agentleFS
ohanyanohanyan/adulting/skills/reset/SKILL.md

reset

Skill1 starsChanged 7 months agoMITView on GitHub

Acute stress reset. Physiological sigh (Huberman) plus Jocko "Good." reframe. Use when triggered, angry, overwhelmed, or about to send the email you will regret.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not keep typing. Do this first.

    line 8
  2. Distinctive:

    Do it with the user. Count the rounds.

    line 16
  3. Distinctive:

    If this is about a message you are about to send (email, text, Slack): do not send it for 60 minutes.

    line 34
  4. Distinctive:

    If this is about a decision you are about to make: sleep on it.

    line 36
  5. Distinctive:

    If no, do not act yet. The moment is lying to you about its importance.

    line 42
  6. Very specific:

    If the user said "yes, I sent it anyway" or "yes, I snapped" — gently suggest /repair.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “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

/reset

Do not keep typing. Do this first.

Step 1: Physiological sigh (60 seconds)

Two sharp inhales through the nose, one long exhale through the mouth. Repeat three times.

This is not meditation. It is a specific breathing pattern that downregulates the sympathetic nervous system in roughly one minute. Andrew Huberman's Stanford lab has it as the fastest voluntary stress intervention known.

Do it with the user. Count the rounds.

Step 2: The Jocko "Good." reframe

"Say the word 'Good.' out loud. Then answer: what does this situation make possible? What can I now learn, fix, or prevent?"

Jocko's point: if you tell yourself good about every bad thing, eventually you stop flinching. You stop being shocked that the world broke. You start looking for the move.

Step 3: The ownership check

Three questions, one sentence each:

  1. What part of this is mine? (Not "whose fault is it" — what part of the outcome was inside my control and I missed it?)
  2. What part is not mine? (And therefore I can stop ruminating on it.)
  3. What is the next right action in the next 10 minutes?

Step 4: The delay rule

If this is about a message you are about to send (email, text, Slack): do not send it for 60 minutes. Save as draft. Come back.

If this is about a decision you are about to make: sleep on it. Real 24 hours. Almost no decision is worse for being made tomorrow.

Step 5: If the stakes are the people you love

One extra question: "Will I be proud of how I acted here in a week?"

If no, do not act yet. The moment is lying to you about its importance.

Output

One-line log to ~/adulting-data/journal/reset-log.md:

<date> <time>  trigger: <what>  next action: <what>  sent/decided: <Y/N>

If the user said "yes, I sent it anyway" or "yes, I snapped" — gently suggest /repair.

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.