npx skills add smithery/parcadei --skill llm-tuning-patterns
parcadei/continuous-claude-v3
llm-tuning-patterns
LLM Tuning Patterns
Installation
$
npx skills add parcadei/continuous-claude-v3 --skill llm-tuning-patterns
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
vercel-composition-patterns
Similar name
vercel-labs/agent-skills
326.5K installs
clerk-nextjs-patterns
Similar name
clerk/skills
41.5K installs
clerk-react-patterns
Similar name
clerk/skills
React SPA auth patterns with @clerk/react for Vite/CRA - ClerkProvider setup, useAuth/useUser/u…
15.8K installs
clerk-react-router-patterns
Similar name
clerk/skills
React Router v7/v8 patterns with Clerk — rootAuthLoader, getAuth in loaders, clerkMiddleware, p…
12.7K installs
clerk-tanstack-patterns
Similar name
clerk/skills
TanStack React Start auth patterns with @clerk/tanstack-react-start - createServerFn, beforeLoa…
12.5K installs
clerk-chrome-extension-patterns
Similar name
clerk/skills
Chrome Extension auth with @clerk/chrome-extension -- popup/sidepanel setup, syncHost for OAuth…
11.7K installsAlso in this package
Other skills from parcadei/continuous-claude-v3 · top by installs.
npx skills add parcadei/continuous-claude-v3
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Claude Code
Not declared
Cursor
Not declared
Codex
Not declared
GitHub Copilot
Not declared
Windsurf
Not declared
Gemini CLI
Not declared
Cline
Not declared
OpenCode
Not declared
Also listed on
Alternate registries and mirrors of this skill.
Repository health
Stars
3.9K
License
LICENSE
Default branch
main
Open issues
30
Status
Active
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md1,923 B -
docs
SUMMARY.md46 B
History
- First seen on skills.sh
- First recorded snapshot · 472 installs
SKILL.md
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