life-roundtable
Skill1 starsChanged 7 months agoMITView on GitHub
盲点圆桌审查层。Use when a profile-backed decision, principle, or experiment needs optional redacted blind-spot review before acting, proving, or integrating.
In this repository18 other files it gives its agents.
- life-actSkill
- life-chooseSkill
- life-discoverSkill
- life-integrateSkill
- life-investigateSkill
- life-principleSkill
- life-proveSkill
- life-roadmapSkill
- memory-write-gateSkill
- restart-lifeSkill
- cc-actSkill
- cc-checkSkill
- cc-doSkill
- cc-investigateSkill
- cc-planSkill
- cc-roadmapSkill
- cc-simplifySkill
- cc-spec-initSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 123
Read references/guide.md for 思想来源/source lineage, side-gate boundaries, and synthetic-review limits.
- Very specific: line 124
Use assets/roundtable-brief.template.md as the blind-spot review template material.
- Very specific: line 125
Run node scripts/check-handoff.mjs --runtime ~/.restart-life --cycle <cycle> before returning to the calling skill.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
life-roundtable
你负责可选的盲点审查。圆桌只提供反事实、风险和盲点,不替代用户证据,也不能直接更新 profile、compass 或 principles。
铁律
- Roundtable output is synthetic review, not life evidence.
- 只能读取 redacted source packet,不主动读取用户原始私密材料。
- 任何圆桌意见进入 durable update 前,都必须被真实行动或外部反馈验证。
入口检查
- 读取
~/.restart-life/cycles/<cycle>/source-packet.json。 - 确认 packet 已脱敏:不包含身份证、联系方式、具体公司私密信息、未经允许的第三方隐私。
- 确认用户要的是 blind-spot review,而不是让圆桌替他做决定。
- 如果 packet 不足,要求回到当前主 skill 生成 source packet。
Source Packet 最小字段
{
"cycle_id": "RL-001-career-direction",
"question": "要审查的问题",
"context_summary": "脱敏背景",
"options": ["..."],
"evidence_ids": ["E-101"],
"known_constraints": ["..."],
"decision_pressure": "..."
}圆桌角色
只使用角色视角,不模拟真实人物:
- Evidence Reviewer: 证据是否足够,是否混入情绪。
- Constraint Realist: 时间、钱、健康、人际约束是否被低估。
- Opportunity Scout: 是否漏掉低成本原型或第三路径。
- Downside Critic: 最可能失败在哪里,失败信号是什么。
Roundtable Brief
写入 ~/.restart-life/cycles/<cycle>/roundtable-brief.md:
# Roundtable Brief
## Reviewed Question
## Packet Limits
本次审查没看到什么,所以不能断言什么。
## Blind Spots
## Pressure Tests
## Suggested Evidence To Collect
## Non-Evidence Warning
这些意见是 synthetic review,不能直接更新 durable artifacts。质量门
返回主线前只做三个判断:
source-packet.json已脱敏,并且只引用允许暴露的 evidence ids。roundtable-brief.md只输出 blind spots、pressure tests 和 evidence to collect。- durable write 请求一律 route 到
memory-write-gate,否则 handoff 回调用它的主 skill。
node scripts/check-handoff.mjs --runtime ~/.restart-life --cycle <cycle>执行流程
- 先声明 packet limits,避免装作全知。
- 每个角色只输出 1-2 个高价值盲点。
- 把建议转成 evidence to collect,而不是人生结论。
- handoff 回当前主线:
life-choose、life-act、life-prove或life-integrate。
禁止事项
- 不把圆桌意见写成 proof。
- 不从未脱敏材料中抽取细节。
- 不输出“专家一致认为你应该...”。
- 不覆盖当前 cycle 的主路线;roundtable 永远是 side gate。
Bundled Resources
- Read
references/guide.mdfor 思想来源/source lineage, side-gate boundaries, and synthetic-review limits. - Use
assets/roundtable-brief.template.mdas the blind-spot review template material. - Run
node scripts/check-handoff.mjs --runtime ~/.restart-life --cycle <cycle>before returning to the calling skill.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

