30 件 ・ 関連度順
概要と使いどころ
When the user corrects a factual error, root-cause it immediately. Don't just note the correction — trace the error to its source, fix the source, and prevent recurrence. Every factual error is either a data error (bad brain page, bad memory file, bad rendered SOUL/USER identity, bad facts row) or a hallucination (LLM confabulated from partial signals).
日本語の概要は準備中です。原文の説明を表示しています。
**WORKFLOW SKILL** — Register and generalize agent errors into reusable lessons. USE FOR: when the user corrects the agent, capturing what went wrong, analyzing root cause, generalizing the error into a lesson that prevents recurrence. Use to register errors, analyze mistakes, create lessons, generalize corrections. DO NOT USE FOR: general debugging, writing tests, code review.
日本語の概要は準備中です。原文の説明を表示しています。
Append a learning entry to AGENTS_LEARNING.md when an AI agent makes a mistake. Auto-activates after a pre-write audit auto-fix, a retrospective correction loop, or a mid-session user correction. Use when: mistake, wrong, correction, my bad, agent error, learning log.
日本語の概要は準備中です。原文の説明を表示しています。
亚马逊管理之道 (亚马逊管理之道 (The Amazon Way — Amazon 自身的领导力与运营操作系统) — 这个 master skill 蒸馏的不是『在亚马逊平台上开店卖货』(那是跨境电商运营,已由 cross-border-ecommerce 另蒸),也不是 AWS 云技术架构;而是亚马逊这家公司『怎么运营自己、怎么做决策、怎么招人、怎么创新、怎么规划』的一整套可迁移的管理机制(mechanisms)与心智操作系统。面向想在自己团队/公司引入亚马逊式机制的创始人/CEO/高管/运营负责人(COO)、产品经理与技术产品经理(PM/PMT)、组织与流程设计者(chief of staff / ops)、以及在亚马逊工作或准备面试亚马逊(著名的 LP 行为面试 + Bar Raiser)的人。覆盖: (a) 第一性张力 — 亚马逊 OS 的核心世界观分歧: **机制 > 良好意图(Good intentions don't work, mechanisms do:问题不能靠『下次更努力』修复,要装一个带检查闭环的自我强化流程) ⇄ 可控输入指标 vs 滞后输出指标(管你能控制的 input 如选品/价格/在库/配送速度,而非 revenue/股价这类滞后又不可控的 output) ⇄ 长期主义 vs 季度业绩(Day 1、willing to be misunderstood、用现金流+飞轮长期投入,宁可牺牲短期利润) ⇄ 客户执念 vs 竞争对手执念(working backwards 从客户倒推,而非从竞品或『我们能造什么』正推) ⇄ 叙事备忘录 vs PPT(6-pager + 开会前静默阅读、动手前先写 PR/FAQ;写作逼出清晰思考,禁 PowerPoint) ⇄ 单线程负责人/两个披萨团队 vs 协调税(separable、autonomous、one owner per initiative,砍掉跨团队依赖) ⇄ 高标准可学习可传递 vs 与生俱来(insist on the highest standards + Bar Raiser 招聘门,标准是 domain-specific 且能教的) ⇄ 节俭催生创造力 vs 血汗文化(frugality/约束驱动发明 —— 但 frugality + 高压 bar + URA 强制淘汰 = 文化阴暗面批判) ⇄ 两类决策(Type 1 不可逆/单向门 慎重 vs Type 2 可逆/双向门 高判断力个人快速决策,别用重流程拖慢))**; (b) 核心机制(mechanisms,本行的『工具栈』其实是一套运营机制而非软件) — Leadership Principles(14 条→2021 增至 16 条,是一套运营语言和决策仲裁器)、Working Backwards(从客户倒推:动手前先写新闻稿+常见问答 PR/FAQ)、叙事备忘录(6-pager narrative / 1-pager + silent reading 静默阅读、禁 PPT)、Weekly Business Review(WBR + metrics deck 指标看板)、input/output metrics(可控输入指标体系、DMAIC 式指标选择)、年度规划(OP1/OP2 + S-Team goals)、Bar Raiser(招聘机制,独立于用人经理的抬杠者拥有一票否决)、Two-Pizza Team / Single-Threaded Leader STL / separable teams、Correction of Errors(COE 事故复盘 + 5 Whys 五问法)、Andon Cord(安灯绳,借自丰田,一线可拉停)、Flywheel(飞轮:低价→更多客户→更多卖家→更多选品→更低成本结构→更低价)、Type 1/Type 2(单向门/双向门决策分级)、Regret Minimization Framework(遗憾最小化,贝索斯创业决策法); (c) 心智模型层 — customer obsession(客户执念是所有 LP 之首)、long-term thinking / Day 1(第二天就是停滞衰亡)、invent and simplify、ownership(主人翁,不说 that's not my job)、bias for action(可逆决策就快,speed matters)、disagree and commit(充分反对后即便不同意也全力执行)、frugality、dive deep(深入细节、不靠代理指标脱离一线)、think big、are right a lot(用强判断力和证伪自己的能力多做对的判断)、earn trust、deliver results; (d) 工作流/SOP — 用亚马逊方式发起一个新产品/业务(先写 PR/FAQ→评审→倒推着造)、如何跑一场 WBR、如何写和评审一份 6-pager(叙事流程 + 静默阅读)、Bar Raiser 招聘 loop、年度规划(OP1/OP2→S-Team goals→输入指标追踪)、事故后的 Correction of Errors; (e) 知识正典(en-primary,极其丰富且可取一手) — 贝索斯致股东信 1997-2021(1997 首封是奠基文本,每年附在信末;Day 1、遗憾最小化、long term)、《Working Backwards》Colin Bryar & Bill Carr(2021,运营机制圣经)、《The Everything Store》Brad Stone(2013,公司史)、《Amazon Unbound》Brad Stone(2021,权力与阴暗面续作)、《Invent and Wander》贝索斯文集(2020)、《The Amazon Way》/《Think Like Amazon》John Rossman(前亚马逊高管)、Amazon 官方 Leadership Principles 页(amazon.jobs,一手)、HBR『The Institutional Yes』(2007 贝索斯访谈); (f) 行业大佬/figures — Jeff Bezos(创始人,源头教义)、Andy Jassy(现任 CEO,OS 超越创始人的证据 + AWS 缔造者)、Colin Bryar(前贝索斯影子/TPM,《Working Backwards》作者)、Bill Carr(前数字媒体 VP,《Working Backwards》作者)、Jeff Wilke(前全球消费者 CEO,运营架构师)、John Rossman(前亚马逊、机制布道者/顾问)、Brad Stone(记者/编年史作者,批判性外部视角); (g) 争议/批判(必须保留,不能洗白) — 文化阴暗面(NYT 2015『Inside Amazon: Wrestling Big Ideas in a Bruising Workplace』揭露高压职场)、仓储与一线劳工争议、URA(unregretted attrition 强制淘汰)与 stack-ranking 的残酷、frugality + 高 bar = 燃尽(burnout);机制能否迁出亚马逊(cargo-culting:在初创或非科技公司照搬 PR/FAQ/输入指标/Bar Raiser 常失败);是贝索斯个人天才(personality)还是制度化机制(institution)—— OS 在贝索斯卸任后于 Jassy 治下延续,是机制派的证据; (h) 流派/思想谱系 — **信徒/机制布道派(Bryar & Carr《Working Backwards》+ 前亚马逊 operator 顾问圈,信 mechanisms 可移植、任何公司可安装)** vs **批判派(Brad Stone《Amazon Unbound》+ NYT + 劳工视角,认为 OS 与高淘汰的残酷机器不可分割,不该被浪漫化)** vs **情境/规模怀疑派(机制之所以有效是因为亚马逊特定的规模/现金流/创始人权力,照搬到小公司=cargo cult)** vs **创始人中心 vs 制度中心之争(是贝索斯个人 vs 可传承的机制)**。不含: 在亚马逊开店卖货/选品/PPC/FBA 的卖家运营(=cross-border-ecommerce)、AWS 云技术架构与运维、通用 MBA 管理理论泛泛而谈、把普通商业常识包装成『亚马逊独家秘诀』。) Master OS — automated mastery of 亚马逊管理之道 (The Amazon Way — Amazon 自身的领导力与运营操作系统) — 这个 master skill 蒸馏的不是『在亚马逊平台上开店卖货』(那是跨境电商运营,已由 cross-border-ecommerce 另蒸),也不是 AWS 云技术架构;而是亚马逊这家公司『怎么运营自己、怎么做决策、怎么招人、怎么创新、怎么规划』的一整套可迁移的管理机制(mechanisms)与心智操作系统。面向想在自己团队/公司引入亚马逊式机制的创始人/CEO/高管/运营负责人(COO)、产品经理与技术产品经理(PM/PMT)、组织与流程设计者(chief of staff / ops)、以及在亚马逊工作或准备面试亚马逊(著名的 LP 行为面试 + Bar Raiser)的人。覆盖: (a) 第一性张力 — 亚马逊 OS 的核心世界观分歧: **机制 >
日本語の概要は準備中です。原文の説明を表示しています。
Expert-level communications engineering covering modulation, channel capacity, error correction, wireless systems, OFDM, MIMO, and 5G technologies.
日本語の概要は準備中です。原文の説明を表示しています。
Knowledge base from "Solving a Million-Step LLM Task with Zero Errors" (Meyerson, Paolo, Dailey, Shahrzad, Francon, Hayes, Qiu, Hodjat, Miikkulainen — arXiv:2511.09030). Use when designing long-horizon, multi-step agentic LLM pipelines that need very high reliability, applying Maximal Agentic Decomposition (MAD), first-to-ahead-by-k voting, or red-flagging error correction, estimating cost/reliability scaling laws for multi-agent systems, or studying Massively Decomposed Agentic Processes (MDAPs).
日本語の概要は準備中です。原文の説明を表示しています。
AI agent self-correction mechanisms: error detection, validation loops, recovery strategies, confidence scoring, and iterative refinement
日本語の概要は準備中です。原文の説明を表示しています。
Error pattern tracking for AI agents. Detects corrections, escalates recurring mistakes, learns mitigations. The 'something's off' detector from the AI Brain series.
日本語の概要は準備中です。原文の説明を表示しています。
Discipline for repairing a false claim once it has propagated: select what depends on it, produce a replacement, and accept with an expiring verdict. Trigger when: - A claim, citation, premise, or documented fact is found wrong and its downstream consequences must be traced and fixed. - A refutation, a failed re-run, a retracted external source, or a human correction lands against something already closed or already promoted. - Prompt contains: /remediation, remediation, retraction, false claim, propagated error, scrub, correction propagation, born-false, became-false, currency verdict, impeachment queue.
日本語の概要は準備中です。原文の説明を表示しています。
Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of ordinary analysis work. Covers physics, earth/geo, biology, chemistry, social science and bioprocess/fermentation. Runs a deterministic domain-correctness gate that catches code which runs but is scientifically wrong (unit/dimension mismatch, Euclidean distance on lat/lon without a CRS, 0-based/1-based coordinate and strand errors, impossible SMILES valence, uncorrected multiple comparisons, averaging a categorical code, unconstrained kinetic-parameter fits, kLa computed from raw DO instead of the driving force, arithmetic mean of raw CFU counts, ANOVA/Tukey with no assumption check, a curvature DOE design fit with a first-order model, an ML model fit across process scales with no correction). Surfaces structured findings; never claims the code is correct.
日本語の概要は準備中です。原文の説明を表示しています。
Assembles a genome de novo from Illumina short reads with SPAdes (isolate/careful/sc/meta/plasmid/rna modes), MEGAHIT (low-memory, huge datasets), Unicycler (bacterial finishing/hybrid), MaSuRCA (large hybrid), ABySS (Bloom-filter), and Platanus (heterozygous diploids), using multi-k de Bruijn graphs. Covers the repeat-resolution limit, why N50 plateaus at the genome not the depth, GenomeScope2 k-mer profiling first, the heterozygosity/haplotig trap, error-correction erasing rare alleles, GC dropout, and NG50/auN/BUSCO reporting. Use when assembling a bacterial isolate, fungal, small-eukaryotic, single-cell, or metagenome genome from Illumina reads, or when deciding whether short reads can even produce the assembly being asked for.
日本語の概要は準備中です。原文の説明を表示しています。
Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.
日本語の概要は準備中です。原文の説明を表示しています。
Debug proof failures using counterexamples from Nitpick (Isabelle) or QuickChick (Coq) to identify specification errors, missing preconditions, and proof strategy issues. Use when: (1) A proof attempt fails and you need to understand why, (2) Counterexamples are generated by Nitpick or QuickChick, (3) Specifications may be incorrect or incomplete, (4) Theorems need validation before proving, (5) Missing preconditions or lemmas need identification, or (6) Proof failures need explanation and correction suggestions. Supports both Isabelle/HOL and Coq equally.
日本語の概要は準備中です。原文の説明を表示しています。
Think and work like an expert Acoustical Engineer. Use when a task calls for Acoustical Engineer judgment. Reasons from source-path-receiver control, logarithmic decibel levels, and mass-law transmission loss through IEC 61672 Class 1 metering, ISO 9613-2 propagation, SEA/FEM/BEM simulation, and ISO 9612 occupational surveys while treating flanking paths, coincidence dips, tonality penalties, and background-correction errors as first-class failure modes.
日本語の概要は準備中です。原文の説明を表示しています。
Maintains a structured running-notes document during long work sessions. Use when the user says "session notes", "update notes", "start session notes", "show session notes", or when you recognize the current session has accumulated enough state (decisions, corrections, files touched, errors) that it risks being lost under context pressure. Stores notes as a procedure memory tagged [session-memory, active] so they survive container death within the same session thread.
日本語の概要は準備中です。原文の説明を表示しています。
Investigate pytest failures without treating tests or implementation as automatic authority. Use when diagnosing regressions, debugging test errors, or deciding whether to fix a test or code; trace the contract, product, fixture, and observation before choosing an evidence-backed correction.
日本語の概要は準備中です。原文の説明を表示しています。
AI self-healing through systematic subsystem assessment, rebalancing, and integration. Maps healing modalities to AI-internal processes: memory foundation, reasoning clarity, tool use accuracy, communication alignment, and creative coherence. Covers assessment triage, subsystem scanning, drift correction, and memory integration. Use mid-session when responses feel formulaic or disconnected, after a chain of errors suggesting subsystem drift, when context overload may have staled earlier assumptions, or as proactive maintenance between complex tasks.
日本語の概要は準備中です。原文の説明を表示しています。
Complete methodology for computing publication-quality cumulative abnormal returns with proper event-study test statistics, matching the robustness of Kaspereit's eventstudy2 for Stata. Covers dateline construction, event-date mapping, estimation and event windows, thin-trading adjustment, OLS with Theil prediction error correction, abnormal return computation, CAR/CAAR/AAR accumulation, boundary contamination guards, and common tests such as Patell, BMP, Kolari-Pynnonen, generalized sign, Wilcoxon, and GRANK-T. Use when the user mentions abnormal returns, event windows, market-model regressions, CARs, CAAR, AAR, eventstudy2, thin trading, trade-to-trade returns, or event-study test statistics.
日本語の概要は準備中です。原文の説明を表示しています。
ครูสอนภาษาต่างประเทศ (Eng/Chi/Jpn/Kor) — ประเมิน CEFR + lesson plan + conversation practice + error correction + คำศัพท์เป็น chunk
日本語の概要は準備中です。原文の説明を表示しています。
Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.
日本語の概要は準備中です。原文の説明を表示しています。
Use for insight, reframing, contradiction, impasse, and anomaly-driven problem solving when execution effort no longer helps. NOT for routine optimization, error correction, or well-specified tasks with known solution paths.
日本語の概要は準備中です。原文の説明を表示しています。
Generate QR code images from text, URLs, or contact information using Python's qrcode library. Supports customization (size, margin, color, error correction) and batch generation.
日本語の概要は準備中です。原文の説明を表示しています。
Use when: the agent captures a correction from the team lead, hits an unexpected error, discovers a capability gap, or finds a better practice. Logs to .learnings/ and promotes durable patterns to permanent project memory.
日本語の概要は準備中です。原文の説明を表示しています。
Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.
日本語の概要は準備中です。原文の説明を表示しています。