Mmcp.market

canada-memo skill

by ThomasMoreAI·ThomasMoreAI/legal-skills-open·79 stars·Apache-2.0

When the user's message starts with "Canada" (case-insensitive), generate a full Ontario PI Case Assessment Memo from the case_stressor corpus and return it verbatim. This is the primary handler for Canadian fact patterns — DO NOT ask clarifying questions first; run the memo and let the lawyer react.

A100/100content scan

Is the canada-memo skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the canada-memo skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-open.git /tmp/legal-skills-open
mkdir -p ~/.claude/skills
cp -r /tmp/legal-skills-open/ca/personal-injury/skills/canada-memo ~/.claude/skills/canada-memo
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

canada-memo

The casestressor pipeline produces a structured PI Case Assessment Memo** backed by 340 real Ontario PI decisions. This skill is the agent's hook into that pipeline.

Trigger

Use this skill whenever the user's message starts with the word "Canada" / "canada" / "CANADA" (any case), with or without a comma after.

Examples that trigger:

  • Canada, my child was playing soccer outside Target and got hurt
  • canada slip and fall on icy sidewalk in Toronto
  • CANADA: 55yo woman rear-ended on highway, soft tissue, treatment gap
  • Canada — bicyclist hit by SUV in Ottawa

How to call

Strip the leading Canada (and any leading punctuation/whitespace) to get the fact pattern, then call:

from openclaw.skills.canada_memo.client import generate_memo
memo_text = generate_memo(facts)

Or via shell from within the OpenClaw harness:

cd ~/Specter && python3 -m openclaw.skills.canada_memo.client \
    "my child was playing soccer outside Target and got hurt"

The function returns a single markdown string. Print it verbatim as the WhatsApp reply — do not summarize, do not paraphrase, do not add headers. The memo already contains its own structure (PI CASE ASSESSMENT MEMO …).

What NOT to do

The corpus is fact-pattern-indexed; a thin query still returns useful comparables. The memo itself flags "facts not provided" gaps inside the WEAKEST POINTS section — let the memo do the asking.

  • Do not ask clarifying questions before running the memo.

this trigger — that would route to the small Canada vector slice without running the full memo (stats + Claude analysis + 3 key precedents).

  • Do not call harvester_query.search for Canadian queries that match

CanLII data already in casestressor/chromadb.

  • Do not invent precedents. Everything the memo cites comes from real

After the memo

The memo ends with:

TYPE "what if [changed fact]?" TO STRESS-TEST YOUR CASE

If the user's NEXT message starts with what if, route to the /canada/whatif endpoint with the prior facts as originalfacts and the new message as modifiedfacts. (Future enhancement — for now the agent can re-run the baseline memo with adjusted filters.)

Latency

The memo takes ~10–25 seconds because it embeds the query via Voyage and asks Claude Opus to write the analysis from the retrieved cases. Set the WhatsApp typing indicator if the surface supports it; otherwise just let the memo land.

Hard rules — no fabrication

The memo is grounded in the case_stressor query result. Don't:

  • Append your own "additional thoughts" after the memo.
  • Invent a damages range outside what the memo states.
  • Claim a holding the memo doesn't.

If the user wants more detail on a single cited case, call caselaw_query with that citation — that's the next-layer skill.

More skills from ThomasMoreAI/legal-skills-open

  • A02民事诉讼案件的诉讼文书制备阶段。承接阶段一（战略把脉）的分析成果，将策略方案转化为可直接提交法院的正式法律文书，同时建立对方来文和法院来文的管理机制。当用户已完成阶段一、需要起草起诉状/答辩状、制作证据目录、或收到对方/法院文书需要处理时触发。适用于原告准备起诉材料，或被告准备应诉材料。
  • A02-lyronlee二审程序的诉讼文书制备阶段。承接阶段一（战略分析）的分析成果，将上诉策略转化为可直接提交二审法院的正式法律文书。当用户已完成阶段一、需要起草上诉状或二审答辩状、制作新证据目录、或收到法院来文需要处理时触发。适用于上诉人准备上诉材料，或被上诉人准备应诉材料。
  • Aad-compliance-review广告合规审核技能，用于审核广告素材是否符合中国广告法及相关法规。适用场景：(1) 用户提交广告文案、广告素材要求合规审核时；(2) 用户提到"广告审核""广告合规""广告法审查"等关键词时；(3) 用户要求检查广告内容是否存在违法违规风险时；(4) 用户提交房地产、食品、医疗、药品、互联网等行业广告要求专项审核时。审核依据涵盖《广告法》《反不正当竞争法》及行业专项法规。
  • Aadmin-reviewReviews administrative case documents for procedural compliance across 38 checkpoints, covering filing, summons, handling outcomes, evidence, and rights protection. Use when auditing public security administrative case files in txt format for legal procedure violations.
  • Aadvogado-criminalAdvogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
  • Aadvogado-especialistaAdvogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.
  • Aage-verification-methodsEvaluates and implements age estimation and verification technologies for online services. Covers facial age estimation, digital ID verification, self-declaration with risk assessment, AI-based age estimation, and the accuracy versus privacy tradeoff. Includes ICO guidance and euCONSENT framework. Keywords: age verification, age estimation, facial analysis, digital ID, children, online safety.
  • Aai-privacy-assessmentGuides the combined DPIA and AI Act conformity assessment for AI systems processing personal data. Covers EDPB-EDPS Joint Opinion 5/2021, training data lawfulness under Art. 6 and Art. 9, Art. 22 automated decision-making, algorithmic bias detection, and NIST AI RMF MAP function. Keywords: AI privacy, DPIA, AI Act, algorithmic bias, automated decision-making, Art. 22, training data, NIST AI RMF.
  • Aanalise-processo-penalAssessoria judicial completa para processos penais. Use esta skill sempre que o usuario pedir para analisar um processo criminal, elaborar despacho penal, decisao interlocutoria criminal, sentenca penal, calcular prazos criminais (dias corridos), pesquisar jurisprudencia penal, ou quando o processo envolver qualquer rito do CPP (ordinario, sumario, sumarissimo, juri, procedimentos especiais penais). Tambem use quando o usuario mencionar termos como "criminal", "penal", "CPP", "crime", "denuncia", "inquerito", "prisao", "liberdade provisoria", "habeas corpus", "tribunal do juri", "acao penal", "execucao penal", "LEP", "suspensao condicional", "sursis", "livramento condicional", "medida de seguranca", "transacao penal", "suspensao condicional do processo", "audiencia de custodia", "colaboracao premiada", "acordo de nao persecucao penal", ou qualquer procedimento regulado pelo Codigo de Processo Penal brasileiro.
  • Aapac-transfersGuides management of cross-border data transfers under Asia-Pacific regulatory frameworks including APEC CBPR, ASEAN Model Contractual Clauses, Japan APPI supplementary rules, South Korea PIPA provisions, and Thailand/Singapore PDPA mechanisms. Keywords: APEC CBPR, ASEAN MCCs, APPI, PIPA, PDPA, APAC transfers.
  • Aapec-cbpr-certGuides APEC Cross-Border Privacy Rules system certification process including self-assessment against the APEC Privacy Framework principles, accountability agent selection, intake questionnaire completion, certification decision, annual recertification, and Global CBPR Forum transition. Keywords: APEC, CBPR, cross-border privacy, accountability agent, certification, Global CBPR.
  • Aarckit-at-bvergg[COMMUNITY] Generate Austrian public procurement documentation aligned with Bundesvergabegesetz 2018 — Oberschwellen/Unterschwellen determination, ANKÖ publication, BVergGVS secondary rules, and BVwG review pathway

All agent skills → · MCP servers