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.
Fine-tune Spark's priority category by marking key contacts as primary and adjusting notification importance.
MITAuto-check passed
Install Spark Recipe Priority Tuning
$ npx skills add readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install readdle/spark-cli-skills spark-recipe-priority-tuning --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/readdle/spark-cli-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recipe-priority-tuning .claude/skills/spark-recipe-priority-tuning && 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 "spark-recipe-priority-tuning" agent skill from https://github.com/readdle/spark-cli-skills/tree/main/skills/recipe-priority-tuning into .claude/skills/spark-recipe-priority-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spark-recipe-priority-tuning", 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/readdle/spark-cli-skills/tree/main/skills/recipe-priority-tuningType 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 readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install readdle/spark-cli-skills spark-recipe-priority-tuning --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/readdle/spark-cli-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/recipe-priority-tuning .agents/skills/spark-recipe-priority-tuning && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "spark-recipe-priority-tuning" agent skill from https://github.com/readdle/spark-cli-skills/tree/main/skills/recipe-priority-tuning into .agents/skills/spark-recipe-priority-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spark-recipe-priority-tuning", 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 readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install readdle/spark-cli-skills spark-recipe-priority-tuning --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/readdle/spark-cli-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/recipe-priority-tuning .cursor/skills/spark-recipe-priority-tuning && 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 "spark-recipe-priority-tuning" agent skill from https://github.com/readdle/spark-cli-skills/tree/main/skills/recipe-priority-tuning into .cursor/skills/spark-recipe-priority-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spark-recipe-priority-tuning", 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/readdle/spark-cli-skills.git --path skills/recipe-priority-tuning--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 readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install readdle/spark-cli-skills spark-recipe-priority-tuning --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/readdle/spark-cli-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/recipe-priority-tuning .gemini/skills/spark-recipe-priority-tuning && 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 "spark-recipe-priority-tuning" agent skill from https://github.com/readdle/spark-cli-skills/tree/main/skills/recipe-priority-tuning into .gemini/skills/spark-recipe-priority-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spark-recipe-priority-tuning", 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 readdle/spark-cli-skills spark-recipe-priority-tuningInstalls 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 readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/readdle/spark-cli-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/recipe-priority-tuning .github/skills/spark-recipe-priority-tuning && 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 "spark-recipe-priority-tuning" agent skill from https://github.com/readdle/spark-cli-skills/tree/main/skills/recipe-priority-tuning into .github/skills/spark-recipe-priority-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spark-recipe-priority-tuning", 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 readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install readdle/spark-cli-skills spark-recipe-priority-tuning --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/readdle/spark-cli-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/recipe-priority-tuning .opencode/skills/spark-recipe-priority-tuning && 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 "spark-recipe-priority-tuning" agent skill from https://github.com/readdle/spark-cli-skills/tree/main/skills/recipe-priority-tuning into .opencode/skills/spark-recipe-priority-tuning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spark-recipe-priority-tuning", 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
spark-recipe-priority-tuning- GitHub stars
- 149
- Token cost
- ~699 tokens
- SKILL.md length
- 283 words
- Files
- 1
- Skills in repo
- 34
- Repo updated
- First seen
- Licence
- MIT
At a glance
Fine-tune Spark's priority category by marking key contacts as primary and adjusting notification importance.
- Works in 6 steps: Review current priority mail → Check who's currently marked as primary → Add missing VIPs → …
- SKILL.md covers Steps and Tips
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Spark Recipe Priority Tuning is an agent skill from readdle/spark-cli-skills. Fine-tune Spark's priority category by marking key contacts as primary and adjusting notification importance.
Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The licence is MIT.
Example prompts
- “/spark-recipe-priority-tuning”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit cb20383. 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 (its code samples are bash).
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
Spark Recipe Priority Tuning loads about 699 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 283 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 readdle/spark-cli-skills at commit cb20383, republished under its MIT licence (© readdle). 283 words, ~699 tokens.
Download SKILL.mdSave it as
.claude/skills/spark-recipe-priority-tuning/SKILL.md (or your agent's skills folder).- name
- spark-recipe-priority-tuning
- description
- Fine-tune Spark's priority category by marking key contacts as primary and adjusting notification importance.
- metadata.version
- 1.0.0
Recipe: Priority Tuning
Fine-tune who gets auto-prioritized by reviewing the current priority category and adjusting contact-level settings.
Prerequisite: Read the use-spark base skill for command reference and filter syntax.
Access level required: triage.
Steps
Step 1: Review current priority mail
spark emails Inbox --filter "category:priority newer_than:14d"Look at which senders appear in the priority category. Ask the user: are these the right people? Anyone missing? Anyone who shouldn't be here?
Step 2: Check who's currently marked as primary
Browse priority mail to identify the senders Spark is auto-prioritizing. Note any patterns - are important contacts missing, or are low-priority senders appearing?
Step 3: Add missing VIPs
For contacts whose emails should always be prioritized:
spark contact-action markContactAsPrimary vip@company.comThis tells Spark to auto-prioritize all future email from this sender.
Step 4: Remove false priorities
For contacts that are showing up in priority but shouldn't be:
spark contact-action unmarkContactAsPrimary noisy-sender@example.comStep 5: Adjust notification importance
For contacts where the user wants push notifications:
spark contact-action markContactAsImportant boss@company.comFor contacts that are priority but don't need notifications:
spark contact-action unmarkContactAsImportant low-urgency@example.comStep 6: Verify the changes
spark emails Inbox --filter "category:priority is:unread"Check that the priority category now reflects the user's preferences. New mail from adjusted contacts will appear in the correct category.
Tips
markContactAsPrimaryis the strongest signal - it guarantees the contact's emails land in priority.markContactAsImportantcontrols push notifications, which is separate from category placement.- Changes apply to all future mail from the contact, not retroactively to existing emails.
- Run this recipe after onboarding a new client, joining a new team, or changing roles - priority contacts change with context.
- When contacts are in the wrong category entirely (not just missing from priority), use
spark contact-action changeCategoryPersonal/changeCategoryNotification/changeCategoryNewslettersto reclassify all future mail from that sender. - A well-tuned priority category means the user can check just
category:priorityfor a reliable "must-read" view.
© readdle, 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 skills/recipe-priority-tuning of readdle/spark-cli-skills.
Open the folder on GitHubat commit cb20383
Compare with similar skills
Spark Recipe Priority Tuning 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 |
|---|---|---|---|---|---|---|
| Spark Recipe Priority Tuning this skillreaddle/spark-cli-skills | 149 | — | ~699 | 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 | |
| Peft Fine TuningOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Fine-Tuning ExpertJeffallan/claude-skills | 12k | — | ~1.7k | Automated safety check: Pass | MIT | |
| OpenVLA-OFT Fine-TuningOrchestra-Research/AI-Research-SKILLs | 13k | — | ~3.7k | 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.
Peft Fine Tuning
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
Fine-Tuning Expert
Jeffallan/claude-skills
Guides LLM fine-tuning with LoRA and QLoRA through Hugging Face PEFT, from dataset validation and training checks to adapter merging, quantization and deployment.
OpenVLA-OFT Fine-Tuning
Orchestra-Research/AI-Research-SKILLs
Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups.
OpenPI Fine-Tuning and Serving
Orchestra-Research/AI-Research-SKILLs
Fine-tunes and serves Physical Intelligence's pi0, pi0-fast and pi0.5 robot policies with JAX or PyTorch, including checkpoint conversion and policy servers.
More from readdle/spark-cli-skills
All 34 skills in this repoSpark Persona Exec Assistant
readdle/spark-cli-skills
Executive assistant persona for Spark. An agent skill from readdle/spark-cli-skills.
Spark Persona Founder
readdle/spark-cli-skills
Founder / CEO persona for Spark. An agent skill from readdle/spark-cli-skills.
Use Spark
readdle/spark-cli-skills
Use the spark CLI to access the user's Spark email data - list emails, search by topic, read threads, check calendar events, find availability, look up contacts, and view team info.
Spark Persona Freelancer
readdle/spark-cli-skills
Freelancer / solo operator persona for Spark. An agent skill from readdle/spark-cli-skills.
Spark Persona Meeting Manager
readdle/spark-cli-skills
Meeting manager persona for Spark. An agent skill from readdle/spark-cli-skills.
Spark Persona Project Manager
readdle/spark-cli-skills
Project manager persona for Spark. An agent skill from readdle/spark-cli-skills.
Questions about Spark Recipe Priority Tuning
What does Spark Recipe Priority Tuning do?
Fine-tune Spark's priority category by marking key contacts as primary and adjusting notification importance. Spark Recipe Priority Tuning is an agent skill from readdle/spark-cli-skills. Fine-tune Spark's priority category by marking key contacts as primary and adjusting notification importance.
How do I install Spark Recipe Priority Tuning in Claude Code?
Run `npx skills add readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a claude-code`. Or copy the skill folder (skills/recipe-priority-tuning in readdle/spark-cli-skills) into .claude/skills/spark-recipe-priority-tuning in your project. Claude Code loads it when a task matches its description.
How do I install Spark Recipe Priority Tuning in Codex?
Run `npx skills add readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a codex`. Or copy the skill folder (skills/recipe-priority-tuning in readdle/spark-cli-skills) into .agents/skills/spark-recipe-priority-tuning in your project. Codex loads it when a task matches its description.
Can I use Spark Recipe Priority Tuning 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 readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spark-recipe-priority-tuning, .gemini/skills/spark-recipe-priority-tuning, .github/skills/spark-recipe-priority-tuning and .opencode/skills/spark-recipe-priority-tuning in your project.
What does Spark Recipe Priority Tuning need to run?
SKILL.md names no scripts, command-line tools or credentials: Spark Recipe Priority Tuning is instructions for the agent only.
Does Spark Recipe Priority Tuning 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 Spark Recipe Priority Tuning 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 Spark Recipe Priority Tuning use?
Spark Recipe Priority Tuning 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 Spark Recipe Priority Tuning use?
About 699 tokens (SKILL.md is roughly 2.8k 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 Spark Recipe Priority Tuning?
Skills that share tags, products or a category with Spark Recipe Priority Tuning: LLM Fine Tuning (sickn33/agentic-awesome-skills, 47k stars), Fine Tuning With Trl (Orchestra-Research/AI-Research-SKILLs, 13k stars), Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Fine-Tuning Expert (Jeffallan/claude-skills, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Spark Recipe Priority Tuning?
readdle (a GitHub organization) maintains it in readdle/spark-cli-skills, which has 149 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on October 7, 2026.
Source: readdle/spark-cli-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.