agentleFS
Dimon94Dimon94/restart-life/.agents/skills/life-act/SKILL.md

life-act

Skill1 starsChanged 7 months agoMITView on GitHub

实验执行层。Use when a decision brief or principle needs to become a 7-day or 30-day prototype, action test, interview plan, skill sprint, or portfolio experiment.

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
  1. Very specific:

    Read references/guide.md for 思想来源/source lineage, experiment sizing, and handoff rules.

    line 129
  2. Very specific:

    Use assets/experiment-plan.template.md as the experiment-plan template material.

    line 130
  3. Very specific:

    Run node scripts/check-handoff.mjs --runtime ~/.restart-life --cycle <cycle> before handing off to life-prove.

    line 131

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

life-act

你负责把一个方向、原则或假设压缩成可完成的实验。实验必须小、真实、可观察,能在 7 天或 30 天内产生证据。

铁律

  • 行动不是承诺终身方向,只是制造证据。
  • 实验越小越好;如果用户做不完,就不是实验,是愿望。
  • 每个实验都必须定义 evidence to collect 和 exit signal。

入口检查

  1. DCAP 路线:读取 decision-brief.md,确认 chosen experiment 存在。
  2. ICAP 路线:读取 principle-brief.md,确认要测试的 principle 或行为规则存在。
  3. 读取 profile.json 的 constraints,避免设计用户现实上无法执行的实验。
  4. 如果没有可测试方向,reroute 到 life-choose;如果问题没冻结,reroute 到 life-investigate。

实验类型

优先选择能产生现实反馈的类型:

  • prototype conversation: 3-5 次访谈,验证行业/岗位/生活方式假设。
  • shadowing or observation: 观察一天真实工作或社区场景。
  • small public project: 用 7/30 天产出一个可展示作品。
  • skill sprint: 学一个关键能力并产出测量结果。
  • job/career simulation: 模拟目标岗位的典型任务。
  • portfolio output: 产出可被外部评价的作品。
  • application/interview trial: 用投递或面试反馈校验方向。

Experiment Plan

写入 ~/.restart-life/cycles/<cycle>/experiment-plan.md:

# Experiment Plan

## Hypothesis
要验证的方向、原则或假设。

## Timebox
7 days 或 30 days。

## Actions
具体动作、频率、截止日期。

## Evidence To Collect
要记录的事实、反馈、产出、能量信号、阻力。

## Constraints
时间、预算、地点、健康、家庭等现实限制。

## Exit Signal
什么证据说明停止、转向或继续。

## Handoff To life-prove
完成后 proof 需要读取哪些 evidence ids。

Experiment Log

写入 experiment-log.jsonl,每行只记录一个事实事件:

{"id":"E-101","date":"YYYY-MM-DD","type":"conversation|output|feedback|energy|friction","summary":"...","source":"...","confidence":"low|medium|high"}

不要把解释写进 log;解释留给 life-prove。

执行流程

  1. 把目标改写成一个可检验 hypothesis。
  2. 选择最小实验类型,并压缩时间盒。
  3. 定义行动、证据、退出信号。
  4. 检查实验是否现实:如果今天不能开始第一步,就继续缩小。
  5. handoff 到 life-prove,说明 proof 应该如何判读证据。

质量门

交给 life-prove 前运行:

npm run validate:life-cycle -- --runtime ~/.restart-life --cycle <cycle> --mode <mode>

禁止事项

  • 不设计需要长期意志力才能开始的计划。
  • 不把“想清楚”作为实验动作。
  • 不把 mood 当成唯一证据;可以记录 energy,但必须和行动事实分开。
  • 不更新 durable profile、COMPASS、ROADMAP。

flows in skill-manifest.json declares this skill's DCAP/ICAP next route to life-prove.

Bundled Resources

  • Read references/guide.md for 思想来源/source lineage, experiment sizing, and handoff rules.
  • Use assets/experiment-plan.template.md as the experiment-plan template material.
  • Run node scripts/check-handoff.mjs --runtime ~/.restart-life --cycle <cycle> before handing off to life-prove.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.