WCAG 2.2 AA compliance, ARIA patterns, keyboard navigation, screen reader optimization
The English summary is being prepared. Showing the original description.
vibeeval/vibecosystem538Updated Aug 9, 2026
FreePublished on GitHub
llm-tuning-patterns
LLM Tuning Patterns
The English summary is being prepared. Showing the original description.
See how to installFiles included (1)
- SKILL.md1.9 KB
SKILL.md (original)
Review the instructions the agent will receive before you install.
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
Reviews
No reviews yet. Tell others what you thought.
Comments
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
More skills from this repository
axe-core integration, WCAG 2.2 AA checklist, keyboard navigation testing, screen reader testing, and ARIA pattern validation.
The English summary is being prepared. Showing the original description.
vibeeval/vibecosystem538Updated Aug 9, 2026
achievements
FreeSteam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements across 5 categories.
The English summary is being prepared. Showing the original description.
vibeeval/vibecosystem538Updated Aug 9, 2026
agent-benchmark
FreeFramework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.
The English summary is being prepared. Showing the original description.
vibeeval/vibecosystem538Updated Aug 9, 2026
Agent Context Isolation
The English summary is being prepared. Showing the original description.
vibeeval/vibecosystem538Updated Aug 9, 2026
agent-linter
FreeAgent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarlilik denetimi. Yeni agent/skill eklendiginde veya mevcut dosyalar duzenlediginde otomatik calistirilir.
The English summary is being prepared. Showing the original description.
vibeeval/vibecosystem538Updated Aug 9, 2026