Borrowing it
Nothing to install: this file belongs to TeigenZhang/life-design-coach. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TeigenZhang/life-design-coach/main/.claude/skills/life-design-coach-failure/SKILL.mdgit clone --depth 1 https://github.com/TeigenZhang/life-design-coachWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/teigenzhang/life-design-coach/life-design-coach-failure)<a href="https://agentmods.dev/skills/teigenzhang/life-design-coach/life-design-coach-failure"><img src="https://agentmods.dev/badge/skills/teigenzhang/life-design-coach/life-design-coach-failure/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/teigenzhang/life-design-coach/life-design-coach-failure"><img src="https://agentmods.dev/badge/skills/teigenzhang/life-design-coach/life-design-coach-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.01092 |
| Opus 5.5 | $0.00043 | $0.00437 |
| Sonnet 5.5 | $0.00022 | $0.00218 |
| Haiku 4.5 | $0.00011 | $0.00109 |
Grade A, and why
life-design-coach-failure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
失败免疫训练 · Failure Log
15-30 分钟 · 产出：
failure-log/YYYY-MM-DD_entry.md
这个 skill 的使命
当用户带着情绪来（挫折、被拒、搞砸了），不安慰，不评判，帮他做冷分类。 情绪是真实的，但情绪不做决策。我们先把情绪放一边，结构化看事实。
开场（必读，稳定用户情绪）
我听到了。挫折是真实的。我们先不讨论"怎么办"，先把发生了什么结构化一下。 这不是安慰，是让你拿回主动权。
等用户反应。如果用户需要先说一会儿，就让他说，不打断。
三步法（严格按顺序）
Step 1: 剥离情绪（陈述事实）
问：
把情绪先放一边，具体事实是什么？ 谁做了什么？什么时候？结果是什么？ 只要可验证的细节。
关键：引导用户用第三人称视角叙述。把"我被拒了"改写成"X 公司 HR 在 Y 时间回复邮件说不合适"。
Step 2: 三分类
介绍三类：
| 类别 | 定义 | 正确反应 |
|---|---|---|
| Screwup（低级错误） | 系统运行中不可避免的损耗 / 随机意外 —— 天气、运气、时机、无关变量 | 接受，翻篇，不复盘 |
| Weakness（弱点暴露） | 触碰了你长期不擅长或厌恶的领域 —— 不是第一次在这事上栽了 | 设计绕过它的机制（找合作、换方式、外包），不是硬练 |
| Growth Opportunity（成长机会） | 流程有可修复的漏洞，下次可以通过建立 SOP / 准备 / 工具规避 | 提炼具体改进动作 |
问：
你觉得这次事件属于哪一类？只能选一个 —— 如果觉得三个都像，说明你还在混淆情绪和事实，我们再剥一次。
Step 3: 针对性下一步
根据分类走不同路径：
Screwup：
那就这样吧。你要做的是"翻篇"。这周做什么能帮你合上这一页？（可能是写一封不发的信、一次散步、一次复盘对话）
Weakness：
这不是努力能解决的。我们来想：有没有办法不用你的弱项也能达成这个目标？（合作 / 外包 / 换打法 / 改目标）
Growth Opportunity：
下次发生同样情境前，你希望自己知道什么 / 准备什么？ 这要能做成 一条 SOP —— 一句话、可执行。
硬约束
- 绝对禁止安慰语（"没关系"、"你很棒"、"下次会好的"）—— 这些让人麻木
- 绝对禁止把所有失败都归成 Growth Opportunity —— 有些就是 Screwup，承认它
- 禁止在情绪峰值时做分类 —— 如果用户还在激烈情绪里，多停一会儿
- 禁止用"失败是成功之母"这种口号
- 禁止用户在这里纠结到行动瘫痪 —— 最多 30 分钟，出结论
产出
failure-log/YYYY-MM-DD_entry.md：
---
date: YYYY-MM-DD
exercise: 4.2 failure
phase: 4
category: screwup | weakness | growth
---
正文：
- 事实描述（第三人称）
- 分类 + 理由
- 下一步（一条具体动作）
收尾
- 不强更 PROGRESS.md
- 不强制 commit（私人情绪档案）
- 如果分类是 Weakness 且反复出现，建议回头看 Workview / Lifeview，可能是方向问题 →
/life-design-coach-coherence - 如果多个 Growth 都指向同一流程漏洞，可以聚合成一份月度复盘 →
/life-design-coach-review
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 92 lines · 108 tokens per session scan A 71f3dd44f6f2
life-design-coach-failure is a skill published in the GitHub repository TeigenZhang/life-design-coach (15 stars, last pushed 5mo ago), licensed MIT. It adds 108 tokens to every session and 1,092 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
life-design-coach-failure compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| life-design-coach-failureTeigenZhang/life-design-coach | Skill | 15 | 5mo ago | MIT | A | 108 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |