ams-habit-tracker
暂无简介
- License 许可
- MIT
- 最近更新
- 2026-11-07
- Stars
- ★ 0
- Forks
- 1
03 SKILL.md 正文
Habit Tracker
Overview
Habits are behaviors on autopilot — the closest thing to free productivity.
Formation loop: cue -> routine -> reward. Tracking adds feedback: the checkmark becomes part of the reward.
Tracking alone doesn't build habits. The habit must be tiny, cue-linked, and rewarding enough to repeat.
Effective systems: 3-7 habits max, seconds-per-day tracking, misses treated as data not failure.
Design for your lowest-energy self. Motivation starts habits; systems sustain them.
When to use
- Starting new habits (exercise, reading, meditation, writing, languages)
- Breaking bad habits by replacing them with better ones
- Choosing a habit-tracking app or analog method
- Recovering after falling off a routine
- Designing team or family habit challenges
Core concepts
- Start ridiculously small. 'Read 2 pages' sticks; 'read 20 pages' fails. Initial goal is showing up, not output. Scale after the identity forms.
- Habit stacking. Attach to an existing habit: 'After coffee, I journal.' Existing habits are the most reliable cues available.
- Implementation intentions. 'I will [behavior] at [time] in [location].' Specificity beats motivation. 'Walk 15 min at 7am' works; 'exercise more' doesn't.
- Environment design. Good habits obvious (shoes by door), bad habits hard (phone in another room). Willpower is unreliable; friction is forever.
- Never miss twice. One miss is an accident; two is a new habit of skipping. After a slip, resume immediately — never 'restart Monday.'
- Identity over outcomes. 'I'm a reader' outlasts 'lose 5kg.' Each completion is a vote for the identity. Track the votes.
- Track, don't judge. The tracker is a dashboard, not a courtroom. Gaps reveal obstacles to design around, not failures to feel bad about.
- Minimum viable version. Define the bad-day version of each habit explicitly. The 2-minute version keeps the streak of showing up alive.
Practical workflow
- Choose 3-5 habits max. Fewer than you want. Each under 10 minutes initially, with a 2-minute starter version for bad days.
- Write implementation intentions. Exact behavior, cue, time, place — plus the minimum version. Vague plans produce vague results.
- Pick a tracking method. App, spreadsheet, wall calendar, notebook grid. Under 10 seconds per habit per day, visible, satisfying to mark.
- Design the environment first. Change one thing per habit before day one: reduce friction or add a cue. Don't wait to fail first.
- Set a weekly review. Which habits are automatic? Which need redesign (size, cue, time) rather than more willpower? Adjust the system.
- Handle slips by protocol. Miss once: note cause, resume tomorrow. Miss twice: shrink the habit or change the cue immediately.
- Evolve quarterly. Graduate easy habits, retire automatic ones from active tracking, add one new habit at a time. Keep the list short forever.
- Pair habits with rewards. After the routine, something genuinely pleasant — even just marking the X. The loop needs its reward to close.
Common pitfalls
- Too many habits at once. Ten new habits in January, zero by February. One at a time is faster long-term because it survives.
- All-or-nothing tracking. Binary pass/fail punishes the 20-minute walk that was still worthwhile. Partial credit keeps showing up alive.
- Tracking without design. Logging failures for months without changing cue, size, or environment. Data without redesign is a guilt log.
- Streak obsession. A broken 100-day streak can end the habit ('it's ruined'). Value the 90%-of-days trend over the unbroken chain.
- Vague habits. 'Be healthier' can't be tracked. 'No soda on weekdays' can. No checkmark possible = not a habit yet.
- Relying on motivation. Design every habit for your busiest, most distracted, lowest-energy self — that's who has to do it.
- Punishing rest. 7-days-a-week with no recovery leads to burnout and abandonment. Schedule rest days deliberately.
- Copying someone's stack. Borrow principles, not schedules. Build from your life, chronotype, and constraints — not an influencer's routine.
04 同仓库更多 Skills
web-scrape
Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open/fetch fails on JS-heavy pages, or when you need clean markdown/structured extraction from a site. Requires FIRECRAWL_API_KEY.
design-taste-frontend
tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML/CSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, "AI-made", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).