just-fucking-cancel
Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and helps you cancel with direct URLs and browser automation. Use when: 'cancel subscriptions', 'audit subscriptions', 'find recurring charges', 'what am I paying for', 'save money', 'subscription cleanup', 'stop wasting money'. Supports CSV import (Apple Card, Chase, Amex, Citi, Bank of America, Capital One, Mint, Copilot) OR Plaid API for automatic transaction pull. Outputs interactive HTML audit with one-click cancel workflow. Pairs with Plaid integration for real-time transaction access without CSV exports.
Best use case
just-fucking-cancel is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and helps you cancel with direct URLs and browser automation. Use when: 'cancel subscriptions', 'audit subscriptions', 'find recurring charges', 'what am I paying for', 'save money', 'subscription cleanup', 'stop wasting money'. Supports CSV import (Apple Card, Chase, Amex, Citi, Bank of America, Capital One, Mint, Copilot) OR Plaid API for automatic transaction pull. Outputs interactive HTML audit with one-click cancel workflow. Pairs with Plaid integration for real-time transaction access without CSV exports.
Teams using just-fucking-cancel should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/just-fucking-cancel/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How just-fucking-cancel Compares
| Feature / Agent | just-fucking-cancel | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and helps you cancel with direct URLs and browser automation. Use when: 'cancel subscriptions', 'audit subscriptions', 'find recurring charges', 'what am I paying for', 'save money', 'subscription cleanup', 'stop wasting money'. Supports CSV import (Apple Card, Chase, Amex, Citi, Bank of America, Capital One, Mint, Copilot) OR Plaid API for automatic transaction pull. Outputs interactive HTML audit with one-click cancel workflow. Pairs with Plaid integration for real-time transaction access without CSV exports.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# just-fucking-cancel Analyze transactions, categorize subscriptions, generate HTML audit, help cancel. ## Triggers - "cancel subscriptions", "audit subscriptions" - "find recurring charges", "what am I paying for" - "subscription audit", "clean up subscriptions" ## Workflow ### 1. Get Transactions **Option A: Plaid API (recommended — no CSV needed)** If the user has Plaid connected (check for Plaid integration/API access): 1. Pull last 6-12 months of transactions via Plaid Transactions API 2. All accounts are automatically included — no manual export needed 3. Skip straight to Step 2 **Option B: CSV Upload** Ask user for bank/card CSV export. Common sources: - Apple Card: Wallet → Card Balance → Export - Chase: Accounts → Download activity → CSV - Amex: Statements & Activity → Download → CSV - Citi: Account Details → Download Transactions - Bank of America: Activity → Download → CSV - Capital One: Transactions → Download - Mint / Copilot: Transactions → Export ### 2. Analyze Recurring Charges Read CSV, identify recurring patterns: - Same merchant, similar amounts, monthly/annual frequency - Flag subscription-like charges (streaming, SaaS, memberships) - Note charge frequency and total annual cost ### 3. Categorize with User For each subscription, ask user to categorize: - **Cancel** - Stop immediately - **Investigate** - Needs decision (unsure, trapped in contract) - **Keep** - Intentional, continue paying Ask in batches of 5-10 to avoid overwhelming. ### 4. Generate HTML Audit Copy [template.html](assets/template.html) and populate: - Update header summary: - Scope line: "found N subscriptions · N transactions" - Breakdown: "Cancelled N · Keeping N" - Savings: yearly amount big, monthly in parentheses - Timestamp: current date - Add rows to appropriate sections (cancelled/investigate/keep) - Include notes from user responses Row templates in the HTML comments show the structure. ### 5. Cancel Subscriptions When user checks items and copies from floating button, they'll paste: `Cancel these: Service1 ($XX), Service2 ($XX)...` For each service: 1. Check [common-services.md](references/common-services.md) for cancel URL 2. Use browser automation to navigate and cancel 3. Update HTML row to cancelled status with date ## HTML Structure Three sections, auto-hide when empty: - **Cancelled** (green badge, strikethrough) - Done items, the win - **Needs Decision** (orange badge) - Has checkboxes for cancel selection - **Keeping** (grey badge) - No checkboxes, just reference Features: - Floating copy button appears when items checked - Privacy toggle blurs service names - Collapsible sections via header click - Dark mode support ## Cancellation Tips For difficult services, see [common-services.md](references/common-services.md): - Direct cancel URLs for 50+ services - Dark pattern warnings (gym contracts, phone-only) - Retention script responses - Credit card dispute backup ## Privacy All data stays local. Transaction CSVs are analyzed in-session only.
Related Skills
portfolio-watcher
Monitor stock/crypto holdings, get price alerts, track portfolio performance
portainer
Control Docker containers and stacks via Portainer API. List containers, start/stop/restart, view logs, and redeploy stacks from git.
portable-tools
Build cross-device tools without hardcoding paths or account names
polymarket
Trade prediction markets on Polymarket. Analyze odds, place bets, track positions, automate alerts, and maximize returns from event outcomes. Covers sports, politics, entertainment, and more.
polymarket-traiding-bot
No description provided.
polymarket-analysis
Analyze Polymarket prediction markets for trading edges. Pair Cost arbitrage, whale tracking, sentiment analysis, momentum signals, user profile tracking. No execution.
polymarket-agent
Autonomous prediction market agent - analyzes markets, researches news, and identifies trading opportunities
polymarket-5
Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data.
polymarket-4
Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data.
polymarket-3
Query Polymarket prediction market odds and events via CLI. Search for markets, get current prices, list events by category. Supports sports betting (NFL, NBA, soccer/EPL, Champions League), politics, crypto, elections, geopolitics. Real money markets = more accurate than polls. No API key required. Use when asked about odds, probabilities, predictions, or "what are the chances of X".
polymarket-2
Query Polymarket prediction markets - check odds, trending markets, search events, track prices.
pollinations
Pollinations.ai API for AI generation - text, images, videos, audio, and analysis. Use when user requests AI-powered generation (text completion, images, videos, audio, vision/analysis, transcription) or mentions Pollinations. Supports 25+ models (OpenAI, Claude, Gemini, Flux, Veo, etc.) with OpenAI-compatible chat endpoint and specialized generation endpoints.