Write the failure story of your year, relationship, move, or big life bet in advance — imagine it's a year later and it went wrong, tell that story vividly, then mine it for the real risks and the cheap things that would have prevented them. Use when someone says 'I'm about to make a big life change', 'what could go wrong with this', 'de-risk my year', or is committing to something large and irreversible. Produces the failure narrative, the extracted risk list with preventatives, and the early-warning signs to watch. The life-scale sibling of a project premortem.
“I'm about to make a big life change.”“What could go wrong with this?”“De-risk my year.”“Run this skill in your browser: https://mohitagw15856.github.io/pm-claude-skills/skill/life-premortem.html”
What to give it
▸The big thing being committed to, and the horizon that matters — a year? the end of the sabbatical? the first year of the marriage?
▸Why it matters and what "success" would look like — you can't fail a goal you haven't named
▸What the user is quietly worried about but — talking themselves out of (this is often the real risk, pre-rationalized away)
▸What's reversible vs not, and what's already committed
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓The failure is told as a specific story, not a risk list wearing a narrative hat
✓The extracted risks are ones the user actually believes, including the quiet
✓worry they'd rationalized away
✓Each real risk has a concrete, cheap-now preventative
✓Early-warning signs are observable and time-anchored (you'd notice them by
✓month 3), not vague
✓It ends by weighing risk against reason — de-risking, not vetoing the dream
⚠️ What it refuses to do
Do not let it become a generic risk checklist — the story frame is the engine;
without it the honesty doesn't come
Do not use it to kill the user's brave thing — the goal is going in clear-eyed,
and a mitigated risk is a reason to prepare, not to quit
Do not surface only comfortable risks — the quiet, pre-rationalized worry is
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp