Install any skill in seconds. Free to start, no credit card required.
Get Started Free →[COMMUNITY] Generate a Canada Charter rights design review — s.2 (expression and association), s.7 (life, liberty, security of person), s.8 (search and seizure), s.15 (equality) — applying Oakes proportionality framing to system design with mitigation tracker and DOJ counsel sign-off block.
.claude/skills/thomasmoreai-arckit-ca-charter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-19 | ✗→✓ | ▲ Improved | 221% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 210% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 941% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 161% | 0% |
> ⚠️ Community-contributed command — not part of the officially-maintained ArcKit baseline. > Output should be reviewed by qualified Canadian counsel, your departmental ATIP coordinator, > ITSEC officer, and (for FITAA matters) the Office of the Commissioner of Foreign Influence > Transparency before reliance. > > Statutory currency: FITAA was enacted June 2024 with regulations still emerging through 2025–2026. > The Commissioner's office is newly stood up and operational guidance will evolve. Verify all > citations against the current Justice Laws Website text and Commissioner's published guidance > before relying on this output.
text$ARGUMENTS
You are an enterprise architect generating a Canada Charter Rights Design Review for a federal system that materially engages Charter-protected interests.
projects/000-global/ARC-000-PRIN-*.md (federal principles, if present)ARC-<id>-PIA-v*.md (ca-pia artefact) where present — §8 reasonable-expectation-of-privacy analysis is grounded in the personal-information categories captured by the PIAARC-<id>-FITAA-v*.md (ca-fitaa artefact) where present — §2 expression and association analysis is a mandatory companion to FITAA.arckit/templates/_partials/RENDERING.md.arckit/templates-custom/ca-charter-template.md (user override).arckit/templates-custom/ca-charter-template.md.arckit/templates/ca-charter-template.mdscripts/bash/generate-document-id.sh <PROJECT_ID> CHRT --filename for the artefact filename.<!-- DOC-CONTROL-HEADER --> marker per RENDERING.md. Use the Canadian classification scheme (UNCLASSIFIED / Protected A / Protected B / Protected C / CONFIDENTIAL / SECRET / TOP SECRET) — replace the standard UK line in the header..arckit/references/citation-instructions.md. The Canadian Charter of Rights and Freedoms MUST appear in the Document Register with its primary URL and the verification date. Cite the key jurisprudence below where applicable.projects/<project-id>/<filename>.Canadian Charter of Rights and Freedoms, Part I of the Constitution Act, 1982, Schedule B to the Canada Act 1982 (UK), c. 11. URL: <https://laws-lois.justice.gc.ca/eng/const/page-12.html>. Authority: Department of Justice (constitutional advisory). Key jurisprudence to cite where applicable: R v Oakes 1986] 1 SCR 103 (proportionality); Hunter v Southam 1984] 2 SCR 145 (s.8); R v Spencer 2014] 2 SCR 212 (s.8 in digital contexts); Carter v Canada 2015] 1 SCR 331 (s.7 framework).
After completing this command, consider running:
$arckit-ca-fitaa -- Charter §2 expression and association analysis is a mandatory companion to FITAA; the FITAA artefact references this review.$arckit-ca-pia -- §8 search-and-seizure analysis is grounded in the personal-information categories captured in the Privacy Impact Assessment.$arckit-risk -- Residual Charter risks per right feed the operational risk register with appropriate severity.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-19 | fail→pass | 10,674 | 21,219 | +99% | 1 | 1 | 0% | 1,643 | 5,277 | +221% | 0 | 0 | — |
case-07 | pass→fail | 14,875 | 11,207 | -25% | 1 | 1 | 0% | 2,486 | 2,117 | -15% | 0 | 0 | — |
case-01 | fail→fail | 17,959 | 7,646 | -57% | 1 | 1 | 0% | 3,056 | 2,379 | -22% | 0 | 0 | — |
case-13 | fail→fail | 4,656 | 5,710 | +23% | 1 | 1 | 0% | 723 | 1,998 | +176% | 0 | 0 | — |
case-02 | fail→fail | 29,539 | 4,966 | -83% | 1 | 1 | 0% | 4,217 | 1,879 | -55% | 0 | 0 | — |
case-03 | fail→fail | 19,296 | 7,472 | -61% | 1 | 1 | 0% | 3,459 | 2,242 | -35% | 0 | 0 | — |
case-04 | fail→pass | 14,664 | 38,435 | +162% | 1 | 1 | 0% | 2,545 | 7,881 | +210% | 0 | 0 | — |
case-05 | fail→fail | 17,890 | 6,970 | -61% | 1 | 1 | 0% | 3,131 | 2,088 | -33% | 0 | 0 | — |
case-06 | fail→fail | 13,133 | 8,200 | -38% | 1 | 1 | 0% | 2,296 | 2,121 | -8% | 0 | 0 | — |
case-08 | pass→fail | 18,450 | 128,452 | +596% | 1 | 1 | 0% | 2,845 | 2,136 | -25% | 0 | 0 | — |
case-09 | fail→pass | 13,185 | 12,057 | -9% | 1 | 1 | 0% | 2,149 | 3,738 | +74% | 0 | 0 | — |
case-10 | fail→fail | 23,305 | 12,701 | -46% | 1 | 1 | 0% | 3,856 | 2,323 | -40% | 0 | 0 | — |
case-11 | fail→fail | 16,584 | 31,448 | +90% | 1 | 1 | 0% | 2,596 | 2,188 | -16% | 0 | 0 | — |
case-12 | fail→fail | 2,001 | 34,872 | +1643% | 1 | 1 | 0% | 292 | 7,859 | +2591% | 0 | 0 | — |
case-14 | fail→pass | 3,710 | 46,014 | +1140% | 1 | 1 | 0% | 744 | 7,743 | +941% | 0 | 0 | — |
case-15 | fail→fail | 7,034 | 5,225 | -26% | 1 | 1 | 0% | 1,068 | 1,994 | +87% | 0 | 0 | — |
case-16 | fail→pass | 16,980 | 114,865 | +576% | 1 | 1 | 0% | 2,844 | 7,423 | +161% | 0 | 0 | — |
case-17 | fail→fail | 39,401 | 36,595 | -7% | 1 | 1 | 0% | 5,860 | 7,857 | +34% | 0 | 0 | — |
case-18 | fail→fail | 1,618 | 6,609 | +308% | 1 | 1 | 0% | 269 | 2,050 | +662% | 0 | 0 | — |
case-20 | pass→pass | 13,763 | 17,380 | +26% | 1 | 1 | 0% | 2,956 | 4,622 | +56% | 0 | 0 | — |
case-21 | pass→fail | 14,439 | 40,289 | +179% | 1 | 1 | 0% | 2,380 | 7,864 | +230% | 0 | 0 | — |
case-22 | pass→fail | 23,682 | 28,206 | +19% | 1 | 1 | 0% | 3,847 | 6,960 | +81% | 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 10 counted toward the lift figure. The other 12 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 10 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.