Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →AI DevKit · Orchestrator for structured SDLC phase skills. Use when the user wants to run the full lifecycle or choose the next phase across requirements, design, planning, implementation, testing, and review.
.claude/skills/bilal140202-dev-lifecycle/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 144% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 6% | 0% |
Coordinate the phase-specific AI DevKit skills instead of running phase details directly.
Required phase skills:
dev-worktree for feature workspace setup and resume.dev-requirements for phases 1-2: new requirement and requirements review.dev-design for phase 3: design review.dev-planning for phases 4 and 6: initial task planning and updates after implementation tasks.dev-implementation for phases 5 and 7: execute plan and check implementation.dev-testing for phase 8: write tests and verify coverage.dev-review for phase 9: final code review.Supporting skills:
memory for reusable project knowledge during clarification.tdd for implementation tasks.verify before completing implementation, implementation checks, testing claims, and review readiness.At the beginning of every dev-lifecycle run:
npx ai-devkit@latest skill list to inspect currently installed project skills.npx ai-devkit@latest skill add --built-in to install all AI DevKit built-in skills. Then rerun npx ai-devkit@latest skill list.npx ai-devkit@latest lint to verify the configured AI docs structure.npx ai-devkit@latest lint --feature <name>.npx ai-devkit@latest init -a -e claude --built-in --yes, then rerun lint.Before executing any phase:
| Phase | Route to | When | |---|---|---| | Setup. Workspace | dev-worktree | Starting or resuming feature work | | 1. New Requirement | dev-requirements | User wants to add a feature or start /new-requirement | | 2. Review Requirements | dev-requirements | Requirements doc needs validation | | 3. Review Design | dev-design | Design doc needs validation against requirements | | 4. Create Initial Plan | dev-planning | Requirements, design, and testing docs are ready for task breakdown | | 5. Execute Plan | dev-implementation | Ready to implement tasks from planning doc | | 6. Update Planning | dev-planning | Auto-trigger after completing any implementation task | | 7. Check Implementation | dev-implementation | Verify code matches design and docs | | 8. Write Tests | dev-testing | Add or verify test coverage | | 9. Code Review | dev-review | Final pre-push review |
Sequential flow: setup -> 1 -> 2 -> 3 -> 4 -> 5 -> 6 after each completed task -> 7 -> 8 -> 9.
If the user wants to continue work on an existing feature:
dev-worktree to identify and confirm the target branch/worktree.npx ai-devkit@latest lint --feature <feature-name> in the active context.dev-lifecycle skill directory:<skill-dir> as the directory containing this SKILL.md.<skill-dir>/scripts/check-status.sh <feature-name>.Not every phase moves forward. When a phase reveals problems, route back:
dev-requirements Phase 1.dev-requirements Phase 2.dev-design and revise design.dev-design if design is wrong, or dev-implementation if code is wrong.dev-design.dev-implementation or dev-testing.npx ai-devkit@latest lint and npx ai-devkit@latest lint --feature <name> to discover and validate the configured docs directory. Do not assume docs/ai; it is only the default.feature-<name>.npx ai-devkit@latest docs init-feature <name>. Use the paths returned by the command as authoritative.npx ai-devkit@latest lint --feature <name>. If you must infer manually, first resolve the configured docs directory from .ai-devkit.json paths.docs, falling back to docs/ai.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,000 | 5,687 | +42% | 1 | 1 | 0% | 215 | 1,650 | +667% | 0 | 0 | — |
case-02 | fail→fail | 4,610 | 5,811 | +26% | 1 | 1 | 0% | 223 | 1,569 | +604% | 0 | 0 | — |
case-03 | fail→fail | 16,066 | 2,529 | -84% | 1 | 1 | 0% | 2,401 | 1,754 | -27% | 0 | 0 | — |
case-04 | fail→pass | 8,021 | 2,798 | -65% | 1 | 1 | 0% | 1,352 | 1,764 | +30% | 0 | 0 | — |
case-05 | fail→pass | 4,714 | 2,356 | -50% | 1 | 1 | 0% | 714 | 1,742 | +144% | 0 | 0 | — |
case-10 | fail→pass | 9,316 | 2,420 | -74% | 1 | 1 | 0% | 1,505 | 1,707 | +13% | 0 | 0 | — |
case-06 | fail→fail | 9,957 | 3,064 | -69% | 1 | 1 | 0% | 1,401 | 1,734 | +24% | 0 | 0 | — |
case-07 | fail→fail | 10,870 | 6,423 | -41% | 1 | 1 | 0% | 1,844 | 1,705 | -8% | 0 | 0 | — |
case-08 | fail→pass | 13,056 | 2,689 | -79% | 1 | 1 | 0% | 1,986 | 1,673 | -16% | 0 | 0 | — |
case-09 | fail→pass | 10,410 | 2,799 | -73% | 1 | 1 | 0% | 1,603 | 1,702 | +6% | 0 | 0 | — |
case-11 | fail→pass | 5,264 | 5,322 | +1% | 1 | 1 | 0% | 779 | 2,138 | +174% | 0 | 0 | — |
case-12 | fail→pass | 8,109 | 3,488 | -57% | 1 | 1 | 0% | 1,349 | 1,896 | +41% | 0 | 0 | — |
case-13 | fail→pass | 8,058 | 4,198 | -48% | 1 | 1 | 0% | 1,100 | 1,986 | +81% | 0 | 0 | — |
case-14 | pass→fail | 11,554 | 8,877 | -23% | 1 | 1 | 0% | 1,740 | 1,733 | -0% | 0 | 0 | — |
case-15 | fail→pass | 9,628 | 6,319 | -34% | 1 | 1 | 0% | 1,499 | 2,318 | +55% | 0 | 0 | — |
case-16 | fail→pass | 10,853 | 9,745 | -10% | 1 | 1 | 0% | 1,823 | 3,172 | +74% | 0 | 0 | — |
case-17 | fail→pass | 6,830 | 3,040 | -55% | 1 | 1 | 0% | 1,141 | 1,871 | +64% | 0 | 0 | — |
case-18 | fail→pass | 7,111 | 10,558 | +48% | 1 | 1 | 0% | 1,223 | 2,767 | +126% | 0 | 0 | — |
case-19 | pass→fail | 9,564 | 5,606 | -41% | 1 | 1 | 0% | 1,740 | 1,728 | -1% | 0 | 0 | — |
case-20 | pass→pass | 3,322 | 8,791 | +165% | 1 | 1 | 0% | 563 | 2,199 | +291% | 0 | 0 | — |
case-21 | pass→fail | 5,913 | 5,825 | -1% | 1 | 1 | 0% | 1,006 | 1,565 | +56% | 0 | 0 | — |
case-22 | pass→pass | 7,736 | 1,768 | -77% | 1 | 1 | 0% | 1,327 | 1,564 | +18% | 0 | 0 | — |
case-23 | pass→pass | 6,291 | 2,160 | -66% | 1 | 1 | 0% | 1,020 | 1,598 | +57% | 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. 23 cases were attempted, and 17 counted toward the lift figure. The other 6 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 +39 percentage points is the difference between those two pass rates over the 17 comparable cases. 3 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.