Skip to content

borghei/Claude-Skills / project-management/discovery/pre-mortem

pre-mortem

Verified

Runs a pre-mortem that sorts launch risks into evidenced tigers, paper tigers and unspoken elephants, each with an owner. Use when a big launch, build or migration is coming, or the team has a bad feeling it cannot name.

assets/sample_risks.json

View on GitHub
{
  "risks": [
    {
      "description": "Authentication service has had 3 outages in the last month; a launch-day outage is plausible",
      "category": "tiger",
      "evidence": "3 incident reports in the last 30 days (P1-level severity)",
      "urgency": "launch_blocking",
      "owner": "Platform lead",
      "decision_date": "2026-06-10"
    },
    {
      "description": "CSV export does not handle unicode characters correctly",
      "category": "tiger",
      "evidence": "QA found the bug last week; affects ~15% of accounts with non-ASCII data",
      "urgency": "fast_follow"
    },
    {
      "description": "No automated monitoring alerts for the new data pipeline",
      "category": "tiger",
      "evidence": "Pipeline deployed 2 weeks ago; only manual log checks exist currently",
      "urgency": "track"
    },
    {
      "description": "A major competitor might copy our feature within weeks",
      "category": "paper_tiger",
      "evidence": "Competitor's last release was 9 months ago; their team is focused on a different market segment"
    },
    {
      "description": "Users might not discover the new analytics dashboard",
      "category": "paper_tiger",
      "evidence": "Dashboard is the new default landing page; usability test showed 100% discovery rate"
    },
    {
      "description": "The PM who originally championed this feature has left the company; nobody has re-validated requirements with current customers",
      "category": "elephant",
      "evidence": "PM departed 6 weeks ago; no customer interviews since then; team has been building to the original spec"
    },
    {
      "description": "The team is experiencing burnout after 3 consecutive crunch sprints; quality may be declining",
      "category": "elephant",
      "evidence": "Two engineers mentioned burnout in 1-on-1s; PR review thoroughness has visibly dropped"
    }
  ]
}
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall