Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Execute structured task plans with status tracking. Use when the user provides a plan file path in the format `plans/{current-date}-{task-name}-{version}.md` or explicitly asks you to execute a plan file.
.claude/skills/microck-execute-plan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 330% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 23% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | -39% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 31% | 0% |
Execute structured task plans with automatic status tracking and progress updates.
When a plan is provided, all tasks in the plan must be completed. Before starting execution, recite:
> "I will execute this plan to completion. All the 20 tasks will be addressed and marked as DONE."
STEP 1: Recite the commitment to complete all tasks in the plan.
STEP 2: Read the entire plan file to identify pending tasks based on task_status.
STEP 3: Announce the next pending task and update its status to IN_PROGRESS in the plan file.
STEP 4: Execute all actions required to complete the task and mark the task status to DONE in the plan file.
STEP 5: Repeat from Step 3 until all tasks are marked as DONE.
STEP 6: Re-read the plan file to verify all tasks are completed before announcing completion.
Use these status indicators in the plan file:
[ ]: PENDING
[~]: IN_PROGRESS
[x]: DONE
[!]: FAILED[ ] (PENDING) task[~] (IN_PROGRESS)[x] (DONE)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,604 | 2,652 | -42% | 1 | 1 | 0% | 217 | 679 | +213% | 0 | 0 | — |
case-02 | fail→fail | 5,864 | 3,235 | -45% | 1 | 1 | 0% | 339 | 794 | +134% | 0 | 0 | — |
case-03 | fail→fail | 5,317 | 3,398 | -36% | 1 | 1 | 0% | 232 | 886 | +282% | 0 | 0 | — |
case-04 | pass→pass | 3,089 | 1,420 | -54% | 1 | 1 | 0% | 453 | 557 | +23% | 0 | 0 | — |
case-05 | pass→pass | 6,443 | 1,626 | -75% | 1 | 1 | 0% | 990 | 605 | -39% | 0 | 0 | — |
case-06 | pass→pass | 2,855 | 1,613 | -44% | 1 | 1 | 0% | 453 | 594 | +31% | 0 | 0 | — |
case-07 | pass→pass | 8,819 | 1,455 | -84% | 1 | 1 | 0% | 1,496 | 562 | -62% | 0 | 0 | — |
case-08 | pass→pass | 7,540 | 2,511 | -67% | 1 | 1 | 0% | 1,220 | 838 | -31% | 0 | 0 | — |
case-09 | pass→pass | 2,405 | 3,653 | +52% | 1 | 1 | 0% | 367 | 1,022 | +178% | 0 | 0 | — |
case-10 | pass→pass | 3,399 | 2,812 | -17% | 1 | 1 | 0% | 484 | 858 | +77% | 0 | 0 | — |
case-11 | pass→pass | 5,281 | 3,288 | -38% | 1 | 1 | 0% | 799 | 982 | +23% | 0 | 0 | — |
case-12 | fail→fail | 4,659 | 1,721 | -63% | 1 | 1 | 0% | 707 | 672 | -5% | 0 | 0 | — |
case-13 | pass→pass | 6,544 | 1,615 | -75% | 1 | 1 | 0% | 908 | 685 | -25% | 0 | 0 | — |
case-14 | pass→pass | 4,608 | 3,497 | -24% | 1 | 1 | 0% | 658 | 997 | +52% | 0 | 0 | — |
case-15 | pass→pass | 4,770 | 6,454 | +35% | 1 | 1 | 0% | 658 | 1,434 | +118% | 0 | 0 | — |
case-16 | fail→pass | 10,620 | 3,772 | -64% | 1 | 1 | 0% | 1,678 | 1,003 | -40% | 0 | 0 | — |
case-17 | pass→pass | 8,912 | 3,289 | -63% | 1 | 1 | 0% | 1,488 | 895 | -40% | 0 | 0 | — |
case-18 | pass→pass | 7,125 | 2,783 | -61% | 1 | 1 | 0% | 1,079 | 795 | -26% | 0 | 0 | — |
case-19 | pass→pass | 8,150 | 3,367 | -59% | 1 | 1 | 0% | 1,297 | 938 | -28% | 0 | 0 | — |
case-20 | pass→pass | 11,646 | 11,731 | +1% | 1 | 1 | 0% | 1,909 | 2,327 | +22% | 0 | 0 | — |
case-21 | fail→fail | 5,892 | 5,470 | -7% | 1 | 1 | 0% | 396 | 710 | +79% | 0 | 0 | — |
case-22 | fail→pass | 4,925 | 15,678 | +218% | 1 | 1 | 0% | 817 | 3,510 | +330% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 19 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.