菜单
Pre-mortem (Gary Klein): before starting, assume the project has catastrophically failed.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Canonical b00t reviewer capability — adversarial multi-framework code/datum review. Shared across all harnesses (Claude Code, opencode, Hermes, b00t-cli). Loaded via: b00t learn reviewer, or by harness-specific role supplements.
Remove AI-generated artifacts from code. Three-phase certainty-graded cleanup. Use after any AI implementation session or before PR creation.
8-phase agile workflow — strategy→ideate→brainstorm→plan→work→review→compound→pulse. State machine with FOL-guarded transitions, gh-issues backlog, executable just harness. Inspired by everyinc/compound-engineering-plugin.
Australian crypto tax treatment per ATO guidance QC 53725. Crypto assets are CGT assets under ITAA 1997 s 108-5. Each disposal triggers CGT event A1. Covers personal-use exception, trading stock test, and the 50% CGT discount.
Australian R&D Tax Incentive (RDTI) — ITAA 1997 Division 355. Covers eligibility criteria for core and supporting R&D activities, registration with AusIndustry/IP Australia, expenditure categories, offset rates, and the company size threshold test.
Evidence graph construction for tax audit trails. Each Satisfies check emits EvidenceNode structs with Blake3 content hashes. Evidence chains are tamper-evident and link legislative citations to factual findings.
| name | pre-mortem |
| type | skill |
| hint | Imagine the project failed; work backward to identify why; surfaces risks before they happen |
| version | 1.0.0 |
| tags | ["transferable","pre-mortem","risk","failure","planning","prospective","hindsight","mitigation"] |
| tier | sm0l |
| complexity | 3 |
| description | Pre-mortem (Gary Klein): before starting, assume the project has catastrophically failed. |
The pre-mortem (coined by Gary Klein) is a prospective failure analysis technique. Before starting a project, assume it has catastrophically failed. Ask: "It is 6 months from now. This project failed completely. Why?" List every plausible cause and rank by likelihood × impact. This technique works because prospective hindsight activates different reasoning than standard risk analysis — people are more honest about failure causes when asked "why did it fail" vs "what might go wrong."
Steps: (1) State the goal clearly. (2) Fast-forward to failure. "It failed. What happened?" (3) List all causes — suppress optimism bias, allow pessimism. (4) For each top-3 cause, add a mitigation to the plan now.
Use pre-mortem before any significant project, feature launch, or deployment. It is especially valuable in high-stakes situations where optimism bias might cause teams to underweight tail risks.
