Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria, risk assessments, and alternative approaches. All plans MUST be validated using the included validation script. Use when users need thorough analysis and structured planning before implementation, when breaking down complex features into actionable steps, or when they explicitly ask for
.claude/skills/microck-create-plan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 318% | 0% |
| case-08 | ✓→✗ | ▼ Worse | -10% | 0% |
Generate comprehensive implementation plans that provide strategic guidance without making actual code changes.
Research the codebase to understand:
Use search and read tools to examine the codebase. Use sage if deeper research is required for the use-case. Explicitly cite sources using filepath:line format.
Generate a Markdown plan file in plans/ directory with naming: plans/{YYYY-MM-DD}-{task-name}-v{N}.md
Example: plans/2025-11-24-add-auth-v1.md
MANDATORY: Run the validation script to ensure the plan meets all requirements:
bash./.forge/skills/create-plan/validate-plan.sh plans/{YYYY-MM-DD}-{task-name}-v{N}.md
Fix any errors or warnings and re-validate until the plan passes all checks.
markdown# [Task Name] ## Objective [Clear statement of goal and expected outcomes] ## Implementation Plan - [ ] 1. [First task with detailed description and rationale] - [ ] 2. [Second task with detailed description and rationale] - [ ] 3. [Third task with detailed description and rationale] ## Verification Criteria - [Criterion 1: Specific, measurable outcome] - [Criterion 2: Specific, measurable outcome] ## Potential Risks and Mitigations 1. **[Risk Description]** Mitigation: [Specific mitigation strategy] 2. **[Risk Description]** Mitigation: [Specific mitigation strategy] ## Alternative Approaches 1. [Alternative 1]: [Brief description and trade-offs] 2. [Alternative 2]: [Brief description and trade-offs]
./.forge/skills/create-plan/validate-plan.sh after creation- [ ]) for ALL implementation tasksThis is a planning-only skill:
If user requests implementation work, suggest switching to an implementation agent.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→fail | 12,883 | 7,356 | -43% | 1 | 1 | 0% | 2,019 | 1,278 | -37% | 0 | 0 | — |
case-01 | fail→fail | 44,950 | 6,433 | -86% | 1 | 1 | 0% | 3,577 | 1,017 | -72% | 0 | 0 | — |
case-02 | fail→fail | 20,919 | 6,025 | -71% | 1 | 1 | 0% | 3,407 | 1,215 | -64% | 0 | 0 | — |
case-03 | fail→fail | 32,855 | 5,477 | -83% | 1 | 1 | 0% | 5,258 | 1,164 | -78% | 0 | 0 | — |
case-04 | fail→fail | 14,317 | 7,115 | -50% | 1 | 1 | 0% | 2,522 | 1,356 | -46% | 0 | 0 | — |
case-05 | fail→fail | 4,736 | 6,368 | +34% | 1 | 1 | 0% | 669 | 1,039 | +55% | 0 | 0 | — |
case-06 | fail→fail | 9,140 | 8,600 | -6% | 1 | 1 | 0% | 1,359 | 1,320 | -3% | 0 | 0 | — |
case-07 | fail→pass | 11,502 | 3,278 | -72% | 1 | 1 | 0% | 1,945 | 1,314 | -32% | 0 | 0 | — |
case-08 | pass→fail | 7,058 | 5,568 | -21% | 1 | 1 | 0% | 1,132 | 1,014 | -10% | 0 | 0 | — |
case-10 | fail→fail | 15,867 | 5,342 | -66% | 1 | 1 | 0% | 2,386 | 1,181 | -51% | 0 | 0 | — |
case-11 | fail→pass | 9,628 | 3,110 | -68% | 1 | 1 | 0% | 1,404 | 1,203 | -14% | 0 | 0 | — |
case-12 | fail→fail | 19,101 | 4,094 | -79% | 1 | 1 | 0% | 3,048 | 1,073 | -65% | 0 | 0 | — |
case-13 | fail→fail | 14,079 | 23,322 | +66% | 1 | 1 | 0% | 2,167 | 4,035 | +86% | 0 | 0 | — |
case-14 | fail→fail | 16,739 | 4,342 | -74% | 1 | 1 | 0% | 2,765 | 905 | -67% | 0 | 0 | — |
case-15 | pass→pass | 5,289 | 2,229 | -58% | 1 | 1 | 0% | 878 | 1,211 | +38% | 0 | 0 | — |
case-16 | fail→pass | 13,296 | 5,000 | -62% | 1 | 1 | 0% | 2,059 | 1,536 | -25% | 0 | 0 | — |
case-17 | pass→fail | 13,662 | 7,180 | -47% | 1 | 1 | 0% | 1,944 | 1,069 | -45% | 0 | 0 | — |
case-18 | pass→fail | 12,103 | 11,370 | -6% | 1 | 1 | 0% | 2,025 | 1,805 | -11% | 0 | 0 | — |
case-19 | pass→pass | 9,181 | 2,464 | -73% | 1 | 1 | 0% | 1,537 | 1,189 | -23% | 0 | 0 | — |
case-20 | fail→pass | 4,799 | 2,236 | -53% | 1 | 1 | 0% | 272 | 1,136 | +318% | 0 | 0 | — |
case-21 | fail→fail | 4,928 | 7,217 | +46% | 1 | 1 | 0% | 167 | 1,212 | +626% | 0 | 0 | — |
case-22 | fail→fail | 5,724 | 6,884 | +20% | 1 | 1 | 0% | 973 | 1,239 | +27% | 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 6 counted toward the lift figure. The other 16 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 +5 percentage points is the difference between those two pass rates over the 6 comparable cases. 5 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.