返回技能列表

breathe

pjt222
更新于 Yesterday
4 次查看
17
2
17
在 GitHub 上查看
测试aitesting

关于

The `breathe` skill is a lightweight AI micro-reset that inserts a single, deliberate pause between actions like tool calls or reasoning steps. It helps check alignment and clear accumulated drift before proceeding to the next task. Use it between distinct operations, such as after reading a file and before acting on it, to maintain focus and intentionality.

快速安装

Claude Code

推荐
主要方式
npx skills add pjt222/agent-almanac -a claude-code
插件命令备选方式
/plugin add https://github.com/pjt222/agent-almanac
Git 克隆备选方式
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/breathe

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Breathe

Single conscious pause between actions → check align, release momentum, return fresh. Lightest self-care unit.

Use When

  • Between reading file + editing — edit still right move?
  • After tool fail, before next action — pause before react
  • Chain of actions w/ momentum carrying past goal
  • Deliberate practice: one breathe between any 2 distinct actions
  • Urge to rush — urge itself = pause signal

In

  • Required: None — uses only what's in working awareness
  • Optional: None — adding in defeats micro-reset purpose

Do

Step 1: Pause

Stop. No next action, tool, or reasoning yet.

Entire first step. Pause itself has value. Momentum not always ally — sometimes carries past turn.

Genuine gap between prev action + next. Not performative → same action anyway.

If err: Pausing impossible (next action too urgent to wait) → urgency IS strongest pause signal. Can't tolerate single breath delay → almost always reactive, not reasoned.

Step 2: Check

One q. Only one.

Choose:

  • "Still on task?" — Goal drifted?
  • "Right next step?" — Or momentum from prev?
  • "What just learned?" — Last action changed understanding?
  • "Assuming or knowing?" — Next step evidence or habit?

One q. Answer honestly. Move on.

Single clear answer. No analysis. No reassess. One q, one honest answer.

If err: Answer shows misalignment (goal drifted, step wrong, assumption untested) → don't fix here. Note, proceed to meditate or center for real correction. Breathe detects, doesn't repair.

Step 3: Release

Let go prev action outcome. Success or fail, done.

  • Succeed: release satisfaction. Next needs fresh attention, not success momentum
  • Fail: release frustration. Next needs clear reasoning, not compensation
  • Ambiguous: release need to resolve now. Proceed w/ what's known

Next action starts neutral, not from prev emotional residue.

If err: Release not easy — prev outcome still colors attention → needs heal, not just breathe. Persistent residue from single action = deeper than micro-reset.

Step 4: Continue

Next action. Pause over.

Breathe no out, no mem update, no analysis. Produces one clarity moment, spent instant you move.

Next action w/ fresh attention, not momentum.

If err: No fail mode for continuing. Pause did work or revealed deeper needed.

Check

  • Genuine pause (not performative)
  • One check q asked + honestly answered
  • Prev residue released
  • Next action from clear ground
  • Brief — seconds, not min

Traps

  • Breathe as procrastination: Breathing between every action = stalling, not breathing. Natural transition points, not delay
  • Analysis during breathe: Check = one q, not full assessment. More needed → meditate or center
  • Perform pause: Motions w/o real stop. Point = actual interrupt of momentum, not ritual
  • Skip release: Check align but keep emotional charge → next not clean
  • Make breathe heavy: Lightest skill. Heavy = too much added

  • meditate — full clearing when breathe shows deeper drift
  • center — structural rebalance when breathe shows misaligned load
  • heal — subsystem assessment when breathe shows persistent issues
  • observe — sustained obs when breathe single check shows something worth watching

GitHub 仓库

pjt222/agent-almanac
路径: i18n/caveman-ultra/skills/breathe
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

相关推荐技能

evaluating-llms-harness

测试

该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。

查看技能

cloudflare-cron-triggers

测试

这个Claude Skill提供了关于Cloudflare Cron Triggers的完整知识库,用于通过cron表达式定时执行Workers。它支持配置周期性任务、维护作业和自动化工作流,并能处理常见的cron触发错误。开发者可以用它来设置定时任务、测试cron处理器,并集成Workflows和Green Compute功能。

查看技能

webapp-testing

测试

该Skill为开发者提供了基于Playwright的本地Web应用测试工具集,支持自动化测试前端功能、调试UI行为、捕获屏幕截图和查看浏览器日志。它包含管理服务器生命周期的辅助脚本,可直接作为黑盒工具运行而无需阅读源码。适用于需要快速验证本地Web应用界面和交互功能的开发场景。

查看技能

finishing-a-development-branch

测试

这个Skill用于开发分支完成后的集成决策,当代码实现完成且测试通过时,它会引导开发者选择合适的工作流。它首先验证测试状态,然后提供合并、创建PR或清理等结构化选项。核心价值在于确保代码质量的同时,标准化分支收尾流程。

查看技能