Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create structured plans for multi-task projects that can be used by the task-orchestrator skill. Use when breaking down complex work into parallel and sequential tasks with dependencies.
.claude/skills/jdrhyne-planner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -18% | 0% |
Create structured, orchestrator-ready plans for multi-task projects.
Source: Adapted from am-will's codex-skills workflow patterns Pairs with: task-orchestrator skill for follow-on implementation
Follow this process:
Each task must be:
❌ Bad: "Implement third-party sign-in"
✓ Good:
Each sprint must:
markdown# Plan: [Task Name] **Generated**: [Date] **Estimated Complexity**: [Low/Medium/High] ## Overview [Brief summary of what needs to be done and the general approach] ## Prerequisites - [Dependencies or requirements that must be met first] - [Tools, libraries, or access needed] - [Tooling limitations, e.g., browser relay/CDP restrictions] ## Sprint 1: [Sprint Name] **Goal**: [What this sprint accomplishes] **Demo/Validation**: - [How to run/demo this sprint's output] - [What to verify] ### Task 1.1: [Task Name] - **Location**: [File paths or components involved] - **Description**: [What needs to be done] - **Perceived Complexity**: [1-10] - **Dependencies**: [Any previous tasks this depends on] - **Acceptance Criteria**: - [Specific, testable criteria] - **Validation**: - [Test(s) or alternate validation steps] ### Task 1.2: [Task Name] [...] ## Sprint 2: [Sprint Name] [...] ## Testing Strategy - [How to test the implementation] - [What to verify at each sprint] ## Potential Risks - [Things that could go wrong] - [Mitigation strategies] ## Rollback Plan - [How to undo changes if needed]
Once plan is ready, hand off to the parallel-task worker:
Please run parallel-task.md against my-plan.mdOr invoke directly: > "Run all unblocked tasks in plan.md using parallel subagents. Keep looping until all tasks are complete."
parallel-task — Parallel task worker that executes the plan this skill producesAdapted from am-will's codex-skills planner/parallel-task prompts.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | pass→pass | 13,112 | 11,600 | -12% | 1 | 1 | 0% | 2,179 | 2,774 | +27% | 0 | 0 | — |
case-01 | fail→pass | 21,158 | 25,663 | +21% | 1 | 1 | 0% | 3,649 | 5,461 | +50% | 0 | 0 | — |
case-02 | fail→pass | 33,140 | 30,091 | -9% | 1 | 1 | 0% | 6,196 | 6,133 | -1% | 0 | 0 | — |
case-03 | fail→fail | 30,278 | 26,568 | -12% | 1 | 1 | 0% | 5,563 | 5,552 | -0% | 0 | 0 | — |
case-04 | pass→pass | 13,619 | 15,570 | +14% | 1 | 1 | 0% | 2,849 | 4,022 | +41% | 0 | 0 | — |
case-05 | pass→pass | 3,923 | 7,273 | +85% | 1 | 1 | 0% | 214 | 1,333 | +523% | 0 | 0 | — |
case-06 | pass→pass | 9,013 | 7,352 | -18% | 1 | 1 | 0% | 1,349 | 1,935 | +43% | 0 | 0 | — |
case-07 | pass→fail | 13,156 | 14,290 | +9% | 1 | 1 | 0% | 2,326 | 3,177 | +37% | 0 | 0 | — |
case-08 | pass→pass | 25,843 | 31,864 | +23% | 1 | 1 | 0% | 4,861 | 6,410 | +32% | 0 | 0 | — |
case-09 | fail→fail | 4,280 | 5,482 | +28% | 1 | 1 | 0% | 153 | 1,186 | +675% | 0 | 0 | — |
case-10 | fail→pass | 25,522 | 25,801 | +1% | 1 | 1 | 0% | 4,351 | 4,473 | +3% | 0 | 0 | — |
case-11 | pass→pass | 17,748 | 19,116 | +8% | 1 | 1 | 0% | 2,847 | 3,936 | +38% | 0 | 0 | — |
case-13 | fail→pass | 17,815 | 26,888 | +51% | 1 | 1 | 0% | 3,572 | 4,813 | +35% | 0 | 0 | — |
case-14 | pass→fail | 17,341 | 5,473 | -68% | 1 | 1 | 0% | 2,861 | 1,562 | -45% | 0 | 0 | — |
case-15 | fail→pass | 24,425 | 17,080 | -30% | 1 | 1 | 0% | 4,624 | 3,804 | -18% | 0 | 0 | — |
case-16 | fail→pass | 10,218 | 6,152 | -40% | 1 | 1 | 0% | 1,615 | 1,747 | +8% | 0 | 0 | — |
case-17 | fail→pass | 16,860 | 19,060 | +13% | 1 | 1 | 0% | 2,742 | 4,093 | +49% | 0 | 0 | — |
case-18 | pass→pass | 17,651 | 23,546 | +33% | 1 | 1 | 0% | 2,921 | 4,319 | +48% | 0 | 0 | — |
case-19 | fail→pass | 18,528 | 20,369 | +10% | 1 | 1 | 0% | 3,332 | 4,437 | +33% | 0 | 0 | — |
case-20 | fail→pass | 12,471 | 16,146 | +29% | 1 | 1 | 0% | 2,091 | 3,639 | +74% | 0 | 0 | — |
case-21 | pass→pass | 9,851 | 10,748 | +9% | 1 | 1 | 0% | 1,693 | 2,819 | +67% | 0 | 0 | — |
case-22 | fail→pass | 16,343 | 14,624 | -11% | 1 | 1 | 0% | 2,980 | 3,352 | +12% | 0 | 0 | — |
case-23 | fail→pass | 16,128 | 19,428 | +20% | 1 | 1 | 0% | 2,554 | 3,560 | +39% | 0 | 0 | — |
case-24 | pass→pass | 20,237 | 21,872 | +8% | 1 | 1 | 0% | 3,283 | 4,424 | +35% | 0 | 0 | — |
case-25 | pass→pass | 20,024 | 34,251 | +71% | 1 | 1 | 0% | 3,156 | 5,869 | +86% | 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. 25 cases were attempted, and 24 counted toward the lift figure. The other 1 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 +36 percentage points is the difference between those two pass rates over the 24 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.