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.zipInstalls 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 PatternsKey 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
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:
| Parameter | Value | Rationale |
|---|---|---|
| max_tokens | 4096 | Proofs need space for chain-of-thought |
| temperature | 0.6 | Higher creativity for tactic exploration |
| top_p | 0.95 | Allow 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
| Parameter | Value | Rationale |
|---|---|---|
| max_tokens | 2048 | Sufficient for most functions |
| temperature | 0.2-0.4 | Prefer deterministic output |
Creative / Exploration Tasks
| Parameter | Value | Rationale |
|---|---|---|
| max_tokens | 4096 | Space for exploration |
| temperature | 0.8-1.0 | Maximum 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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| llm-tuning-patterns (this skill) | 1 | 7mo | No flags | Intermediate |
| prompt-analyzer | 1 | 7mo | No flags | Intermediate |
| instructor | 1 | 7mo | Review | Intermediate |
| context-engineering | 0 | 2mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by parcadei
View all by parcadei →You might also like
prompt-analyzer
huangserva
提示词分析与洞察 - 查看Prompt详情、对比差异、推荐相似提示词、元素库统计
instructor
davila7
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
context-engineering
itallstartedwithaidea
>-
rlm
XiaoConstantine
Recursive Language Model for processing large contexts (>50KB). Use for complex analysis tasks where token efficiency matters. Achieves 40% token savings by letting the LLM programmatically explore context via Query() and FINAL() patterns.
scepticagent-prompts
Maros112358
ScepticAgent AI prompt reference. Use whenever the user asks about the prompts, wants to change analysis behaviour, modify what the AI looks for, adjust highlight categories or scoring, understand what instructions are sent to the AI, or tune the output format of analysis or highlights.
langsmith-evaluator
dhar174
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run v