LL

llm-tuning-patterns

Provides proven parameter configurations for LLMs to enhance performance in logic, coding, and creative tasks.

Install

mkdir -p .claude/skills/llm-tuning-patterns && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3797" && unzip -o skill.zip -d .claude/skills/llm-tuning-patterns && rm skill.zip

Installs to .claude/skills/llm-tuning-patterns

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

LLM Tuning Patterns
19 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Select evidence-based parameter sets
  • Implement parallel proof sampling
  • Generate proof plans before tactic execution
  • Calibrate temperature for specific reasoning tasks
  • Detect token-truncation risks in chain-of-thought

How it works

Applies established parameter patterns derived from APOLLO parity analysis and proof-based research to control LLM behavior.

Inputs & outputs

You give it
Theorem statement or code logic task description
You get back
Optimized configuration values and structured prompt plan

When to use llm-tuning-patterns

  • Configure LLM for Lean 4 theorem proving
  • Optimize model parameters for code generation
  • Tune temperature settings for creative exploration
  • Implement parallel sampling for complex logic tasks

About this skill

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:

ParameterValueRationale
max_tokens4096Proofs need space for chain-of-thought
temperature0.6Higher creativity for tactic exploration
top_p0.95Allow diverse proof paths

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

ParameterValueRationale
max_tokens2048Sufficient for most functions
temperature0.2-0.4Prefer deterministic output

Creative / Exploration Tasks

ParameterValueRationale
max_tokens4096Space for exploration
temperature0.8-1.0Maximum creativity

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

When not to use it

  • When using models without parameter controls
  • For trivial tasks requiring no reasoning

Limitations

  • Settings derived from APOLLO may not generalize to all model families
  • Parallel sampling increases compute costs linearly

How it compares

It replaces trial-and-error prompting with data-backed, evidence-based configuration settings calibrated for specific algorithmic tasks.

Compared to similar skills

llm-tuning-patterns side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
llm-tuning-patterns (this skill)17moNo flagsIntermediate
prompt-analyzer17moNo flagsIntermediate
instructor17moReviewIntermediate
context-engineering02moNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry