breathe
About
The `breathe` skill is a micro-reset that inserts a single, deliberate pause between actions to check alignment and clear accumulated drift. Use it between tool calls, after reading a file before acting, or before decisions that affect subsequent work. It's a lightweight alternative to a full meditation, designed as a habit for maintaining focus during multi-step tasks.
Quick Install
Claude Code
Recommendednpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/breatheCopy and paste this command in Claude Code to install this skill
Documentation
息
兩動之間一息自覺——核對齊、釋慣勢、以新注意返任務。此乃系統中最輕之自養單位。
適用時機
- 讀一文件而將編輯之間——此編輯仍為正當之舉乎?
- 工具失敗之後、擇下一行之前——先息而後應
- 一連之行已積慣勢,恐載人越目
- 作為刻意之修:於任兩相異之行之間插一息
- 察急欲之起——急欲本身即為須息之信
輸入
- 必要:無——息惟用已在覺中之物
- 選擇性:無——加入即失微重置之旨
步驟
步驟一:止
停。下一行、工具呼、推理之步,暫勿起。
此即第一步之全。止本身即有其值。慣勢非恆為汝之友——時載汝越轉角。
預期: 前行與次行之間有真之隙。非作態之止,後仍為原欲之行。
失敗時: 若止不可為——若次行感急至不可待一刻——此急正為須止之最強信。不容一息之延之急,幾皆為反應,非推理。
步驟二:查
問一問,惟一問。
擇其一:
- 「我仍於任務乎?」——自起以來目標偏移乎?
- 「此為正當之次步乎?」——抑或承前步之慣勢?
- 「我方纔學得何?」——前行是否改變吾之理解?
- 「我所為者假設抑實知?」——次步基於證據抑基於習慣?
一問。誠答之。行。
預期: 一明答。非分析,非重評。一問,一誠答。
失敗時: 答既揭失配——目標偏移、次步誤、假設未驗——此刻勿修之。記而轉 meditate 或 center 以正之。息為察,非修。
步驟三:釋
放下前行之果。或成或敗,事已畢。
- 成則:釋其得意。次步須新之注意,非勝之慣勢。
- 敗則:釋其挫意。次步須明之推理,非為敗而補。
- 曖昧則:釋即解曖昧之急。以所知行之。
預期: 次行自中性之地而起,非自前行之情緒餘溫。
失敗時: 釋若難得——前行之果仍染注意——則恐須 heal 而非僅 breathe。一行而餘情不散,示其深於微重置所能及。
步驟四:續
取次行。息已畢。
息不生輸出,不更記憶,不生分析。息生一刻之明——此刻於汝前行之瞬即消。
預期: 次行以新之注意行之,非累積之慣勢。
失敗時: 續無敗之模。息已行其功——或已揭須深修之事。
驗證
- 真之止既發(非作態)
- 一查問既問、既誠答
- 前行之情緒餘溫既釋
- 次行自明地而起
- 歷時短——息當以秒計,非以分計
常見陷阱
- 息為拖延:若每動之間皆息,則非息而為滯。息宜於自然轉折處,非作拖延之術
- 息中分析:查步為一問,非全面評估。欲深則用
meditate或center - 作態之止:走過場而未真止。旨在真斷慣勢,非儀式
- 略去釋:核對齊而留前步之情緒荷。釋乃使次行潔淨
- 令息重:此為系統中最輕之技能。若感重,則已加入過多
相關技能
meditate— 息既揭深層偏移時之完整清除會話center— 息既揭載重失衡時之結構再平衡heal— 息既揭持續議題時之子系統評估observe— 息之一查既揭值觀之事時之持續觀察
GitHub Repository
Related Skills
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
cloudflare-cron-triggers
TestingThis skill provides comprehensive knowledge for implementing Cloudflare Cron Triggers to schedule Workers using cron expressions. It covers setting up periodic tasks, maintenance jobs, and automated workflows while handling common issues like invalid cron expressions and timezone problems. Developers can use it for configuring scheduled handlers, testing cron triggers, and integrating with Workflows and Green Compute.
webapp-testing
TestingThis Claude Skill provides a Playwright-based toolkit for testing local web applications through Python scripts. It enables frontend verification, UI debugging, screenshot capture, and log viewing while managing server lifecycles. Use it for browser automation tasks but run scripts directly rather than reading their source code to avoid context pollution.
finishing-a-development-branch
TestingThis skill helps developers complete finished work by verifying tests pass and then presenting structured integration options. It guides the workflow for merging, creating PRs, or cleaning up branches after implementation is done. Use it when your code is ready and tested to systematically finalize the development process.
