Install any skill in seconds. Free to start, no credit card required.
Get Started Free →[COMMUNITY] Generate a Canada Security of Information Act handling plan — Special Operational Information (SOI) register, marking and handling matrix, transmission channels, compartments and need-to-know, destruction and sanitisation, CSIS Act §16 and §19 coordination, RCMP NSP liaison, breach response, personnel reliability prerequisites.
.claude/skills/thomasmoreai-arckit-ca-soia/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 701% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 125% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 135% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 133% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 57% | 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 Security of Information Act handling plan for a federal information system that processes Special Operational Information or other classified material.
projects/000-global/ARC-000-PRIN-*.md (federal principles, if present)ARC-<id>-ITSG-*.md) if present — its categorisation drives the handling envelopeARC-<id>-FITAA-*.md) if present — the protected investigative dataset overlaps with SOI.arckit/templates/_partials/RENDERING.md.arckit/templates-custom/ca-soia-template.md (user override).arckit/templates-custom/ca-soia-template.md.arckit/templates/ca-soia-template.mdscripts/bash/generate-document-id.sh <PROJECT_ID> SOIA --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. Note that the artefact itself will frequently warrant a SECRET or higher classification..arckit/references/citation-instructions.md. The Security of Information Act (R.S.C., 1985, c. O-5) and the Canadian Security Intelligence Service Act (R.S.C., 1985, c. C-23) MUST appear in the Document Register with their primary URLs (Justice Laws Website) and the verification date.projects/<project-id>/<filename>.Security of Information Act (R.S.C., 1985, c. O-5); Canadian Security Intelligence Service Act (R.S.C., 1985, c. C-23); TBS Standard on Security Screening; CSE ITSP-series guidance (ITSP.40.006 media sanitisation, ITSP.30.031 v3 user authentication, etc.). Authority: CSIS, CSE / Cyber Centre, RCMP, TBS. Primary URLs: <https://laws-lois.justice.gc.ca/eng/acts/O-5/> (SOIA) and <https://laws-lois.justice.gc.ca/eng/acts/C-23/> (CSIS Act).
CSIS Act amendments via Bill C-26 (cyber security) and Bill C-70 (foreign interference) are still settling — flag the consolidated Justice Laws text date in the External References section.
After completing this command, consider running:
$arckit-ca-itsg-33 -- SOIA handling rules sit on top of the ITSG-33 security baseline; categorisation and control profile are the prerequisite layer.$arckit-risk -- SOIA-specific residual risks (compartment compromise, suspected unauthorised disclosure) feed the operational risk register.$arckit-adr -- Compartment design, MOU choices with CSIS / RCMP, and tier-promotion thresholds warrant Architecture Decision Records.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 28,775 | 7,240 | -75% | 1 | 1 | 0% | 4,861 | 2,610 | -46% | 0 | 0 | — |
case-02 | fail→fail | 33,436 | 5,000 | -85% | 1 | 1 | 0% | 6,188 | 2,512 | -59% | 0 | 0 | — |
case-03 | fail→fail | 20,007 | 8,073 | -60% | 1 | 1 | 0% | 3,322 | 2,763 | -17% | 0 | 0 | — |
case-04 | fail→pass | 9,108 | 46,740 | +413% | 1 | 1 | 0% | 1,469 | 11,773 | +701% | 0 | 0 | — |
case-05 | pass→fail | 8,117 | 8,350 | +3% | 1 | 1 | 0% | 1,219 | 3,057 | +151% | 0 | 0 | — |
case-06 | pass→fail | 20,097 | 45,370 | +126% | 1 | 1 | 0% | 1,725 | 2,703 | +57% | 0 | 0 | — |
case-07 | fail→fail | 15,554 | 9,768 | -37% | 1 | 1 | 0% | 787 | 2,658 | +238% | 0 | 0 | — |
case-08 | pass→pass | 2,585 | 1,939 | -25% | 1 | 1 | 0% | 448 | 2,522 | +463% | 0 | 0 | — |
case-09 | pass→pass | 6,158 | 12,654 | +105% | 1 | 1 | 0% | 1,104 | 4,305 | +290% | 0 | 0 | — |
case-10 | fail→fail | 15,605 | 5,651 | -64% | 1 | 1 | 0% | 2,873 | 2,605 | -9% | 0 | 0 | — |
case-11 | fail→fail | 17,097 | 8,194 | -52% | 1 | 1 | 0% | 2,690 | 2,685 | -0% | 0 | 0 | — |
case-12 | fail→pass | 8,655 | 5,932 | -31% | 1 | 1 | 0% | 1,373 | 3,092 | +125% | 0 | 0 | — |
case-13 | fail→fail | 11,045 | 39,550 | +258% | 1 | 1 | 0% | 1,587 | 2,768 | +74% | 0 | 0 | — |
case-14 | fail→pass | 20,954 | 2,394 | -89% | 1 | 1 | 0% | 1,074 | 2,527 | +135% | 0 | 0 | — |
case-15 | pass→fail | 11,107 | 6,427 | -42% | 1 | 1 | 0% | 1,550 | 2,600 | +68% | 0 | 0 | — |
case-16 | pass→pass | 10,451 | 11,979 | +15% | 1 | 1 | 0% | 1,821 | 4,019 | +121% | 0 | 0 | — |
case-17 | fail→pass | 17,130 | 2,310 | -87% | 1 | 1 | 0% | 1,050 | 2,448 | +133% | 0 | 0 | — |
case-18 | pass→fail | 7,572 | 11,025 | +46% | 1 | 1 | 0% | 1,238 | 2,947 | +138% | 0 | 0 | — |
case-19 | fail→fail | 44,706 | 7,892 | -82% | 1 | 1 | 0% | 1,838 | 2,822 | +54% | 0 | 0 | — |
case-20 | fail→fail | 14,504 | 5,281 | -64% | 1 | 1 | 0% | 2,497 | 2,524 | +1% | 0 | 0 | — |
case-21 | fail→fail | 12,030 | 20,709 | +72% | 1 | 1 | 0% | 2,197 | 6,268 | +185% | 0 | 0 | — |
case-22 | fail→pass | 10,804 | 3,829 | -65% | 1 | 1 | 0% | 1,713 | 2,692 | +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. 22 cases were attempted, and 7 counted toward the lift figure. The other 15 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 7 comparable cases. 7 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.