agentleFS
JayRHaJayRHa/agent-skills/habit-builder/SKILL.md

habit-builder

Skill12 starsChanged 5 months agoMITView on GitHub

Designs a realistic, evidence-based plan to build a new habit or break a bad one — using cue-routine-reward loops, habit stacking, environment design, tiny starting steps, and relapse-proof tracking. Use this skill when a user asks to "help me build a habit", "stop a bad habit", "be more consistent", "create a morning/evening routine", "stick to X", or wants a system to make a behavior automatic.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this for everyday behavior change (exercise, reading, sleep, focus, screen time, diet habits).

    line 15
  2. Distinctive:

    Current context: when/where it would happen, what's blocking it, past attempts.

    line 20
  3. Distinctive:

    Relying on motivation/willpower: instead of designing the environment.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Habit Builder

Overview

This skill turns a vague intention ("I want to read more / stop doomscrolling") into a concrete behavior-change plan grounded in habit science — the cue→routine→reward loop, making good habits obvious/easy/attractive/satisfying and bad ones the opposite, habit stacking, environment design, and a tracking system that survives slip-ups.

Keywords: habit, routine, behavior change, consistency, habit stacking, atomic habits, morning routine, break a habit, accountability, streak, willpower, motivation.

When to use vs. not

Use this for everyday behavior change (exercise, reading, sleep, focus, screen time, diet habits). This is coaching, not clinical treatment — for addiction, self-harm, eating disorders, or compulsions causing real harm, recommend a qualified professional rather than a habit tracker.

Inputs to gather first

  1. The target behavior — specific and observable ("read 10 pages", not "be smarter").
  2. Build or break? And the why behind it (the identity/goal it serves).
  3. Current context: when/where it would happen, what's blocking it, past attempts.
  4. Existing routines to anchor onto (habit stacking).
  5. Realistic capacity — time, energy, competing demands.

Workflow

  1. Define the behavior tiny and specific. Shrink it until it's almost impossible to fail ("one push-up", "read one page"). Consistency first, scale later. The goal is to cast a vote for an identity ("I'm a reader"), not hit a number.
  2. Find the cue. Anchor the new habit to an existing one — habit stacking: "After I pour my morning coffee, I will write one sentence." Time + location + preceding action are the most reliable cues. See references/habit-loop.md.
  3. Design the environment. Make good habits obvious and easy (book on the pillow, gym clothes laid out) and bad habits invisible and hard (phone in another room, delete the app, unplug the TV). Environment beats willpower. See references/environment-design.md.
  4. Engineer the reward. Make it immediately satisfying — a tracker checkmark, a tiny celebration, pairing the habit with something enjoyable (temptation bundling). The brain repeats what feels good now.
  5. For breaking a habit, invert the loop. Make the cue invisible, the routine hard/unattractive, and remove the reward; replace the routine with a substitute that serves the same craving.
  6. Set up tracking + the never-miss-twice rule. A simple visual streak; missing once is fine, missing twice is the start of a new (bad) habit. Plan in advance for the obstacle that will break the streak (an if-then plan). See references/tracking.md.
  7. Schedule a review. Weekly check: did it happen? what got in the way? Adjust the cue, size, or environment — not your self-worth. Scale the habit up only once it's automatic.

Decision framework

SymptomFix
"I keep forgetting"Weak cue → habit-stack onto a rock-solid existing routine
"I don't have time"Habit too big → shrink to a 2-minute version
"I lose motivation"Relying on willpower → redesign environment + add immediate reward
"I start then quit"No recovery plan → adopt never-miss-twice + if-then plans
"I do it but it doesn't stick"No identity link → frame as "becoming the kind of person who…"

Worked example

See examples/morning-routine.md for a full plan to build a consistent morning routine, including the obstacle plan.

Best Practices

  • Start absurdly small. A habit you never skip beats an ambitious one you abandon.
  • Stack onto an existing habit for a reliable trigger.
  • Change the environment, not your willpower. Make the right thing the easy thing.
  • Never miss twice. One slip is noise; two is a trend.
  • Track visibly — streaks and checkmarks are their own reward.
  • Tie it to identity — "I'm a runner" sustains longer than "I should run."

Common Pitfalls

  • Going too big too fast and burning out in week one.
  • Relying on motivation/willpower instead of designing the environment.
  • No clear cue ("I'll do it when I have time" never happens).
  • All-or-nothing thinking — one miss spirals into quitting.
  • Stacking too many new habits at once — build one until automatic.
  • No reward — unrewarded behaviors don't repeat.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.