LLM Fine Tuning
sickn33/agentic-awesome-skills
Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP.
“LLM Tuning Patterns”
MITAuto-check passed
Install LLM Tuning Patterns
$ npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 llm-tuning-patterns --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/llm-tuning-patterns .claude/skills/llm-tuning-patterns && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "llm-tuning-patterns" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/llm-tuning-patterns into .claude/skills/llm-tuning-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-tuning-patterns", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/llm-tuning-patternsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 llm-tuning-patterns --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/llm-tuning-patterns .agents/skills/llm-tuning-patterns && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "llm-tuning-patterns" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/llm-tuning-patterns into .agents/skills/llm-tuning-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-tuning-patterns", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 llm-tuning-patterns --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/llm-tuning-patterns .cursor/skills/llm-tuning-patterns && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "llm-tuning-patterns" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/llm-tuning-patterns into .cursor/skills/llm-tuning-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-tuning-patterns", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/parcadei/Continuous-Claude-v3.git --path .claude/skills/llm-tuning-patterns--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 llm-tuning-patterns --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/llm-tuning-patterns .gemini/skills/llm-tuning-patterns && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "llm-tuning-patterns" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/llm-tuning-patterns into .gemini/skills/llm-tuning-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-tuning-patterns", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install parcadei/Continuous-Claude-v3 llm-tuning-patternsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/llm-tuning-patterns .github/skills/llm-tuning-patterns && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "llm-tuning-patterns" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/llm-tuning-patterns into .github/skills/llm-tuning-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-tuning-patterns", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install parcadei/Continuous-Claude-v3 llm-tuning-patterns --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/llm-tuning-patterns .opencode/skills/llm-tuning-patterns && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "llm-tuning-patterns" agent skill from https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/llm-tuning-patterns into .opencode/skills/llm-tuning-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-tuning-patterns", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
llm-tuning-patterns- GitHub stars
- 3.9k
- Used in
- 1 other repo
- Token cost
- ~481 tokens
- SKILL.md length
- 180 words
- Files
- 1
- Skills in repo
- 141
- Repo updated
- First seen
- Licence
- MIT
At a glance
- SKILL.md covers Pattern, Theorem Proving / Formal…, Code Generation and Creative / Exploration Tasks, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
LLM Tuning Patterns is a skill in parcadei/Continuous-Claude-v3 (3.9k stars). Its SKILL.md is about 481 tokens, and copies of it appear in 1 other owners' repositories. Licence: MIT.
What it can do on your machine
Read from SKILL.md and the folder at commit d07ff4b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
LLM Tuning Patterns loads about 481 tokens when it runs. Until then it costs about 10 tokens; SKILL.md has 180 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from parcadei/Continuous-Claude-v3 at commit d07ff4b, republished under its MIT licence (© parcadei). 180 words, ~481 tokens.
Download SKILL.mdSave it as
.claude/skills/llm-tuning-patterns/SKILL.md (or your agent's skills folder).- name
- llm-tuning-patterns
- description
- LLM Tuning Patterns
- user-invocable
- false
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
© parcadei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/llm-tuning-patterns of parcadei/Continuous-Claude-v3.
Open the folder on GitHubat commit d07ff4b
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in parcadei/Continuous-Claude-v3, which our catalogue first saw on October 7, 2026.
Compare with similar skills
LLM Tuning Patterns next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| LLM Tuning Patterns this skillparcadei/Continuous-Claude-v3 | 3.9k | 1 repos | ~481 | Automated safety check: Pass | MIT | |
| LLM Fine Tuningsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Fine Tuning With TrlOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Agent Platform Tuninggoogle/skills | 21k | — | ~9.6k | Automated safety check: Pass | Apache-2.0 | |
| Agent Platform Tuning Managementgoogle/skills | 21k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Peft Fine TuningOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Fine Tuning With Trl
Orchestra-Research/AI-Research-SKILLs
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.
- Official
Agent Platform Tuning
google/skills
Agent Platform Model Tuning. An agent skill from google/skills.
- Official
Agent Platform Tuning Management
google/skills
Manages GenAI tuning jobs in Agent Platform. An agent skill from google/skills.
Peft Fine Tuning
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
Od Tune Collab
nexu-io/open-design
Default reference pipeline for the tune-collab taskKind — pick a direction, patch-edit the existing artifact, critique, hand off.
More from parcadei/Continuous-Claude-v3
All 141 skills in this repoCompound Learnings
parcadei/Continuous-Claude-v3
Transform session learnings into permanent capabilities (skills, rules, agents).
Debug Hooks
parcadei/Continuous-Claude-v3
Systematic hook debugging workflow. An agent skill from parcadei/Continuous-Claude-v3.
Tldr Deep
parcadei/Continuous-Claude-v3
Full 5-layer analysis of a specific function. An agent skill from parcadei/Continuous-Claude-v3.
Gradient Methods
parcadei/Continuous-Claude-v3
Problem-solving strategies for gradient methods in optimization
Math
parcadei/Continuous-Claude-v3
Unified math capabilities - computation, solving, and explanation.
Math Model Selector
parcadei/Continuous-Claude-v3
Routes problems to appropriate mathematical frameworks using expert heuristics
Questions about LLM Tuning Patterns
How do I install LLM Tuning Patterns in Claude Code?
Run `npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a claude-code`. Or copy the skill folder (.claude/skills/llm-tuning-patterns in parcadei/Continuous-Claude-v3) into .claude/skills/llm-tuning-patterns in your project. Claude Code loads it when a task matches its description.
How do I install LLM Tuning Patterns in Codex?
Run `npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a codex`. Or copy the skill folder (.claude/skills/llm-tuning-patterns in parcadei/Continuous-Claude-v3) into .agents/skills/llm-tuning-patterns in your project. Codex loads it when a task matches its description.
Can I use LLM Tuning Patterns in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add parcadei/Continuous-Claude-v3 --skill llm-tuning-patterns -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/llm-tuning-patterns, .gemini/skills/llm-tuning-patterns, .github/skills/llm-tuning-patterns and .opencode/skills/llm-tuning-patterns in your project.
What does LLM Tuning Patterns need to run?
SKILL.md names no scripts, command-line tools or credentials: LLM Tuning Patterns is instructions for the agent only.
Does LLM Tuning Patterns access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is LLM Tuning Patterns safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does LLM Tuning Patterns use?
LLM Tuning Patterns is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does LLM Tuning Patterns use?
About 481 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to LLM Tuning Patterns?
Skills that share tags, products or a category with LLM Tuning Patterns: LLM Fine Tuning (sickn33/agentic-awesome-skills, 47k stars), Fine Tuning With Trl (Orchestra-Research/AI-Research-SKILLs, 13k stars), Agent Platform Tuning (google/skills, 21k stars) and Agent Platform Tuning Management (google/skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains LLM Tuning Patterns?
parcadei (a GitHub user) maintains it in parcadei/Continuous-Claude-v3, which has 3,943 GitHub stars. The repository holds 141 skills in this directory. The repository was last updated on January 26, 2026.
Source: parcadei/Continuous-Claude-v3 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.