demo-tests/procrastination-buster/SKILL.md
Beat procrastination with task breakdown, 2-minute starts, and accountability tracking
npx skillsauth add hidai25/eval-view procrastination-busterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Start today, finish stronger—powered by small momentum and honest tracking.
Procrastination-Buster breaks the cycle of avoidance by combining behavioral science with practical friction reduction:
Ask clawd: "Break down [task name] into 5 startable steps"
Ask clawd: "Give me a 2-minute start for [task]"
Ask clawd: "What's stopping me from starting [task]?"
Ask clawd: "Track my progress on [task]—check in tomorrow"
Ask clawd: "What did I finish this week?"
The 2-Minute Rule Start, don't finish. Commit to 2 minutes of the task. Momentum usually carries past the barrier. If it doesn't, you've still moved forward.
Pomodoro Starts Chain three 25-minute sprints with 5-minute breaks. After the first sprint, procrastination usually evaporates—the task becomes real.
Environment Design Remove friction from your space: close unneeded tabs, silence notifications, place materials within arm's reach. Friction is silent procrastination.
Future Self Letter Write a note to yourself after finishing: "I did this. Here's what I learned. Here's what to do next time." Future you reads it before the next task and starts stronger.
Break before you build - Spend 5 minutes outlining steps before starting. Clarity kills procrastination.
Track the start, not the finish - Win the hardest battle first. Starting is 80% of the work; finishing follows naturally.
Blockers are data - Avoid blaming willpower. Document what's actually stopping you (unclear deadline? fear of judgment? lack of skill?). Attack the real blocker.
Commit small, compound wins - "Finish by Friday" is abstract. "Work 25 minutes today" is doable. String five doable commits together and you're done.
All data stays local on your machine - Your task history, blockers, and commitments live on your device. No cloud sync, no tracking, just you and your persistence.
testing
Start EvalView watch mode to automatically re-run regression checks whenever project files change.
development
Run EvalView regression checks against golden baselines to detect regressions in AI agent behavior after code, prompt, or model changes.
testing
Generate EvalView test cases — either from a SKILL.md file using LLM-powered generation, or by capturing real agent interactions through a proxy.
development
A skill that helps review code for best practices, bugs, and security issues