llm-tuning-patterns skill
LLM Tuning Patterns
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
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
- Aagent-context-isolationAgent Context Isolation
- Aagent-orchestrationAgent Orchestration Rules
- Aagentic-workflowAgentic Workflow Pattern
- Aagentica-claude-proxyGuide for integrating Agentica SDK with Claude Code CLI proxy
- Aagentica-infrastructureReference guide for Agentica multi-agent infrastructure APIs
- Aagentica-promptsWrite reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
- Aagentica-sdkBuild Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
- Aagentica-serverAgentica server + Claude proxy setup - architecture, startup sequence, debugging
- Aagentica-spawnSpawn Agentica multi-agent patterns
- Aanalytic-functionsProblem-solving strategies for analytic functions in complex analysis
- Aast-grep-findAST-based code search and refactoring via ast-grep MCP
- Aasync-repl-protocolAsync REPL Protocol