unlazy
Completion-discipline skill for long agent tasks: write the acceptance list first, run checks, re-verify returned work and report only what the evidence supports.
Test results
Run with our skill harness: the skill alone in a throwaway project, invoked by name, and the real output file checked. Skills are tested in Claude Code and Cursor only so far.
| Client | Result | Last passed | What we checked |
|---|---|---|---|
| Claude Code 2.1.296 (Claude Code) | Passed Tested 2026-10-26 | 2026-10-26 | unlazy: {'GATES.md written': True, 'gate has CHECK: + EXPECT:': True, 'hidden check (200,10)->180 (50,50)->25': True, 'token comment kept': True, 'gate checker used': True}; gates=GATES.md |
| Cursor 2026.10.22-27dcf5f | Passed Tested 2026-10-26 | 2026-10-26 | unlazy: {'GATES.md written': True, 'gate has CHECK: + EXPECT:': True, 'hidden check (200,10)->180 (50,50)->25': True, 'token comment kept': True, 'gate checker used': True}; gates=GATES.md |
Skill version: github.com/Leonxlnx/unlazy @ 16671491 (2026-09-03).
Get it
The skill’s files and install instructions are in its repository: github.com/Leonxlnx/unlazy.