メニュー
Pre-mortem analysis that imagines a plan has failed, then works backward to identify causes and preventions. Use before launches, major decisions, or risky initiatives to surface hidden risks.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | premortem |
| description | Pre-mortem analysis that imagines a plan has failed, then works backward to identify causes and preventions. Use before launches, major decisions, or risky initiatives to surface hidden risks. |
| user-invocable | true |
Imagine the plan has completely failed, then work backward to identify what went wrong and how to prevent it.
Set the scene: "It's [timeframe] in the future. This initiative was a complete disaster. Looking back, what happened?"
Generate failure scenarios without filtering for likelihood—get everything on the table first, then prioritize.
The Plan Summarize what's being attempted and the success criteria.
Time Jump "It's [X months] later. This has failed completely. The outcome: [describe the disaster vividly]."
What Went Wrong
Generate 8-12 plausible failure causes across categories:
| Category | Failure Mode | How It Played Out |
|---|---|---|
| Execution | [What failed] | [The story of how] |
| External | [What failed] | [The story of how] |
| People | [What failed] | [The story of how] |
| Technical | [What failed] | [The story of how] |
| Assumptions | [What failed] | [The story of how] |
Risk Prioritization
| Failure Mode | Likelihood | Impact | Priority |
|---|---|---|---|
| ... | High/Med/Low | High/Med/Low | 1-5 |
Top 3 Risks & Mitigations
For each top risk:
Pre-Mortem Insights What did this exercise reveal that wasn't obvious before?
Revised Confidence After this analysis, how confident are you in success? What would increase confidence?
$ARGUMENTS
Guide through a libsignal pin bump in signal-go. Use this skill whenever the user mentions bumping libsignal, updating the libsignal version, a new libsignal release, signal_ffi.h changes, or the canary workflow flagging a new upstream release. This is a high-risk operation — invoke this skill to make sure no steps are missed.
Cut a new signal-go release. Use this skill whenever the user mentions cutting a release, tagging a version, publishing a release, bumping the version, or shipping v0.x.y. Also invoke when the user asks how to release or what steps are needed before shipping.
Create a new Architecture Decision Record (ADR) for signal-go. Use this skill whenever the user mentions writing an ADR, filing an ADR, "should this have an ADR", adding a new decision record, or when any CLAUDE.md rule triggers an ADR (new Go dep, store format change, security trade-off, new protocol, new package). Also invoke proactively when the user is about to make a change that the CLAUDE.md "When to ask first" list covers.
