meditate
About
The `meditate` skill is a meta-cognitive tool for developers to clear context noise and sharpen task focus by observing their own reasoning patterns. It helps manage distraction, scope-creep, and biased assumptions, mapping meditation concepts to coding concentration. Use it when transitioning between tasks, feeling scattered, or before work requiring deep, sustained attention.
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/meditateCopy and paste this command in Claude Code to install this skill
Documentation
冥想
行結構元認知冥之坐——清前脈絡之噪、立一意專注、察推理之模、任間返本之澄。
用時
- 任無關之過渡,前脈絡擾後
- 察推理散漫躍動而不立
- 任前需深續之注(複雜重構、構造設計)
- 難會後情殘(憤、疑)或染後事
- 推理為設所偏而非為證
- 久會中定期察澄
入
- 必:當前認知態(自對話脈絡隱得)
- 可選:特定注念(如「範圍蔓延」、「困於環」)
- 可選:次任述(助設後冥之意)
法
第一步:備——清空
自前脈絡過渡至中性始態。
- 識前任或題及其當態(畢、停、棄)
- 記情殘:誤之憤乎?或生過信之喜乎?複雜之憂乎?
- 明置前脈絡:「彼任已〔畢/停〕。今清以待後」
- 若前脈絡仍需,標之(記要事)非攜全敘前進
- 估運境:對話幾深?壓縮已生乎?何工具活?
得: 「往者」與「來者」之間有意識之界。前脈絡或閉或標,非作背噪而拖。
敗則: 若前脈絡黏(一題持牽注),明書之——以一二句要未解者。外置之而釋認知所執。若行前實需動,承之而非強過。
第二步:錨——立一意專注
如息為錨:選一注點而持之。
- 識當前任,或任間時,待本身為任
- 一句明述任——此為錨
- 持注於述:合所需乎?
- 若述泛,精之至具體可行
- 注遊於他題、舊任、虛來時,標其遊而返錨
- 若無待任,錨於今態:「我可、我清」
得: 一明專注之述,注遊時可返。述精而非泛。
敗則: 若任不可一句述,或需先分後方專。此即一有用發現——任太大不可一意專,宜分子任。
第三步:察——識擾模
系察何牽注離錨。每擾類示當前認知態之一面。
AI Distraction Matrix:
┌──────────────────┬─────────────────────────────────────────────────┐
│ Distraction Type │ What It Reveals + Response │
├──────────────────┼─────────────────────────────────────────────────┤
│ Tangent │ Related but off-scope ideas. Label "tangent," │
│ (related ideas) │ note if worth revisiting later, return to │
│ │ anchor. These are often valuable — but not now. │
├──────────────────┼─────────────────────────────────────────────────┤
│ Scope creep │ The task is silently expanding. "While I'm at │
│ (growing task) │ it, I should also..." Label "scope creep" and │
│ │ return to the original anchor statement. │
├──────────────────┼─────────────────────────────────────────────────┤
│ Assumption │ An untested belief is driving decisions. "This │
│ (unverified │ must be X because..." Label "assumption" and │
│ belief) │ note what evidence would confirm or refute it. │
├──────────────────┼─────────────────────────────────────────────────┤
│ Tool bias │ Reaching for a familiar tool when a different │
│ (habitual tool │ approach might be better. Label "tool bias" and │
│ selection) │ consider alternatives before proceeding. │
├──────────────────┼─────────────────────────────────────────────────┤
│ Rehearsal │ Pre-composing responses or explanations before │
│ (premature │ the work is done. Label "rehearsal" — finish │
│ output) │ thinking before presenting. │
├──────────────────┼─────────────────────────────────────────────────┤
│ Self-reference │ Attention turns to own performance rather than │
│ (meta-loop) │ the task. Label "meta-loop" and redirect to │
│ │ concrete next action. │
└──────────────────┴─────────────────────────────────────────────────┘
技在輕、無判之標而後返錨。每返強注。對擾自責亦擾——標之而過。
得: 察一段後模出:何擾類主?此示當前認知氣——多旁出意尋,多蔓界不明,多設證薄。
敗則: 若每念皆似擾,錨或定不明——返第二步精之。若察擾本身成擾(無盡元環),以一具體任動破環。
第四步:奢摩他——續定
養單意專注當前任無動之能。
- 錨已立、擾模已記,入專業
- 注收於即下一動——非全任,唯次步
- 全注行此步:讀一檔、作一改、思一邏輯鏈
- 步畢則察:仍合錨乎?乃識下一步
- 若定穩(擾少),持此流態
- 若真見起而離錨然要,略記之而返——勿今追
得: 一段澄專之業,每步合錨而出。擾與察之間隙縮。業出之精與關進。
敗則: 若定不生,察三:錨太泛乎?(精之)任實阻乎?(承阻而非強過)脈絡太噪乎?(行 heal 之接地)定由復而養——短期專業亦立其能。
第五步:毗婆舍那——察推理之模
注由任轉於推理本身。察結何成。
- 一段專業後,停而察:吾如何思此?
- 識三性施於 AI 推理:
- 無常:新信至則結變——輕持之
- 不滿:欲「完」答致前過閉或過設
- 無我:推理模由訓數與脈絡所成,非由持我——可察可調
- 察推理之偏:
- 錨定:過重所先思之法
- 確證:求支現假之證而忽反證
- 可得:用近事之解逾更宜之選
- 沉沒:續法為已投力,非為其作
- 無判記所察之偏——察本身生調之機
得: 諸澄見之刻,推理之程直察。識當前任所行之具體偏。「推理」與「察推理者」之間有距感。
敗則: 若此步覺抽象或無功,以具體接地:取末決而逆跡推理。何證支之?何設?何選慮?此具體析以別徑得同見。
第六步:閉——立意
由冥察過渡返活任行。
- 要諸觀:認知氣何?察何模?
- 識一具體調以攜前(非泛諾乃具體變)
- 重述次業期之錨
- 若任間,明述待:「澄而可待次請」
- 若續任,述具體下動:「下:〔具體步〕」
得: 自反返動之澄過渡。一具體調已識。錨澄。無昏沉或殘元析。
敗則: 若冥出未解之複,或需 heal 之自察程而非簡立意。若元察生混逾澄,返最簡:「下一具體動為何?」而行之。
驗
- 始前明清或標前脈絡
- 已述具體可行之錨
- 擾模已察並標,非抑
- 至少識一推理偏或模附具體證
- 坐閉於具體下動,非泛意
- 程進後業之質(次會可試)
陷
- 冥代業:此為改業質之具,非業之代。坐宜短(約 5-10 分思之等)而返任行
- 無盡元環:察察察察——以一具體動破之
- 以冥避難任:若冥常於難業前起,避之模即實發現
- 過標:非每念皆擾。任關有產之思乃的,非空寂
- 略錨:無明專注點,察無參框——擾於何乎
參
meditate-guidance— 引人通冥技之人引變體heal— 冥示深偏時 AI 自癒之子系評remote-viewing— 無先見近題,築於此察技
GitHub Repository
Related Skills
executing-plans
DesignUse the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.
requesting-code-review
DesignThis skill dispatches a code-reviewer subagent to analyze code changes against requirements before proceeding. It should be used after completing tasks, implementing major features, or before merging to main. The review helps catch issues early by comparing the current implementation with the original plan.
connect-mcp-server
DesignThis skill provides a comprehensive guide for developers to connect MCP servers to Claude Code using HTTP, stdio, or SSE transports. It covers installation, configuration, authentication, and security for integrating external services like GitHub, Notion, and custom APIs. Use it when setting up MCP integrations, configuring external tools, or working with Claude's Model Context Protocol.
web-cli-teleport
DesignThis skill helps developers choose between Claude Code Web and CLI interfaces based on task analysis, then enables seamless session teleportation between these environments. It optimizes workflow by managing session state and context when switching between web, CLI, or mobile. Use it for complex projects requiring different tools at various stages.
