canada-memolisted

# canada-memo The case_stressor 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: ```python from openclaw.skills.canada_memo.client import generate_memo memo_text = generate_memo(facts) ``` Or via shell from within the OpenClaw harness: ```bash 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 - **Do not** ask clarifying questions before running the memo. 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 —