Mmcp.market

llm-tuning-patterns skill

by parcadei·parcadei/Continuous-Claude-v3·3.9k stars·MIT

LLM Tuning Patterns

A100/100content scan

Is the llm-tuning-patterns skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the llm-tuning-patterns skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.

git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git /tmp/Continuous-Claude-v3
mkdir -p ~/.claude/skills
cp -r /tmp/Continuous-Claude-v3/.claude/skills/llm-tuning-patterns ~/.claude/skills/llm-tuning-patterns
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

LLM Tuning Patterns

Evidence-based patterns for configuring LLM parameters, based on APOLLO and Godel-Prover research.

Pattern

Different tasks require different LLM configurations. Use these evidence-based settings.

Theorem Proving / Formal Reasoning

Based on APOLLO parity analysis:

Proof Plan Prompt

Always request a proof plan before tactics:

Given the theorem to prove:
[theorem statement]

First, write a high-level proof plan explaining your approach.
Then, suggest Lean 4 tactics to implement each step.

The proof plan (chain-of-thought) significantly improves tactic quality.

Parallel Sampling

For hard proofs, use parallel sampling:

  • Generate N=8-32 candidate proof attempts
  • Use best-of-N selection
  • Each sample at temperature 0.6-0.8

Code Generation

Creative / Exploration Tasks

Anti-Patterns

  • Too low tokens for proofs: 512 tokens truncates chain-of-thought
  • Too low temperature for proofs: 0.2 misses creative tactic paths
  • No proof plan: Jumping to tactics without planning reduces success rate

Source Sessions

  • This session: APOLLO parity - increased max_tokens 512->4096, temp 0.2->0.6
  • This session: Added proof plan prompt for chain-of-thought before tactics

More skills from parcadei/Continuous-Claude-v3

All agent skills → · MCP servers