Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Strategic planning with optional interview workflow. Use when the user wants to plan before implementing — "plan this", "let's plan", structured requirements gathering for vague ideas. Pairs with @compass-planner agent. Supports consensus mode and review mode.
.claude/skills/evolution-foundation-dev-plan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -19% | 0% |
Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.
Plan creates comprehensive, actionable work plans through intelligent interaction. It auto-detects whether to interview the user (broad requests) or plan directly (detailed requests).
dev-ralplan (Tier 1, imported in EPIC 3)dev-autopilot instead@bolt-executorJumping into code without understanding requirements leads to rework, scope creep, and missed edge cases. Plan provides structured requirements gathering, expert analysis, and quality-gated plans so that execution starts from a solid foundation.
@scout-explorer agent before asking the user about themworkspace/projects/plans/{name}.md| Mode | Trigger | Behavior | |------|---------|----------| | Interview | Default for broad requests | Interactive requirements gathering | | Direct | --direct, or detailed request | Skip interview, generate plan directly | | Review | --review | Critic evaluation of an existing plan |
After plan is approved by user:
@bolt-executor for implementationdev-autopilot for full lifecycle executionFor deeper structured planning, hand off to @compass-planner agent — it runs a tighter interview workflow with mandatory user confirmation gates.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | fail→fail | 7,272 | 1,893 | -74% | 1 | 1 | 0% | 1,196 | 804 | -33% | 0 | 0 | — |
case-01 | fail→fail | 15,875 | 4,565 | -71% | 1 | 1 | 0% | 2,511 | 1,273 | -49% | 0 | 0 | — |
case-02 | fail→fail | 22,048 | 18,082 | -18% | 1 | 1 | 0% | 3,567 | 3,663 | +3% | 0 | 0 | — |
case-03 | pass→pass | 3,303 | 2,799 | -15% | 1 | 1 | 0% | 567 | 985 | +74% | 0 | 0 | — |
case-04 | pass→fail | 3,288 | 2,682 | -18% | 1 | 1 | 0% | 458 | 855 | +87% | 0 | 0 | — |
case-05 | fail→pass | 8,678 | 7,509 | -13% | 1 | 1 | 0% | 1,408 | 1,804 | +28% | 0 | 0 | — |
case-06 | pass→fail | 9,845 | 6,283 | -36% | 1 | 1 | 0% | 1,537 | 870 | -43% | 0 | 0 | — |
case-07 | fail→fail | 6,603 | 8,606 | +30% | 1 | 1 | 0% | 1,056 | 1,785 | +69% | 0 | 0 | — |
case-08 | fail→fail | 8,962 | 2,885 | -68% | 1 | 1 | 0% | 1,319 | 957 | -27% | 0 | 0 | — |
case-10 | fail→pass | 6,379 | 2,424 | -62% | 1 | 1 | 0% | 976 | 878 | -10% | 0 | 0 | — |
case-11 | fail→pass | 4,005 | 2,485 | -38% | 1 | 1 | 0% | 547 | 950 | +74% | 0 | 0 | — |
case-12 | fail→pass | 12,121 | 3,189 | -74% | 1 | 1 | 0% | 1,883 | 1,077 | -43% | 0 | 0 | — |
case-13 | pass→pass | 9,798 | 1,880 | -81% | 1 | 1 | 0% | 1,548 | 794 | -49% | 0 | 0 | — |
case-14 | pass→fail | 16,509 | 4,229 | -74% | 1 | 1 | 0% | 2,448 | 1,232 | -50% | 0 | 0 | — |
case-15 | fail→pass | 13,420 | 6,222 | -54% | 1 | 1 | 0% | 1,895 | 1,526 | -19% | 0 | 0 | — |
case-16 | pass→pass | 5,944 | 3,035 | -49% | 1 | 1 | 0% | 830 | 1,043 | +26% | 0 | 0 | — |
case-17 | pass→pass | 6,013 | 2,915 | -52% | 1 | 1 | 0% | 924 | 1,059 | +15% | 0 | 0 | — |
case-18 | fail→fail | 13,600 | 4,975 | -63% | 1 | 1 | 0% | 2,038 | 1,240 | -39% | 0 | 0 | — |
case-19 | fail→pass | 11,645 | 3,785 | -67% | 1 | 1 | 0% | 1,744 | 1,145 | -34% | 0 | 0 | — |
case-20 | fail→pass | 7,193 | 2,705 | -62% | 1 | 1 | 0% | 1,014 | 983 | -3% | 0 | 0 | — |
case-21 | fail→pass | 4,963 | 2,115 | -57% | 1 | 1 | 0% | 714 | 809 | +13% | 0 | 0 | — |
case-22 | pass→pass | 6,514 | 2,080 | -68% | 1 | 1 | 0% | 1,073 | 859 | -20% | 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 21 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 +23 percentage points is the difference between those two pass rates over the 21 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.