llm-tuning-patterns

by parcadei3.9k

LLM Tuning Patterns

Install

The skill file stays in the publisher's repository.

Paste the copied command in a terminal. It installs this SKILL.md into that agent.

npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a cursor -y

How do I install llm-tuning-patterns?: Download .claude/skills/llm-tuning-patterns/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does llm-tuning-patterns live?: The publisher keeps it at https://github.com/parcadei/Continuous-Claude-v3.
Which agents can use llm-tuning-patterns?: Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.

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

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

Based on APOLLO parity analysis:

Parameter	Value	Rationale
max_tokens	4096	Proofs need space for chain-of-thought
temperature	0.6	Higher creativity for tactic exploration

Parameter	Value	Rationale
max_tokens	2048	Sufficient for most functions
temperature	0.2-0.4	Prefer deterministic output

Parameter	Value	Rationale
max_tokens	4096	Space for exploration
temperature	0.8-1.0	Maximum creativity