Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.
.claude/skills/aiskillstore-planner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 14% | 0% |
Create detailed, phased implementation plans for bugs, features, or tasks.
Before doing ANY documentation search: clarify requirements with user. This will narrow and aid you in finding the right docs.
Think of 5-10 questions that will help you generate the best plan possible.
Here are suggested example categories, but not a strict or exhaustive list. You may ask anything helpful. Use best judgement & prioritize ambiguity and risk reduction:
When the plan involves any external library, API, framework, or service, use the Context7 skill to fetch the latest official docs before drafting tasks. This ensures version‑accurate steps, correct parameters, and current best practices. If no external dependencies apply, skip this phase.
Each sprint must:
Each task must be:
Bad: "Implement Google OAuth" Good:
Save the file
Generate filename from request:
-plan.md suffixExamples:
xyz-bug-plan.mdAFTER it is saved. Identify potential issues & edge cases in plan. Address proactively. Where could smth go wrong? What about the plan is ambiguous? Missing step, dependency, or pitfall?
If any gotchas found, stop & ask up to 3 more questions. (either w/ request_user_input or directly)
Refine the plan if any additional useful info is provided.
markdown# Plan: [Task Name] **Generated**: [Date] **Estimated Complexity**: [Low/Medium/High] ## Overview [Summary of task and approach] ## Prerequisites - [Dependencies or requirements] - [Tools, libraries, access needed] ## Sprint 1: [Name] **Goal**: [What this accomplishes] **Demo/Validation**: - [How to run/demo] - [What to verify] ### Task 1.1: [Name] - **Location**: [File paths] - **Description**: [What to do] - **Dependencies**: [Previous tasks] - **Acceptance Criteria**: - [Specific criteria] - **Validation**: - [Tests or verification] ### Task 1.2: [Name] [...] ## Sprint 2: [Name] [...] ## Testing Strategy - [How to test] - [What to verify per sprint] ## Potential Risks & Gotchas - [What could go wrong] - [Mitigation strategies] ## Rollback Plan - [How to undo if needed]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,021 | 15,901 | -28% | 1 | 1 | 0% | 3,370 | 2,804 | -17% | 0 | 0 | — |
case-02 | fail→pass | 31,888 | 21,018 | -34% | 1 | 1 | 0% | 5,917 | 2,390 | -60% | 0 | 0 | — |
case-03 | fail→fail | 37,592 | 13,871 | -63% | 1 | 1 | 0% | 6,861 | 2,378 | -65% | 0 | 0 | — |
case-04 | pass→fail | 12,611 | 14,954 | +19% | 1 | 1 | 0% | 2,622 | 2,713 | +3% | 0 | 0 | — |
case-05 | pass→pass | 13,178 | 19,696 | +49% | 1 | 1 | 0% | 1,334 | 3,082 | +131% | 0 | 0 | — |
case-06 | pass→fail | 11,899 | 13,087 | +10% | 1 | 1 | 0% | 1,142 | 3,203 | +180% | 0 | 0 | — |
case-07 | fail→pass | 19,442 | 11,552 | -41% | 1 | 1 | 0% | 2,354 | 1,971 | -16% | 0 | 0 | — |
case-08 | fail→pass | 20,066 | 12,204 | -39% | 1 | 1 | 0% | 2,555 | 2,210 | -14% | 0 | 0 | — |
case-09 | fail→fail | 35,065 | 11,535 | -67% | 1 | 1 | 0% | 2,397 | 2,120 | -12% | 0 | 0 | — |
case-10 | fail→fail | 2,525 | 9,227 | +265% | 1 | 1 | 0% | 423 | 1,709 | +304% | 0 | 0 | — |
case-11 | fail→pass | 13,887 | 8,181 | -41% | 1 | 1 | 0% | 1,304 | 1,489 | +14% | 0 | 0 | — |
case-12 | fail→pass | 14,177 | 4,129 | -71% | 1 | 1 | 0% | 1,351 | 1,629 | +21% | 0 | 0 | — |
case-13 | fail→fail | 11,787 | 14,481 | +23% | 1 | 1 | 0% | 1,794 | 2,566 | +43% | 0 | 0 | — |
case-14 | pass→pass | 15,608 | 12,226 | -22% | 1 | 1 | 0% | 1,626 | 2,724 | +68% | 0 | 0 | — |
case-15 | fail→pass | 9,081 | 3,186 | -65% | 1 | 1 | 0% | 1,105 | 1,338 | +21% | 0 | 0 | — |
case-16 | fail→pass | 18,001 | 3,439 | -81% | 1 | 1 | 0% | 2,133 | 1,558 | -27% | 0 | 0 | — |
case-17 | fail→fail | 12,554 | 10,278 | -18% | 1 | 1 | 0% | 1,068 | 1,391 | +30% | 0 | 0 | — |
case-18 | fail→pass | 19,335 | 13,258 | -31% | 1 | 1 | 0% | 2,996 | 2,357 | -21% | 0 | 0 | — |
case-19 | pass→pass | 14,027 | 10,109 | -28% | 1 | 1 | 0% | 1,506 | 1,782 | +18% | 0 | 0 | — |
case-20 | fail→pass | 5,721 | 7,200 | +26% | 1 | 1 | 0% | 764 | 1,303 | +71% | 0 | 0 | — |
case-21 | pass→pass | 14,547 | 25,728 | +77% | 1 | 1 | 0% | 2,258 | 3,824 | +69% | 0 | 0 | — |
case-22 | pass→pass | 19,880 | 32,862 | +65% | 1 | 1 | 0% | 2,314 | 4,456 | +93% | 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. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 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.