spark-recipe-priority-tuning — Claude Code skill: setup guide
Calibrates Spark's priority inbox by assigning primary status to key contacts and tweaking notification flags via Spark CLI.
npx skills add readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a claude-code
npx skills add readdle/spark-cli-skills --skill recipe-priority-tuning -a claude-codeWhat spark-recipe-priority-tuning does
This skill provides a step-by-step workflow to audit and refine Spark's priority email category. The agent inspects senders from the last 14 days using spark emails Inbox --filter "category:priority newer_than:14d" to discover which addresses should stay prioritized and which ones should be excluded.
Contact adjustments run through commands like spark contact-action markContactAsPrimary for must-read senders and unmarkContactAsPrimary for noisy senders. Push alerts are managed separately with markContactAsImportant or unmarkContactAsImportant. Senders routed to incorrect categories can also be shifted to personal mail, newsletters, or notifications.
The recipe requires the use-spark skill and the triage access level. Category adjustments apply strictly to incoming future messages, so already received emails in your inbox will not change categories retroactively.
What it helps with
- remove low-priority senders from the priority inbox
- designate VIP contacts using
markContactAsPrimary - toggle push notification alerts per sender
- verify unread priority messages after updating rules
Example prompts for the agent
- Review my priority senders in Spark from the past two weeks
- Mark [email protected] as primary in Spark so their emails always stay in priority
- Turn off push notifications for [email protected] in Spark
How to install spark-recipe-priority-tuning
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill spark-recipe-priority-tuning -a claude-codenpx skills add readdle/spark-cli-skills --skill recipe-priority-tuning -a claude-code2Manually: put the files in place
~/.claude/skills/recipe-priority-tuning/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/recipe-priority-tuning/
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-priority-tuning -a codex2Manually: put the files in place
.agents/skills/recipe-priority-tuning/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-priority-tuning -a cursor2Manually: put the files in place
.cursor/skills/recipe-priority-tuning/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install readdle/spark-cli-skills recipe-priority-tuning2Manually: put the files in place
.github/skills/recipe-priority-tuning/SKILL.md1Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-priority-tuning -a gemini-cli2Platform CLI
gemini skills install https://github.com/readdle/spark-cli-skills --path skills/recipe-priority-tuningManually: put the files in place
.devin/skills/recipe-priority-tuning/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add readdle/spark-cli-skills --skill recipe-priority-tuning -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about spark-recipe-priority-tuning
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 in your terminal.
What does spark-recipe-priority-tuning do?
It guides the agent through inspecting recent priority emails, designating key contacts, and updating notification settings in Spark CLI.
Does updating a contact affect already received emails?
No, updates apply only to future incoming messages from that contact.
Source text
SKILL.md · MIT
---
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
requires:
skills:
- use-spark
accessLevel: triage
---
# 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
```bash
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:
```bash
spark contact-action markContactAsPrimary [email protected]
```
This 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:
```bash
spark contact-action unmarkContactAsPrimary [email protected]
```
### Step 5: Adjust notification importance
For contacts where the user wants push notifications:
```bash
spark contact-action markContactAsImportant [email protected]
```
For contacts that are priority but don't need notifications:
```bash
spark contact-action unmarkContactAsImportant [email protected]
```
### Step 6: Verify the changes
```bash
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
- `markContactAsPrimary` is the strongest signal - it guarantees the contact's emails land in priority.
- `markContactAsImportant` controls 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` / `changeCategoryNewsletters` to reclassify all future mail from that sender.
- A well-tuned priority category means the user can check just `category:priority` for a reliable "must-read" view.
© readdle · MIT · readdle/spark-cli-skills