Agent skill

Spark Recipe Unsubscribe Audit

by readdle in readdle/spark-cli-skills

Full unsubscribe audit: scan inbox, archive, and GateKeeper for newsletter senders, classify by volume and engagement, detect phishing and duplicate subscriptions, then unsubscribe via spark action…

MITAuto-check passedWriting & Content

Install Spark Recipe Unsubscribe Audit

skills CLI
$ npx skills add readdle/spark-cli-skills --skill spark-recipe-unsubscribe-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install readdle/spark-cli-skills spark-recipe-unsubscribe-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/readdle/spark-cli-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/recipe-unsubscribe-audit .claude/skills/spark-recipe-unsubscribe-audit && rm -rf skills-src

Use ~/.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/

Facts

Skill name
spark-recipe-unsubscribe-audit
GitHub stars
149
Token cost
~1.4k tokens
SKILL.md length
571 words
Files
1
Skills in repo
34
Repo updated
First seen
Licence
MIT

At a glance

Full unsubscribe audit: scan inbox, archive, and GateKeeper for newsletter senders, classify by volume and engagement, detect phishing and duplicate subscriptions, then unsubscribe via spark action…

  • Works in 6 steps: Scan all three pools → Aggregate and classify → Verify duplicate copies before acting → …
  • Tasks that involve Newsletters
  • SKILL.md covers Steps and Tips
  • Reaches substack.com

What it does

Spark Recipe Unsubscribe Audit is an agent skill from readdle/spark-cli-skills. Full unsubscribe audit: scan inbox, archive, and GateKeeper for newsletter senders, classify by volume and engagement, detect phishing and duplicate subscriptions, then unsubscribe via spark action or extracted footer links.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Newsletters and Email management. The licence is MIT.

When your agent uses it

  • Tasks that involve Newsletters
  • Tasks that involve Email management

Example prompts

  • “/spark-recipe-unsubscribe-audit”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Scan all three pools
  2. Aggregate and classify
  3. Verify duplicate copies before acting
  4. Unsubscribe approved senders
  5. Tame the keepers
  6. Report

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

    Hosts in commands or code, which the agent is likely to contact:

    • substack.com

    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 Unsubscribe Audit loads about 1.4k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 571 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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). 571 words, ~1,399 tokens.

Download SKILL.mdSave it as .claude/skills/spark-recipe-unsubscribe-audit/SKILL.md (or your agent's skills folder).
name
spark-recipe-unsubscribe-audit
description
Full unsubscribe audit: scan inbox, archive, and GateKeeper for newsletter senders, classify by volume and engagement, detect phishing and duplicate subscriptions, then unsubscribe via spark action or extracted footer links.
metadata.version
1.0.0

Recipe: Unsubscribe Audit

Audit every newsletter pool, recommend unsubscribe candidates backed by engagement data, and execute only after the user approves the list. Spark supplies the data (senders, volumes, read flags, bodies); the agent owns classification, duplicate verification, and execution.

Prerequisite: Read the use-spark base skill for command reference and filter syntax.

Access level required: triage.

Steps

Step 1: Scan all three pools

An inbox-only scan misses most of the volume. Check all three:

bash
# Unified inbox, all accounts (paginate to get everything)
spark emails Inbox --filter "category:newsletter newer_than:30d" --page-size 100

# Auto-archived mail — Gmail filters/automations often skip the inbox
# entirely; repeat per Gmail-backed account. This pool can be the largest.
spark emails "user@gmail.com:Archive" --filter "category:newsletter newer_than:14d" --page-size 100

# GateKeeper queue — new senders held outside the inbox view
spark emails Inbox --new-senders --page-size 50
Step 2: Aggregate and classify

Count per sender: emails per 30 days and unread rate (from the Flags column). Classify into tiers:

TierSignalAction
UnsubscribePure marketing/drip, ~100% unreadRecommend removal
ConsiderHigh volume, partial engagementUser's call; suggest digest or auto-summary
KeepMostly readLeave alone
TransactionalInvoices, PINs, order/security noticesExclude from the audit
PhishingSee belowMark as spam — NEVER unsubscribe
App-nagInstagram/LinkedIn-style notification mailFix in the app's notification settings

Phishing tripwire: brand name in the display name but an unrelated sender domain (e.g. "SpotifyUS" from mail@jhbuilder.com), urgent billing/security subjects. Clicking anything — including unsubscribe — confirms the address is live. Flag prominently; recommend mark-as-spam instead. The same applies to everything already in the Spam folder: never unsubscribe there.

Present the classification and wait for the user to confirm or amend the list before acting. Expect them to rescue a few senders.

Step 3: Verify duplicate copies before acting

When the same newsletter arrives 2+ times, do NOT assume two subscriptions:

  1. Compare To: headers of the copies via spark thread <id>. Different addresses → genuinely separate subscriptions; unsubscribe the unwanted copy using the link from that specific copy (tokens are per-subscription).
  2. Substack: decode the https://substack.com/redirect/2/<base64url-JSON> unsubscribe link; the payload's u field is the subscription ID. Same u in both copies → one subscription delivered twice (alias/forward). Unsubscribing kills it entirely — report instead of acting.
  3. Same To:, same account (e.g. Patreon) → same situation; skip and report.
Show full SKILL.md (258 more words)Show less
Step 4: Unsubscribe approved senders

For each approved sender, try Spark's built-in mechanism first:

bash
spark action unsubscribe <id>

If the command is unavailable in the installed CLI version or the sender has no List-Unsubscribe mechanism, fall back to footer-link extraction:

bash
spark thread <id> > /tmp/unsub/<id>.txt
grep -i -o 'https://[^][ )(>"<]*' /tmp/unsub/<id>.txt | grep -i 'unsub\|optout\|opt-out\|preference\|darse de baja'

Then complete each link in a browser (agent-driven browser automation or hand the list to the user). Browser rules: one-click confirmations are common; preference centers need "unsubscribe from all marketing" + save; never type personal data (pre-filled email fields are fine); login walls, captchas, and errors → record as blocked and move on. Footers vary by language and ESP — if the pattern misses, read the last ~25 lines of the body and pick the actual unsubscribe link, not adjacent tracking links.

For senders that should be blocked entirely (cold outreach, spam-adjacent):

bash
spark contact-action blockContact spammer@example.com
spark contact-action blockDomain example.com
Step 5: Tame the keepers

For high-volume senders the user keeps:

bash
spark contact-action enableAutosummaryForContact newsletter@example.com
spark contact-action groupEmailsFromContact sender@example.com
Step 6: Report

Summarize: senders removed, emails/month saved, blocked items with manual next steps, app-nag senders to fix in-app, phishing marked as spam, and duplicates that need account-level fixes (e.g. Substack account settings, forwarding rules).

Tips

  • Engagement data makes recommendations credible: "30 emails/month, 100% unread" beats "looks like marketing".
  • Shell loops abort on a failing grep — dump pages to temp files first, parse second, and append || true.
  • Click-tracker redirect links (SendGrid, Braze, e.zoom.us, klclick, webengage) are fine — the browser follows them to the real unsubscribe page.
  • Sendy footers contain both /l/... (tracking) and /unsubscribe/... links — pick the latter.
  • unsubscribe via the mailing list's own mechanism is cleaner than blocking; reserve blockContact/blockDomain for senders that ignore unsubscribes.
  • Run this recipe quarterly; subscriptions regrow.

© 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-unsubscribe-audit of readdle/spark-cli-skills.

Open the folder on GitHubat commit cb20383

Compare with similar skills

Spark Recipe Unsubscribe Audit 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.

Spark Recipe Unsubscribe Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Spark Recipe Unsubscribe Audit this skillreaddle/spark-cli-skills149—~1.4kAutomated safety check: PassMIT
Gog Weekly Digestopenclaw/gogcli8.5k—~264Automated safety check: PassMIT
Agent Supply Chain NewsletterDataDog/datadog-agent3.8k—~1.2kAutomated safety check: PassApache-2.0
Newsletter Monitorgooseworks-ai/goose-skills1.2k1 repos~701Automated safety check: PassMIT
Email And Newslettersocial-media-skills/skills134—~1.5kAutomated safety check: PassMIT
Loop Covercharlie947/motion-graphics-skills180—~939Automated safety check: PassMIT

Similar skills

  • Gog Weekly Digest

    openclaw/gogcli

    Read-only weekly digest across Google Calendar, Gmail, and Tasks with gog.

    8.5k GitHub stars~264 tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Agent Supply Chain Newsletter

    DataDog/datadog-agent

    Official

    Generate the Agent Supply Chain newsletter by researching team activity on GitHub and Confluence, then creating a Confluence draft and Gmail draft

    3.8k GitHub stars~1.2k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Newsletter Monitor

    gooseworks-ai/goose-skills

    Scan an AgentMail inbox for newsletter signals using configurable keyword campaigns.

    1.2k GitHub starsUsed in 1 repo~701 tokens
    Writing & ContentAuto-check passed
  • Email And Newsletter

    social-media-skills/skills

    Email and newsletter strategy for creators and brands — the owned-audience layer that social feeds.

    134 GitHub stars~1.5k tokensUpdated 9 days ago
    Writing & ContentAuto-check passed
  • Loop Cover

    charlie947/motion-graphics-skills

    Turn a newsletter or blog cover into a seamless looping GIF at 896 x 640, 180 frames at 20fps.

    180 GitHub stars~939 tokensUpdated today
    Media & CreativeAuto-check passed
  • Triage Superhuman Inbox

    superset-sh/superset

    Work through a Superhuman inbox — sort what is there into needs a reply, waiting on someone else, worth knowing, and noise, then archive, star, label, remind, or unsubscribe only as the user directs.

    15k GitHub stars~1.2k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from readdle/spark-cli-skills

All 34 skills in this repo
  • Spark Persona Exec Assistant

    readdle/spark-cli-skills

    Executive assistant persona for Spark. An agent skill from readdle/spark-cli-skills.

    149 GitHub stars~775 tokensUpdated 4 days ago
    Auto-check passed
  • Spark Persona Founder

    readdle/spark-cli-skills

    Founder / CEO persona for Spark. An agent skill from readdle/spark-cli-skills.

    149 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed
  • 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.

    149 GitHub stars~14k tokensUpdated 4 days ago
    Auto-check: warnings
  • Spark Persona Freelancer

    readdle/spark-cli-skills

    Freelancer / solo operator persona for Spark. An agent skill from readdle/spark-cli-skills.

    149 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed
  • Spark Persona Meeting Manager

    readdle/spark-cli-skills

    Meeting manager persona for Spark. An agent skill from readdle/spark-cli-skills.

    149 GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed
  • Spark Persona Project Manager

    readdle/spark-cli-skills

    Project manager persona for Spark. An agent skill from readdle/spark-cli-skills.

    149 GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check passed

Questions about Spark Recipe Unsubscribe Audit

What does Spark Recipe Unsubscribe Audit do?

Full unsubscribe audit: scan inbox, archive, and GateKeeper for newsletter senders, classify by volume and engagement, detect phishing and duplicate subscriptions, then unsubscribe via spark action…. Spark Recipe Unsubscribe Audit is an agent skill from readdle/spark-cli-skills. Full unsubscribe audit: scan inbox, archive, and GateKeeper for newsletter senders, classify by volume and engagement, detect phishing and duplicate subscriptions, then unsubscribe via spark action or extracted footer links.

When should I use Spark Recipe Unsubscribe Audit?

Spark Recipe Unsubscribe Audit fits situations like: tasks that involve Newsletters; tasks that involve Email management.

How do I install Spark Recipe Unsubscribe Audit in Claude Code?

Run `npx skills add readdle/spark-cli-skills --skill spark-recipe-unsubscribe-audit -a claude-code`. Or copy the skill folder (skills/recipe-unsubscribe-audit in readdle/spark-cli-skills) into .claude/skills/spark-recipe-unsubscribe-audit in your project. Claude Code loads it when a task matches its description.

How do I install Spark Recipe Unsubscribe Audit in Codex?

Run `npx skills add readdle/spark-cli-skills --skill spark-recipe-unsubscribe-audit -a codex`. Or copy the skill folder (skills/recipe-unsubscribe-audit in readdle/spark-cli-skills) into .agents/skills/spark-recipe-unsubscribe-audit in your project. Codex loads it when a task matches its description.

Can I use Spark Recipe Unsubscribe Audit 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-unsubscribe-audit -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-unsubscribe-audit, .gemini/skills/spark-recipe-unsubscribe-audit, .github/skills/spark-recipe-unsubscribe-audit and .opencode/skills/spark-recipe-unsubscribe-audit in your project.

What does Spark Recipe Unsubscribe Audit need to run?

SKILL.md names no scripts, command-line tools or credentials: Spark Recipe Unsubscribe Audit is instructions for the agent only.

Does Spark Recipe Unsubscribe Audit access the network?

SKILL.md names 1 domain. In commands or code: substack.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Spark Recipe Unsubscribe Audit 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 Unsubscribe Audit use?

Spark Recipe Unsubscribe Audit 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 Unsubscribe Audit use?

About 1.4k tokens (SKILL.md is roughly 5.6k 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 Unsubscribe Audit?

Skills that share tags, products or a category with Spark Recipe Unsubscribe Audit: Gog Weekly Digest (openclaw/gogcli, 8.5k stars), Agent Supply Chain Newsletter (DataDog/datadog-agent, 3.8k stars), Newsletter Monitor (gooseworks-ai/goose-skills, 1.2k stars) and Email And Newsletter (social-media-skills/skills, 134 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Spark Recipe Unsubscribe Audit?

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.