Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Budget Checkin

ASecurity

Run a monthly money check-in with an AI assistant: categorize spending, spot leaks, set one savings target, and view it through the 50/30/20 lens — judgment-free. Use once a month to stay aware of where your money goes. General educational information, not financial advice.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill budget-checkin --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Budget Checkin?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Budget Checkin
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-budget-checkin/badge)](https://www.skillsdirectory.com/skills/aicodedecode-budget-checkin)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: budget-checkin
description: Run a monthly money check-in with an AI assistant: categorize spending, spot leaks, set one savings target, and view it through the 50/30/20 lens — judgment-free. Use once a month to stay aware of where your money goes. General educational information, not financial advice.
category: everyday-assistant
---

# Budget Check-in

## Overview

A monthly money check-in is a 30-minute conversation with yourself, mediated by your assistant. No
spreadsheets to build, no guilt trips — just a regular look at where your money went last month and
one small decision about next month. The ritual matters more than the math: people who check monthly
almost always spend more intentionally than people who never look.

This skill gives you a repeatable monthly routine. You'll bring your spending data (however rough),
the assistant helps you categorize it, spot patterns, and set a single savings target. It's
deliberately gentle: the point is awareness, not austerity. One check-in won't change your finances.
Twelve will.

## When to use

- The first week of a new month, reviewing the month that just ended
- When money feels tight but you're not sure why
- Before a big expense or life change (moving, a trip, a job switch)
- When you want to start saving but don't know what's realistic
- Quarterly or yearly, as a deeper review of the trend across check-ins

## Core concepts

- **Awareness beats optimization.** You don't need the perfect budgeting method. You need to regularly
  look at real numbers. Most "leaks" are found in the first honest look, not the tenth refinement.
- **Categories should match your life.** Rent, groceries, eating out, transport, subscriptions, fun
  money — pick 6–10 categories that reflect how you actually spend. Too many categories and you'll
  quit; too few and everything hides in "miscellaneous."
- **The 50/30/20 lens is a mirror, not a rule.** Roughly 50% needs, 30% wants, 20% savings is a way to
  *see* your spending shape, not a law to obey. If your rent alone eats 50%, that's information about
  your city, not a personal failure.
- **One target at a time.** "Save more" fails. "Move ₹5,000 to savings on the 5th of each month"
  works. A check-in that produces one concrete decision beats one that produces ten intentions.
- **Judgment-free is a method, not a mood.** Shame makes people avoid looking, and avoidance is the
  actual enemy. Treat surprises in the data as interesting findings, not confessions.

## Practical workflow

Once a month, open a conversation with your numbers. You don't need perfect data — bank/UPI
statements, a notes app, or even rough recall works:

*"Here's my spending for September: rent ₹18,000, groceries ₹9,000, eating out ₹6,500, transport
₹3,000, subscriptions ₹1,200, shopping ₹4,000, and about ₹5,000 I can't account for. My take-home is
₹52,000. Help me do my monthly check-in."*

Then walk through the ritual:

1. **Categorize and total.** *"Sort this into needs, wants, and savings. Show me the totals and what
   percentage each is."* The assistant does the arithmetic; you do the noticing.
2. **Spot the leaks.** *"What stands out? Flag anything that looks high or grew compared to last
   month."* Eating out and subscriptions are the usual suspects — but let the data speak before you
   assume.
3. **Apply the 50/30/20 lens.** *"How does my spending compare to the 50/30/20 shape? Don't lecture me
   — just show me where I land."* If your shape is wildly different, ask *why* before asking *how to
   fix it*. High rent in an expensive city is a structural fact, not a leak.
4. **Set one target.** *"Based on this, suggest one realistic savings target for next month — specific
   amount, specific date."* Make it automatic if you can: a standing transfer beats willpower every
   time.
5. **Close the loop.** *"Summarize this check-in in five lines: total spent, biggest category, one
   surprise, the savings target, and one thing to watch next month."* Save the summary. Next month's
   check-in starts by re-reading it.

Everything here is general educational information about personal money management, not professional
financial advice. For investment decisions, debt strategy, tax planning, or anything with real
stakes, talk to a licensed financial advisor.

## Common pitfalls

- **Checking once and never again.** A single check-in is a snapshot; the value is in the series. Put
  a monthly reminder on your calendar for the 1st or 2nd.
- **Demanding perfect data.** "I don't have exact numbers" is how people postpone forever. Rough
  numbers checked monthly beat precise numbers checked never.
- **Setting five targets.** One target you actually hit builds the muscle. Five targets you miss
  builds the story that "budgeting doesn't work for me."
- **Treating wants as moral failures.** The 30% exists because a life with zero fun money is a life
  you'll abandon the plan to live. Budget the fun; don't banish it.
- **Comparing yourself to benchmarks.** The 50/30/20 split is a starting lens, not a grade. Your city,
  your income, your life stage — context always wins over ratios.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →