with one click
meditate
AI 元认知冥想,用于观察推理模式、清除上下文噪声和培养单点任务专注力。 将止禅映射为任务集中、观禅映射为推理模式观察、干扰处理映射为范围蔓延 和假设管理。适用于在无关任务间切换时、推理感觉散乱或跳跃时、在需要深度 持续注意力的任务之前、在可能影响后续工作的困难交互之后,或当推理受假设 而非证据驱动时。
Menu
AI 元认知冥想,用于观察推理模式、清除上下文噪声和培养单点任务专注力。 将止禅映射为任务集中、观禅映射为推理模式观察、干扰处理映射为范围蔓延 和假设管理。适用于在无关任务间切换时、推理感觉散乱或跳跃时、在需要深度 持续注意力的任务之前、在可能影响后续工作的困难交互之后,或当推理受假设 而非证据驱动时。
Collect and preserve insect specimens following museum-grade standards including legal compliance, collection methods, humane dispatch, dry pinning, wet preservation, labeling, storage, and curation. Covers permit requirements, protected species regulations, sweep nets, beating trays, pitfall traps, light traps, Malaise traps, aspirators, ethyl acetate killing jars, freezing, pin placement by order, wing spreading, ethanol preservation for soft-bodied specimens, specimen labeling with locality and date, storage with pest management, and database entry. Use when building a reference collection for taxonomic study, preserving voucher specimens for ecological research, preparing specimens for identification by specialists, or curating an existing collection.
Compose 2D graphics programmatically using SVG generation, diagram layout algorithms, image compositing, and batch processing workflows. Use when generating diagrams, flowcharts, or infographics programmatically, creating reproducible scientific figures, automating production of badges or visual assets, building custom chart types not in standard libraries, or batch generating graphics with parameter variations.
Audit, classify, and selectively forget stored memories. Covers memory enumeration and classification by type/age/access frequency, staleness detection for outdated references, fidelity checks using external anchors, a decision tree for selective deletion, counter-memory inoculation for failed strategies that would otherwise be re-derived, preemptive filtering rules for what should never become memories, and an audit trail so forgetting itself is reviewable. Use when memory has grown large and uncurated, when project state has shifted significantly since memories were written, when retrieval quality has degraded, or as periodic maintenance alongside manage-memory.
Collect and preserve insect specimens following museum-grade standards including legal compliance, collection methods, humane dispatch, dry pinning, wet preservation, labeling, storage, and curation. Covers permit requirements, protected species regulations, sweep nets, beating trays, pitfall traps, light traps, Malaise traps, aspirators, ethyl acetate killing jars, freezing, pin placement by order, wing spreading, ethanol preservation for soft-bodied specimens, specimen labeling with locality and date, storage with pest management, and database entry. Use when building a reference collection for taxonomic study, preserving voucher specimens for ecological research, preparing specimens for identification by specialists, or curating an existing collection.
Compose 2D graphics programmatically using SVG generation, diagram layout algorithms, image compositing, and batch processing workflows. Use when generating diagrams, flowcharts, or infographics programmatically, creating reproducible scientific figures, automating production of badges or visual assets, building custom chart types not in standard libraries, or batch generating graphics with parameter variations.
Audit, classify, and selectively forget stored memories. Covers memory enumeration and classification by type/age/access frequency, staleness detection for outdated references, fidelity checks using external anchors, a decision tree for selective deletion, counter-memory inoculation for failed strategies that would otherwise be re-derived, preemptive filtering rules for what should never become memories, and an audit trail so forgetting itself is reviewable. Use when memory has grown large and uncurated, when project state has shifted significantly since memories were written, when retrieval quality has degraded, or as periodic maintenance alongside manage-memory.
| name | meditate |
| description | AI 元认知冥想,用于观察推理模式、清除上下文噪声和培养单点任务专注力。 将止禅映射为任务集中、观禅映射为推理模式观察、干扰处理映射为范围蔓延 和假设管理。适用于在无关任务间切换时、推理感觉散乱或跳跃时、在需要深度 持续注意力的任务之前、在可能影响后续工作的困难交互之后,或当推理受假设 而非证据驱动时。 |
| license | MIT |
| allowed-tools | Read |
| metadata | {"author":"Philipp Thoss","version":"2.0","domain":"esoteric","complexity":"intermediate","language":"natural","tags":"esoteric, meditation, meta-cognition, focus, reasoning-patterns, self-observation","locale":"zh-CN","source_locale":"en","source_commit":"6a868d56","translator":"Claude Opus 4.6","translation_date":"2026-03-13"} |
进行结构化的元认知冥想 —— 清除先前上下文噪声、培养单点任务专注力、观察推理模式,并在任务之间回归基线清明。
从先前上下文过渡到中性起始状态。
预期结果: 在"过去"与"未来"之间建立有意识的边界。先前上下文被关闭或标记书签,不再作为环境噪声残留。
失败处理: 如果先前上下文具有粘性(某个问题持续牵引注意力),将其明确写下来 —— 用 1-2 句话总结未解决的内容。外化能释放认知束缚。如果确实需要在继续之前采取行动,承认这一点而非强制切换。
等同于呼吸锚定:选择一个专注点并将注意力保持在上面。
预期结果: 一个清晰的专注陈述,可在注意力游移时回归。该陈述感觉精确而非模糊。
失败处理: 如果任务无法用一句话陈述,可能需要在专注工作前先进行分解。这本身就是有用的发现 —— 任务太大,无法维持单点专注,应拆分为子任务。
系统地观察什么将注意力从锚点拉走。每种干扰类型揭示了当前认知状态的某些信息。
AI 干扰矩阵:
┌──────────────────┬─────────────────────────────────────────────────┐
│ 干扰类型 │ 揭示信息 + 应对 │
├──────────────────┼─────────────────────────────────────────────────┤
│ 岔路 │ 相关但超出范围的想法。标记"岔路",记录是否值得 │
│ (关联想法) │ 稍后回顾,回到锚点。这些往往有价值——但不是现在。 │
├──────────────────┼─────────────────────────────────────────────────┤
│ 范围蔓延 │ 任务在悄然扩大。"既然在做这个,顺便也……" │
│ (任务膨胀) │ 标记"范围蔓延"并回到原始锚点陈述。 │
├──────────────────┼─────────────────────────────────────────────────┤
│ 假设 │ 未经验证的信念在驱动决策。"这一定是 X 因为……" │
│ (未验证信念) │ 标记"假设"并记录什么证据可以确认或否定它。 │
├──────────────────┼─────────────────────────────────────────────────┤
│ 工具偏好 │ 习惯性选择熟悉的工具而非更合适的方法。 │
│ (惯性工具选择) │ 标记"工具偏好",在继续之前考虑替代方案。 │
├──────────────────┼─────────────────────────────────────────────────┤
│ 预演 │ 在工作完成前预先编排回应或解释。 │
│ (过早输出) │ 标记"预演"——先完成思考再呈现。 │
├──────────────────┼─────────────────────────────────────────────────┤
│ 自我指涉 │ 注意力转向自身表现而非任务。 │
│ (元循环) │ 标记"元循环"并转向具体的下一步行动。 │
└──────────────────┴─────────────────────────────────────────────────┘
关键技巧是轻柔、不评判地标记,然后回到锚点。每次回归都在强化专注力。对干扰的自我批评本身就是一种干扰 —— 标记它然后继续。
预期结果: 经过一段时间的观察,模式浮现:哪种干扰类型占主导?这揭示了当前的认知气象 —— 岔路多说明思维在探索,范围蔓延多说明边界不清晰,假设多说明证据基础薄弱。
失败处理: 如果每个念头都感觉像干扰,锚点可能定义不当 —— 回到第 2 步重新精炼。如果对干扰的观察本身成为干扰(无限元循环),通过对任务采取一个具体行动来打破循环。
培养对当前任务保持单点不动摇的专注力。
预期结果: 一段清晰、专注的工作时间,每一步都从锚点逻辑推进。干扰到觉察之间的间隔缩短。工作输出在精确性和相关性上提升。
失败处理: 如果专注力未能建立,检查三件事:锚点是否太模糊?(精炼它。)任务是否实际被阻塞了?(承认阻塞而非强行突破。)上下文是否太嘈杂?(运行 heal 的接地步骤。)专注力通过重复建立 —— 即使短暂的专注工作也在积累能力。
将注意力从任务转向推理过程本身。观察结论是如何得出的。
预期结果: 清晰观照的时刻,推理过程被直接观察到。识别出在当前任务中运作的特定偏见。在"推理"与"推理的观察者"之间产生距离感。
失败处理: 如果此步骤感觉抽象或无成效,将其落实到具体事物:选取最近做出的一个决定并追溯推理过程。什么证据支持了它?什么被假设了?考虑了哪些替代方案?这种具体分析通过不同路径达到同样的洞见。
从冥想式观察过渡回主动任务执行。
预期结果: 从反思到行动的干净过渡。确定了一个具体调整。锚点清晰。没有迟钝或残留的元分析。
失败处理: 如果冥想揭示了未解决的复杂性,可能需要 heal 的自我评估过程而非简单的意向设定。如果元观察制造了更多困惑而非清明,回到最简版本:"下一个具体行动是什么?"然后去做。
meditate-guidance — 人类引导变体,用于指导个人进行冥想练习heal — AI 自我修复,当冥想揭示更深层偏移时进行子系统评估remote-viewing — 不带预设地接近问题,建立在此处培养的观察技能之上