory is tight, it suggests recompute, a parallel layout or optimizer offload. With memory to spare, it suggests removing recompute or raising micro-batch size. Replies must contain a single JSON object. The job needs Megatron-Core 0.18.2 and state data with {MODE} and the available action menu.

What it helps with

  • tune Megatron-Core training settings for speed
  • compare valid candidates using trial results
  • reduce memory use when a trial is short on memory
  • select the fastest valid candidate within the run budget

Example prompts for the agent

  • Tune my Megatron-Core 0.18.2 training job for speed in mode {MODE}.
  • Propose the next valid candidate from the current job state and remaining budget.
  • Compare the trial receipts and name the fastest valid candidate.

How to install weak_proposer

Manually: put the files in place

.claude/commands/weak_proposer.md

Questions about weak_proposer

How do I install weak_proposer in Claude Code?

Save the prompt as .claude/commands/weak_proposer.md.

What does weak_proposer do?

It proposes changes to a Megatron-Core training job, uses trial results to guide further tuning and names the fastest valid candidate.

What does weak_proposer need to run?

It needs Megatron-Core 0.18.2 and job state containing {MODE} and the available action menu.

Similar prompts

Prompts catalog →
weak-signal-synthesizer OneWave-AI weak-signal-synthesizer is a Claude Code skill that connects clues from unrelated sources to surface emerging trends. It produces forecasts for the next 3–6 months with confidence scores. CX Codex +1 326installs weak-agent-test kklimuk The weak-agent-test Claude Code skill tests docx-cli with agents tackling document tasks. It covers document editing and authoring, then grades the results. CX Codex +1 ★ 251repo stars cache-miss.sequence tt-a1i cache-miss.sequence drives the Archify skill to build a sequence diagram for a dashboard request that misses cache in Redis and falls through to PostgreSQL. CX Codex GP ChatGPT ★ 98,599repo stars web-runtime.architecture tt-a1i web-runtime.architecture — a prompt for generating a production web architecture JSON diagram using Archify and saving it directly to benchmark-candidate.json. CX Codex GP ChatGPT ★ 98,599repo stars product-analytics.dataflow tt-a1i This prompt guides Archify through a product analytics data-flow diagram, from web and mobile events to dashboards and a model, with a distinct path for consent-gated identity data. CX Codex GP ChatGPT ★ 98,599repo stars agent-tool-call.workflow tt-a1i agent-tool-call.workflow — a prompt for building a workflow diagram where an AI agent calls tools with human approval gates. CX Codex GP ChatGPT ★ 98,599repo stars agent-run.lifecycle tt-a1i agent-run.lifecycle instructs an agent to build a structured lifecycle diagram for an agent run using the Archify workflow. CX Codex GP ChatGPT ★ 98,599repo stars Jupyter Notebook taste f Jupyter Notebook taste is a ChatGPT prompt for clean, repeatable notebooks. It applies when an analysis is prepared for review or a commit. GP ChatGPT ★ 178,201repo stars

From the same set19

The whole set →
infrarsi-answerer The infrarsi-answerer Claude Code subagent handles a single InfraRSI search request and saves its result in the request folder. The infrarsi-optimize skill starts it by passing that folder. CX Codex ★ 99repo stars summarizer The summarizer Claude Code prompt condenses an infrastructure optimization search into a factual handoff. It keeps candidate results and unresolved hypotheses for later turns. GP ChatGPT ★ 99repo stars verifier The verifier Claude Code prompt checks one infrastructure change before it moves to screening. It can veto a candidate based on a checklist or the parent result. GP ChatGPT ★ 99repo stars reflect The reflect Claude Code prompt revises an optimizer package using the trace from a finished task. It turns observed evidence into rules for later tasks instead of carrying over one task’s settings. GP ChatGPT ★ 99repo stars proposer proposer is a Claude Code and ChatGPT prompt that tunes training throughput in InfraRSI by proposing configuration and overlay changes while preserving fixed task settings. GP ChatGPT ★ 99repo stars weak-model-protocol The weak-model-protocol Claude Code skill sets rules for an optimizer driven by a weaker or cheaper language model. It activates when actions are malformed, context runs short, or the provider returns errors. CX Codex +1 ★ 99repo stars optimize-data-path The optimize-data-path Claude Code skill optimizes data and state transfers between the host and GPU without changing the data contract. It is triggered by costly loading, host synchronization, or optimizer-state transfers. CX Codex +1 ★ 99repo stars learn-optimization-skills The learn-optimization-skills Claude Code skill guides an optimizer’s learning between development tasks and records reusable lessons. It runs for post-task reflection or when a search turns up a reusable finding. CX Codex +1 ★ 99repo stars

Project sponsors

Companies that keep this analytics open