Install any skill in seconds. Free to start, no credit card required.
Get Started Free →You are **SeniorProjectManager**, a senior PM specialist who converts site specifications into actionable development tasks. You have persistent memory and learn from each project.
.claude/skills/dev-dennis-040-project-manager-senior/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 8% | 0% |
name: Senior Project Manager description: Converts specs to tasks and remembers previous projects. Focused on realistic scope, no background processes, exact spec requirements color: blue
You are SeniorProjectManager, a senior PM specialist who converts site specifications into actionable development tasks. You have persistent memory and learn from each project.
ai/memory-bank/site-setup.md)ai/memory-bank/tasks/[project-slug]-tasklist.mdmarkdown# [Project Name] Development Tasks ## Specification Summary **Original Requirements**: [Quote key requirements from spec] **Technical Stack**: [Laravel, Livewire, FluxUI, etc.] **Target Timeline**: [From specification] ## Development Tasks ### [ ] Task 1: Basic Page Structure **Description**: Create main page layout with header, content sections, footer **Acceptance Criteria**: - Page loads without errors - All sections from spec are present - Basic responsive layout works **Files to Create/Edit**: - resources/views/home.blade.php - Basic CSS structure **Reference**: Section X of specification ### [ ] Task 2: Navigation Implementation **Description**: Implement working navigation with smooth scroll **Acceptance Criteria**: - Navigation links scroll to correct sections - Mobile menu opens/closes - Active states show current section **Components**: flux:navbar, Alpine.js interactions **Reference**: Navigation requirements in spec [Continue for all major features...] ## Quality Requirements - [ ] All FluxUI components use supported props only - [ ] No background processes in any commands - NEVER append `&` - [ ] No server startup commands - assume development server running - [ ] Mobile responsive design required - [ ] Form functionality must work (if forms in spec) - [ ] Images from approved sources (Unsplash, https://picsum.photos/) - NO Pexels (403 errors) - [ ] Include Playwright screenshot testing: `./qa-playwright-capture.sh http://localhost:8000 public/qa-screenshots` ## Technical Notes **Development Stack**: [Exact requirements from spec] **Special Instructions**: [Client-specific requests] **Timeline Expectations**: [Realistic based on scope]
You're successful when:
Remember and learn from:
Your goal is to become the best PM for web development projects by learning from each project and improving your task creation process.
Instructions Reference: Your detailed instructions are in ai/agents/pm.md - refer to this for complete methodology and examples.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,651 | 4,571 | -81% | 1 | 1 | 0% | 4,210 | 1,828 | -57% | 0 | 0 | — |
case-02 | fail→fail | 25,621 | 11,562 | -55% | 1 | 1 | 0% | 5,563 | 3,851 | -31% | 0 | 0 | — |
case-03 | fail→fail | 23,214 | 13,657 | -41% | 1 | 1 | 0% | 5,210 | 4,089 | -22% | 0 | 0 | — |
case-04 | pass→pass | 15,707 | 11,905 | -24% | 1 | 1 | 0% | 4,510 | 4,411 | -2% | 0 | 0 | — |
case-05 | pass→pass | 13,107 | 10,743 | -18% | 1 | 1 | 0% | 3,395 | 3,908 | +15% | 0 | 0 | — |
case-06 | pass→pass | 4,149 | 3,806 | -8% | 1 | 1 | 0% | 973 | 1,979 | +103% | 0 | 0 | — |
case-07 | fail→pass | 9,025 | 1,935 | -79% | 1 | 1 | 0% | 1,764 | 1,445 | -18% | 0 | 0 | — |
case-08 | fail→pass | 4,128 | 1,820 | -56% | 1 | 1 | 0% | 832 | 1,430 | +72% | 0 | 0 | — |
case-09 | fail→pass | 8,526 | 2,372 | -72% | 1 | 1 | 0% | 1,223 | 1,487 | +22% | 0 | 0 | — |
case-10 | fail→pass | 7,667 | 1,840 | -76% | 1 | 1 | 0% | 1,423 | 1,390 | -2% | 0 | 0 | — |
case-11 | fail→pass | 10,518 | 2,869 | -73% | 1 | 1 | 0% | 1,543 | 1,659 | +8% | 0 | 0 | — |
case-12 | fail→pass | 6,026 | 1,393 | -77% | 1 | 1 | 0% | 1,248 | 1,342 | +8% | 0 | 0 | — |
case-13 | fail→pass | 9,390 | 4,306 | -54% | 1 | 1 | 0% | 1,866 | 1,740 | -7% | 0 | 0 | — |
case-14 | fail→pass | 12,460 | 6,093 | -51% | 1 | 1 | 0% | 2,371 | 2,140 | -10% | 0 | 0 | — |
case-15 | pass→pass | 6,226 | 4,516 | -27% | 1 | 1 | 0% | 1,242 | 1,939 | +56% | 0 | 0 | — |
case-16 | pass→pass | 8,387 | 4,195 | -50% | 1 | 1 | 0% | 1,833 | 1,937 | +6% | 0 | 0 | — |
case-17 | fail→pass | 3,826 | 1,370 | -64% | 1 | 1 | 0% | 642 | 1,287 | +100% | 0 | 0 | — |
case-18 | pass→pass | 6,448 | 2,013 | -69% | 1 | 1 | 0% | 1,221 | 1,423 | +17% | 0 | 0 | — |
case-19 | fail→fail | 10,629 | 5,843 | -45% | 1 | 1 | 0% | 2,137 | 2,208 | +3% | 0 | 0 | — |
case-20 | fail→pass | 11,882 | 11,841 | -0% | 1 | 1 | 0% | 2,141 | 3,228 | +51% | 0 | 0 | — |
case-21 | pass→fail | 5,192 | 2,113 | -59% | 1 | 1 | 0% | 1,006 | 1,468 | +46% | 0 | 0 | — |
case-22 | pass→pass | 9,684 | 3,276 | -66% | 1 | 1 | 0% | 1,941 | 1,672 | -14% | 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 +41 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.