forecast-premortem — Claude Code skill: what it does, how to install
forecast-premortem is a Claude Code skill that stress-tests probabilistic forecasts by assuming failure before launch. It reveals overlooked risks and recalibrates overconfident estimates.
no license 108 installs ★ 203 updated 2026-09-01
npx skills add lyndonkl/claude --skill forecast-premortem -a claude-codeWhat forecast-premortem does
The skill implements Gary Klein's premortem technique for forecasting and decision-making. Rather than estimating success chances upfront, the workflow assumes failure already happened and traces the timeline backward. This perspective brings hidden threats, black swans, and unexamined dependencies into view.
Available modes cover failure premortems, success analyses for pessimistic outcomes below 20%, and multi-angle reviews through critic and observer personas. The process asks for your target prediction, initial probability, and confidence interval. It calculates the cumulative impact of specific breakdown modes to adjust probability figures.
Quantitative recalibration requires numeric inputs for probabilities and intervals. Without those baseline figures, the assessment remains purely qualitative.
What it helps with
- uncover hidden failure modes behind high-confidence projections
- stress-test pessimistic outcomes with probabilities under 20%
- calculate adjustments for overly narrow confidence intervals
- evaluate plans through conflicting skeptic and neutral viewpoints
Example prompts for the agent
- Run a failure premortem on our target to hit $10M ARR with 75% confidence
- Stress-test this pessimistic 10% commercialization forecast using backcasting
- Evaluate our release plan through the dragonfly eye perspective
How to install forecast-premortem
1Skills CLI (Vercel)
npx skills add lyndonkl/claude --skill forecast-premortem -a claude-code2Manually: put the files in place
~/.claude/skills/forecast-premortem/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/forecast-premortem/
1Skills CLI (Vercel)
npx skills add lyndonkl/claude --skill forecast-premortem -a codex2Manually: put the files in place
.agents/skills/forecast-premortem/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add lyndonkl/claude --skill forecast-premortem -a cursor2Manually: put the files in place
.cursor/skills/forecast-premortem/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install lyndonkl/claude skills/forecast-premortem2Manually: put the files in place
.github/skills/forecast-premortem/SKILL.md1Skills CLI (Vercel)
npx skills add lyndonkl/claude --skill forecast-premortem -a gemini-cli2Platform CLI
gemini skills install https://github.com/lyndonkl/claude --path skills/forecast-premortemManually: put the files in place
.devin/skills/forecast-premortem/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add lyndonkl/claude --skill forecast-premortem -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about forecast-premortem
How do I install forecast-premortem in Claude Code?
Run npx skills add lyndonkl/claude --skill forecast-premortem -a claude-code in your terminal. You can also save the file directly to ~/.claude/skills/forecast-premortem/SKILL.md.
What does the forecast-premortem skill do?
It inverts prediction analysis by presuming an outcome has failed, mapping potential causes backward in time. The output delivers adjusted probabilities alongside early warning indicators.
When should you use the success premortem workflow?
This option is designed for pessimistic forecasts below 20% likelihood. It presumes the low-probability success occurred to uncover overlooked enablers and counter cognitive bias.