Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create or update project governing principles and development guidelines. Use at project start to establish code quality, testing standards, and architectural constraints that guide all development.
.claude/skills/foryourhealth111-pixel-speckit-constitution/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 53% | 0% |
text$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
You are updating the project constitution at .specify/memory/constitution.md. This file is a TEMPLATE containing placeholder tokens in square brackets (e.g. [PROJECT_NAME], [PRINCIPLE_1_NAME]). Your job is to (a) collect/derive concrete values, (b) fill the template precisely, and (c) propagate any amendments across dependent artifacts.
Note: If .specify/memory/constitution.md does not exist yet, it should have been initialized from .specify/templates/constitution-template.md during project setup. If it's missing, copy the template first.
Follow this execution flow:
.specify/memory/constitution.md.[ALL_CAPS_IDENTIFIER].IMPORTANT: The user might require less or more principles than the ones used in the template. If a number is specified, respect that - follow the general template. You will update the doc accordingly.
RATIFICATION_DATE is the original adoption date (if unknown ask or mark TODO), LAST_AMENDED_DATE is today if changes are made, otherwise keep previous.CONSTITUTION_VERSION must increment according to semantic versioning rules:.specify/templates/plan-template.md and ensure any "Constitution Check" or rules align with updated principles..specify/templates/spec-template.md for scope/requirements alignment—update if constitution adds/removes mandatory sections or constraints..specify/templates/tasks-template.md and ensure task categorization reflects new or removed principle-driven task types (e.g., observability, versioning, testing discipline)..specify/templates/commands/*.md (including this one) to verify no outdated references (agent-specific names like CLAUDE only) remain when generic guidance is required.README.md, docs/quickstart.md, or agent-specific guidance files if present). Update references to principles changed..specify/memory/constitution.md (overwrite).docs: amend constitution to vX.Y.Z (principle additions + governance update)).Formatting & Style Requirements:
If the user supplies partial updates (e.g., only one principle revision), still perform validation and version decision steps.
If critical info missing (e.g., ratification date truly unknown), insert TODO(<FIELD_NAME>): explanation and include in the Sync Impact Report under deferred items.
Do not create a new template; always operate on the existing .specify/memory/constitution.md file.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,617 | 6,282 | +12% | 1 | 1 | 0% | 174 | 1,612 | +826% | 0 | 0 | — |
case-02 | fail→fail | 16,076 | 6,335 | -61% | 1 | 1 | 0% | 2,840 | 1,463 | -48% | 0 | 0 | — |
case-03 | fail→fail | 17,948 | 8,123 | -55% | 1 | 1 | 0% | 3,240 | 1,451 | -55% | 0 | 0 | — |
case-04 | fail→fail | 8,258 | 5,965 | -28% | 1 | 1 | 0% | 1,506 | 1,532 | +2% | 0 | 0 | — |
case-05 | fail→fail | 2,526 | 4,917 | +95% | 1 | 1 | 0% | 272 | 1,449 | +433% | 0 | 0 | — |
case-06 | pass→fail | 3,540 | 5,820 | +64% | 1 | 1 | 0% | 517 | 1,406 | +172% | 0 | 0 | — |
case-07 | fail→pass | 8,161 | 3,440 | -58% | 1 | 1 | 0% | 1,318 | 1,780 | +35% | 0 | 0 | — |
case-08 | pass→fail | 3,041 | 4,840 | +59% | 1 | 1 | 0% | 561 | 1,367 | +144% | 0 | 0 | — |
case-09 | fail→pass | 10,148 | 2,859 | -72% | 1 | 1 | 0% | 1,674 | 1,653 | -1% | 0 | 0 | — |
case-10 | pass→pass | 4,869 | 3,196 | -34% | 1 | 1 | 0% | 709 | 1,584 | +123% | 0 | 0 | — |
case-11 | pass→pass | 3,961 | 5,442 | +37% | 1 | 1 | 0% | 780 | 2,094 | +168% | 0 | 0 | — |
case-12 | pass→pass | 3,273 | 3,044 | -7% | 1 | 1 | 0% | 486 | 1,655 | +241% | 0 | 0 | — |
case-13 | fail→pass | 9,576 | 1,743 | -82% | 1 | 1 | 0% | 1,774 | 1,407 | -21% | 0 | 0 | — |
case-14 | pass→pass | 8,341 | 18,833 | +126% | 1 | 1 | 0% | 1,606 | 3,936 | +145% | 0 | 0 | — |
case-15 | fail→pass | 8,383 | 2,207 | -74% | 1 | 1 | 0% | 1,314 | 1,559 | +19% | 0 | 0 | — |
case-16 | pass→pass | 3,530 | 7,631 | +116% | 1 | 1 | 0% | 586 | 2,185 | +273% | 0 | 0 | — |
case-17 | pass→pass | 4,850 | 2,652 | -45% | 1 | 1 | 0% | 771 | 1,511 | +96% | 0 | 0 | — |
case-18 | fail→pass | 5,612 | 2,736 | -51% | 1 | 1 | 0% | 1,023 | 1,564 | +53% | 0 | 0 | — |
case-19 | fail→fail | 6,817 | 3,040 | -55% | 1 | 1 | 0% | 1,143 | 1,587 | +39% | 0 | 0 | — |
case-20 | pass→fail | 20,713 | 26,943 | +30% | 1 | 1 | 0% | 4,168 | 6,567 | +58% | 0 | 0 | — |
case-21 | pass→pass | 11,229 | 18,313 | +63% | 1 | 1 | 0% | 2,254 | 4,642 | +106% | 0 | 0 | — |
case-22 | fail→fail | 2,088 | 5,520 | +164% | 1 | 1 | 0% | 339 | 1,452 | +328% | 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 14 counted toward the lift figure. The other 8 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 +9 percentage points is the difference between those two pass rates over the 14 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.