breathe
About
The `breathe` skill is a lightweight AI micro-reset that inserts a single, deliberate pause between actions to check alignment and prevent drift. It's designed for use between distinct steps like tool calls, file operations, or decisions to maintain focus. This provides a moment of meta-cognition without the full session of a `meditate` skill.
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
行間一覺之頓——察合、釋勢、新注返務。系統中最輕之自養。
用時
- 讀檔與改之間——改仍為正乎?
- 工具敗後,擇下行之前——頓而後應
- 諸行累勢或載過所旨
- 為習:凡二別行間插一息
- 覺欲速——欲本身為頓之信
入
- 必要:無——息唯用已在察中者
- 可選:無——增入破微重置之旨
法
第一步:頓
止。勿始下行、工具呼、或推理步。
此即全步。頓本有值。勢非恆汝友——或載汝過轉。
得: 前行與下行間真有隙。非表演之頓後仍行原本欲行者。
敗則: 若頓似不能——若下行急至不容一息——彼急乃頓須之最強信。不容一息之急幾恆反射,非理。
第二步:察
問一題。唯一。
擇:
- 「吾仍於務乎?」 — 旨已移自始乎?
- 「此為正下步乎?」 — 抑承前步之勢?
- 「末行學何?」 — 末行改吾之解乎?
- 「吾假乎知乎?」 — 下步據證抑據習?
一問,實答,繼。
得: 一清答。非析。非重評。一問,一實答。
敗則: 若答示不合——旨已移、下步誤、假未驗——勿於此修。記而進 meditate 或 center 以正。息為察,非修。
第三步:釋
放前行之果。或成或敗,已畢。
- 若成:釋快。下步須新注,非承成之勢
- 若敗:釋挫。下步須清推,非補敗
- 若模糊:釋當解模糊之欲。以所知繼
得: 下行自中地始,非自前行之情殘。
敗則: 若釋不易——若前行之果仍色注——此或須 heal 而非止於 breathe。一行之持久情殘示深於微重置所能解者。
第四步:繼
行下步。頓已畢。
息不生出、不更記、不生析。其生一刻之明,而刻耗於汝前進之瞬。
得: 下行以新注起,非以累勢。
敗則: 繼無敗態。頓已行其功——或已示深工須之。
驗
- 真頓發生(非表演)
- 一察題已問並實答
- 前行之情殘已釋
- 下行自清地起
- 總耗時短——息宜秒,非分
陷
- 息為遷延:若每行間皆息,非在息——乃拖。用息於自然轉點,非為延
- 息中析:察步為一問,非全評。若須更,用
meditate或center - 表演頓:走過場而無真止。旨在實斷勢,非儀
- 略釋:察合而持前步情荷。釋令下行清
- 重息:此為系統中最輕之技。若覺重,加之太多
參
meditate— 全清會,若息示深偏center— 結構再衡,若息示載分不合heal— 子系察,若息示持久題observe— 持察,若息之一察示值觀者
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.
