「gold」の検索結果

Manage golden dataset regression tests for LLM prompts using Promptfoo. Commands — init, add, run, report. Use when user says "regression", "golden dataset", "prompt regression", "eval run", "test my prompts", or after shipping prompt changes.

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。

Canonical rules for writing, rewriting, or reviewing Shift desktop Playwright E2E tests and visual goldens under `apps/desktop/e2e/`. Use whenever you add or change a `.spec.ts`, a fixture, `EditorDriver`, a screenshot baseline, or Playwright project membership, and whenever you investigate a flaky or failing E2E test. Covers waits, oracles, goldens, fixtures, projects, and flake verification.

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。

Implements snapshot/golden file tests with temporal normalization so tests don't break daily. Use when implementing tests that compare output against expected snapshots.

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。

DevOps 与站点可靠性工程 (SRE) — 平台 / 基础设施 / 可靠性工程师的认知操作系统, 覆盖软件交付 + 运维全生命周期 (CI/CD 与发布工程 trunk-based + 渐进式发布 canary/blue-green/feature flag + GitOps Argo CD/Flux / 基础设施即代码 Terraform/OpenTofu/Pulumi/Ansible + policy-as-code OPA / 容器与编排 Docker/Kubernetes + Helm/Kustomize + service mesh Istio/Linkerd / 可观测性 Prometheus + Loki + OpenTelemetry + Honeycomb + eBPF + RED/USE / SLO-SLI-error budget 与可靠性工程 Google SRE 学科 + 容量规划 + 优雅降级 / 事件管理与 on-call 事件指挥 + PagerDuty + runbook + 无指责复盘 + MTTR / 云平台与 FinOps AWS/GCP/Azure + 成本优化 + 弹性伸缩 / 平台工程与开发者体验 IDP + Backstage + golden path + Team Topologies / DevSecOps 与供应链安全 shift-left + SBOM + SLSA + sigstore + Vault / 韧性与混沌工程 fault injection + game day + 安全科学 / DORA 指标与工程效能 部署频率 + 变更前置时间 + 变更失败率 + Accelerate 研究 / 数据库与有状态运维 schema 迁移 + 备份容灾) — 不含 通用应用开发 / 纯云销售认证速成 / 'DevOps = 跑 Jenkins 的岗位' 窄化误解 / ITIL 工单文化传统运维 (旧范式仅做边界) / 把手工运维 ClickOps 当稳态 (是 toil, 本 skill 核心反模式) (DevOps & Site Reliability Engineering — the cognitive operating system of platform / infrastructure / reliability practitioners who own the full software delivery + operational lifecycle, covering (a) CI/CD & release engineering (build pipelines, trunk-based development, progressive delivery — canary / blue-green / feature flags, GitOps with Argo CD / Flux), (b) Infrastructure as Code (Terraform / OpenTofu, Pulumi, CloudFormation, Ansible, Crossplane — module design, state management, drift, policy-as-code OPA / Sentinel / Checkov), (c) containers & orchestration (Docker / OCI, Kubernetes — scheduling, networking CNI, storage CSI, operators / CRDs, Helm / Kustomize, service mesh Istio / Linkerd), (d) observability (the three pillars + beyond — metrics Prometheus / VictoriaMetrics, logs Loki / ELK, traces OpenTelemetry / Jaeger / Tempo, high-cardinality observability Honeycomb, eBPF, RED / USE methods, SLO-based alerting), (e) SLO / SLI / error budgets & reliability engineering (Google SRE discipline — service level objectives, error budget policy, toil budgets, capacity planning, load shedding, graceful degradation), (f) incident management & on-call (incident command, PagerDuty / Opsgenie, runbooks, blameless postmortems, MTTR / MTTD, error budget burn), (g) cloud platforms & FinOps (AWS / GCP / Azure well-architected, multi-region, cost optimization, autoscaling), (h) platform engineering & developer experience (internal developer platforms, Backstage, golden paths, self-service, Team Topologies), (i) DevSecOps & supply-chain security (shift-left, SAST / DAST, SBOM, SLSA, sigstore / cosign, secrets management Vault), (j) resilience & chaos engineering (chaos experiments, fault injection, game days, resilience engineering / safety science), (k) DORA metrics & engineering effectiveness (deployment frequency, lead time, change failure rate, MTTR, the Accelerate research), (l) databases & stateful operations (schema migrations, backups / DR, replication); NOT generic software development / app feature coding (是 平行学科, DevOps/SRE 关注 delivery + operability 不是 product feature), NOT pure cloud sales / certification cram without operational depth, NOT 'DevOps = a job title that runs Jenkins' 的窄化误解 (DevOps 是 文化 + 实践, SRE 是 Google 对 reliability 的工程化具体实现), NOT ITIL-heavy 传统运维 工单文化 (是 被 DevOps 取代的旧范式, 仅做边界标注), NOT manual ops / ClickOps as a steady state (是 toil, 本 skill 的核心反模式).) Master OS — automated mastery of DevOps & Site Reliability Engineering — the cognitive operating system of platform / infrastructure / reliability practitioners who own the full software delivery + operational lifecycle, covering (a) CI/CD & release engineering (build pipelines, trunk-based development, progressive delivery — canary / blue-green / feature flags, GitOps with Argo CD / Flux), (b) Infrastructure as Code (Terraform / OpenTofu, Pulumi, CloudFormation, Ansible, Crossplane — module design, state management, drift, policy-as-code OPA / Sentinel / Checkov), (c) containers & orchestration (Docker / OCI, Kubernetes — scheduling, networking CNI, storage CSI, operators / CRDs, He

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。

CEO (Chief Executive Officer) — 一家公司「最高操作员」的工艺, 与泛泛「领导力 / 管理学」不同: (a) 设定战略与凝结愿景 (Drucker 的「企业的经营理论」+ Porter 论定位 + Hamilton Helmer 的「七力」+ Andy Grove 的「战略转折点」+ Roger Martin 《Playing to Win》); (b) 资本配置是 CEO 单一最高杠杆的工作 (Buffett/Munger Berkshire 致股东信 + William Thorndike 《The Outsiders 商界局外人》论 8 位非常规 CEO + Michael Mauboussin 论 hurdle rate + Bezos 年度致股东信「invariants vs bets」+ Mark Leonard Constellation Software); (c) 组建与领导高管班子 (Patrick Lencioni 《团队的五大障碍》+ Ben Horowitz 《艰难的事》+ Reed Hastings 《No Rules Rules》人才密度 + Andy Grove HOP《高产出管理》+ Lou Gerstner IBM 转型 + Marshall Goldsmith); (d) 董事会与投资人关系 (Larcker & Tayan 《公司治理重要》+ Bill George 《True North》+ 正式 CEO-董事长 / CEO-独立董事 protocol + 维权投资人 playbook + 资本市场沟通); (e) 企业文化与价值观作为操作系统 (Netflix 文化手册 + Amazon Leadership Principles + Bridgewater 《Principles》Ray Dalio + Schein 论组织文化 + 任正非 灰度 + 张瑞敏 人单合一 + 稻盛和夫 阿米巴); (f) 高不确定下的高风险决策 (Bezos Type 1/Type 2 决策 + premortem Klein + Kahneman 论 executive bias + RAPID/DACI + base rates + 情景规划 + 反思 premortem); (g) 对内对外沟通 (创始人 / CEO 致股东信作为机构构建工具: Bezos / Buffett / Reed Hastings 备忘录 / 任正非 内部讲话 + Town Hall + 危机沟通 Tylenol/Boeing/Wells Fargo + 应对维权投资人); (h) 跨阶段规模化 (创业 0→1 / 扩张 1→100 / 成熟期掌舵 / 危机转型): Steve Blank + Brian Chesky founder-mode + Marc Andreessen + Pierre Lassonde + Lou Gerstner 转型; (i) 创始人 CEO vs 职业经理人 CEO 的差异 (Paul Graham 「Founder Mode」2024 + Brian Chesky + Reed Hastings (创始人→职业过渡) + BCG/McKinsey 的「manager mode」+ 两者各自代价 + 什么时候切换)。诚实处理: 幸存者偏差 (单个 CEO 的打法 ≠ 普适规律, 学术研究显示 CEO 个人方差约 ⅓, 约 70% 来自行业 / 时代 / 运气 / 资本结构), 创始人崇拜, 区分可复制工艺与不可移植个人魅力, 治理与利益相关者责任 (员工 / 股东 / 社会), 反对 CEO 神话与 Welch 退休金扭曲 / Theranos / WeWork / FTX / Uber-Kalanick 时代 / Musk 80h+ / 996 工时崇拜。覆盖 founder-CEO (Bezos/Hastings/黄仁勋/Chesky/Brin/任正非) 与职业 CEO (Nadella/Gerstner/Pichai/Mulally/Lafley)。不含: 泛泛管理理论 (商业书已覆盖, 本 skill 专谈 C-suite 这个具体岗位), 不含: 「领导力」作为个人成长自助 (Robbins/Tracy/Maxwell 励志体裁), 不含: 「如何创业」早期战术 — 一旦有员工 / 董事会 / 资本, CEO 的工艺才开始。 (CEO (Chief Executive Officer) — the craft of being the top operator of a company, distinct from generic 'leadership/management': (a) setting the strategy and crystallizing the vision (Drucker's 'theory of the business' + Porter on positioning + Hamilton Helmer's 7 powers + Andy Grove's strategic inflection points + Roger Martin Playing to Win); (b) capital allocation as the CEO's single highest-leverage job (Buffett/Munger Berkshire letters + William Thorndike 'The Outsiders' on 8 unconventional CEOs + Michael Mauboussin on hurdle rates + Bezos's annual shareholder letter approach to invariants vs bets + Mark Leonard Constellation Software); (c) building and leading the executive team (Patrick Lencioni 'Five Dysfunctions' + Ben Horowitz 'Hard Things About Hard Things' + Reed Hastings 'No Rules Rules' on talent density + Andy Grove HOP + Lou Gerstner IBM turnaround + Marshall Goldsmith); (d) board and investor relations (Larcker & Tayan 'Corporate Governance Matters' + Bill George 'True North' + the formal CEO-Chair / CEO-Lead Director protocols + activist investor playbooks + capital markets communication); (e) culture and values as operating system (Netflix culture deck + Amazon Leadership Principles + Bridgewater 'Principles' Ray Dalio + Schein on org culture + 任正非 Ren Zhengfei 灰度 + 张瑞敏 Zhang Ruimin 人单合一 + 稻盛和夫 阿米巴); (f) high-stakes decision-making under uncertainty (Bezos Type 1 vs Type 2 + premortem Klein + Kahneman 'Thinking Fast and Slow' for executive bias + RAPID/DACI + base rates + scenario planning + premortem); (g) internal and external communication (founder/CEO letters as institution-builders: Bezos shareholder letters / Buffett letters / Reed Hastings memos / 任正非 内部讲话 + Town Halls + crisis communication Tylenol/Boeing/Wells Fargo + activist responses); (h) cross-stage scaling (founder-CEO of 0→1 / scaling 1→100 / mature-stage stewardship / turnaround): Steve Blank + Brian Chesky founder-mode + Marc Andreessen + Pierre Lassonde mining vs steady-state + Lou Gerstner turnaround; (i) the founder-CEO vs professional-manager-CEO distinction (Paul Graham 'Founder Mod

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。

You launched an ambassador program. 3 applications. One ghosted after week 2. Should you lower the bar? Offer more perks? Spam influencers? This gives you the complete community & ambassador operations SOP — from pre-launch checklist to recruitment to tiered management to retention to governance. Built from Notion (20M users, real ambassador interviews), AFFiNE (60K stars), Asana, and ClickUp programs. By @WeiYipei. What's inside: • Pre-launch readiness checklist (6 conditions that must be true before starting) • 6-step community setup SOP (platform selection → rules → admin standards → monitoring → wiki → metrics) • Ambassador recruitment system (A+B qualification, application form design, scoring rubric) • 4-tier progression system (Bronze → Silver → Gold → Platinum with point thresholds) • 5-pillar incentive framework (Product quality → Beta access → Founder access → KOL path → Full engagement) • Churn early-warning system + retention playbook • Event operations SOP (6 event types × full lifecycle) • Health metrics dashboard (6 core KPIs + 5 ambassador-specific indicators) • Governance & risk control (behavior code, escalation matrix) • Real templates: recruitment post, welcome email, annual calendar 🇨🇳 你搞了个大使计划。来了3个申请。一个第二周就消失了。该降门槛？加福利？群发KOL？这份SOP给你从启动前置条件到招募到留存到治理的完整社区/大使运营方法论。基于 Notion（2000万用户，大使真实访谈）、AFFiNE（60K stars）、Asana、ClickUp 实战案例。 🇯🇵 アンバサダープログラムを立ち上げた。応募3件。1人は2週間で消えた。基準を下げる？特典を増やす？このSOPは、事前チェックリストから採用、段階管理、リテンション、ガバナンスまでの完全なコミュニティ＆アンバサダー運営フレームワークを提供します。Notion（2000万ユーザー）、AFFiNE（60K stars）の実例から構築。 🇰🇷 앰배서더 프로그램을 시작했습니다. 지원 3건. 하나는 2주 만에 사라졌습니다. 기준을 낮출까요? 이 SOP는 사전 체크리스트부터 모집, 단계별 관리, 리텐션, 거버넌스까지 완전한 커뮤니티 & 앰배서더 운영 프레임워크를 제공합니다. Notion(2000만 사용자), AFFiNE(60K stars) 실전 사례에서 구축. Triggers: "ambassador program" | "community building" | "community management" | "DevRel" | "developer relations" | "community growth" | "大使计划" | "社区运营" | "社区搭建" | "コミュニティ運営" | "アンバサダー" | "커뮤니티 운영" | "앰배서더" | "open source community" | "user retention"

Build automated regression suites — golden sets, threshold alerting, CI integration for model changes. Use when asked to "catch model regressions in CI", "build a golden set", or "automate eval regression".

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。

Review a design artifact (spec, plan, PR packet) with fresh, memoryless subagents. Invoke when the user asks — "goldfish this", "fresh eyes", "tear this apart" — or after suggesting it for a spec that has grown load-bearing and the user agrees.

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。

Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Drop-in replacement for bd/Beads with simpler architecture. Use for: tracking issues/beads with dependencies, creating bugs/features/tasks, planning specs, implementing features from specs, code reviews, committing code, creating PRs, loading coding guidelines (TypeScript, Python, TDD, golden testing, Convex, monorepo patterns), code cleanup, research briefs, architecture docs, agent handoffs, and checking out third-party library source code. Invoke when user mentions: tbd, beads, bd, shortcuts, issues, bugs, tasks, features, epics, todo, tracking, specs, planning, implementation, validation, guidelines, templates, commit, PR, pull request, code review, testing, TDD, test-driven, golden testing, snapshot testing, TypeScript, Python, Convex, monorepo, cleanup, dead code, refactor, handoff, research, architecture, labels, search, checkout library, source code review, or any workflow shortcut.

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。

The TaskBarHero game updated (new version) and the tbh-meter reader needs re-calibration — symptoms are gold showing 0, stage mode "?", or the live party/XP/stats dropping out (party empty / no live levels / runs degraded) after a patch, or you're prepping a meter release for a new game build. Runs the diagnose→dump→diff→reseed→bump→verify playbook (the fix is usually a reseed, but a build can also change an Obscured encoding with zero offset movement — caught only by the live gate, fixed by a read-strategy change). Use when the game version changed, after a TBH patch, when a player reports gold/stage/party/XP broken following an update, or when asked to re-seed / re-calibrate the reader for a new build.

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。

Extract maximum value from existing code — performance optimization, API surface refinement, and dead weight elimination. The art of turning base code into gold through systematic identification and amplification of value-bearing patterns. Use when optimizing a working but sluggish codebase, refining an API surface that has accumulated cruft, reducing bundle size or memory footprint, or preparing code for open-source release — when code works correctly but doesn't shine and needs polish rather than a full rewrite.

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。

Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents. Drop-in replacement for bd/Beads with simpler architecture. Use for: tracking issues/beads with dependencies, creating bugs/features/tasks, planning specs, implementing features from specs, code reviews, committing code, creating PRs, loading coding guidelines (TypeScript, Python, TDD, golden testing, Convex, monorepo patterns), code cleanup, research briefs, architecture docs, agent handoffs, and checking out third-party library source code. Invoke when user mentions: tbd, beads, bd, shortcuts, issues, bugs, tasks, features, epics, todo, tracking, specs, planning, implementation, validation, guidelines, templates, commit, PR, pull request, code review, testing, TDD, test-driven, golden testing, snapshot testing, TypeScript, Python, Convex, monorepo, cleanup, dead code, refactor, handoff, research, architecture, labels, search, checkout library, source code review, or any workflow shortcut.

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。

Forge highly privileged Kerberos Ticket Granting Tickets (TGTs) to gain persistent, undetectable, and long-term administrative access across an entire Active Directory domain. Use this skill during the final stages of a Red Team operation after Domain Admin access has been achieved, simulating an Advanced Persistent Threat (APT) establishing deep persistence that survives password resets.

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。

Execute a complete Active Directory penetration test from initial enumeration to domain dominance. Use this skill for AD security assessments including LDAP enumeration, Kerberos attacks (Kerberoasting, AS-REP roasting), BloodHound attack path analysis, credential dumping with Mimikatz, lateral movement via PsExec/WMI/DCOM, DCSync for NTDS extraction, and Golden/Silver ticket forging. Covers the full kill chain from domain user to domain admin.

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。

Stand up a fast, cached, isolated, disposable macOS CI lane on Tart — layered golden VM images, ephemeral per-job GitHub Actions runners, host-mounted caches, and a reusable per-repo vm-image manifest. Use when setting up VM-based CI for Pulp or generalizing it to another repo, building/refreshing golden images, wiring ephemeral runners, or debugging the VM lane.

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。

The measurement surface for ALL Pulp DSP and audio-pipeline work — read it BEFORE writing or gating DSP, not only when something already sounds wrong. Covers the C++ harness (signal generators, metrics, assertions, RenderScenario, contracts), the offline Audio Doctor (magnitude/frequency response, THD/THD+N, phase/group delay), and their Python sibling the Audio Quality Lab (tools/audio/quality-lab — null residual + alignment, LTAS log-spectral distance, spectral flux/centroid, HNR, Theil-Sen drift slope, Kaiser-sinc resampling, license-guarded corpus, regression-net ratchet). TRIGGER on AUTHORING work — "build/design an oscillator/filter/synth/effect", "add a DSP module", "what should the acceptance gate be", "how do I measure aliasing / anti-aliasing / alias floor", "null against a reference", "is this DSP correct", "choose a tolerance", "golden/regression corpus for audio", "measure drift or jitter", "A/B two renders" — AND on DEBUGGING work — "is there sound / no audio / I hear nothing", "does this filter/compressor/synth/delay produce the right signal", "prove the DSP / prove the contract", "measure the frequency response", "what's the THD / is it distorting", "what's the group delay / phase response / measured latency", "magnitude response curve", "render a test tone and assert", "audio regression", "64-frame works but 128 is silent", "sample-rate change pitch-shifted it", "describe what's in this buffer", "audio doctor", "compare before/after a DSP refactor". Reach for this BEFORE hand-rolling any FFT, null test, alias measurement, pitch tracker, or golden-render script — most of it already exists in one of the two lanes. Test/tool layer over HeadlessHost — deterministic, no audio device, no speakers. Off the realtime thread entirely.

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。

Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.

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。

Provides GKE golden path configuration defaults, production readiness checklists, and cluster default patterns. Use when designing GKE clusters, verifying GKE production readiness, or checking configurations against GKE defaults. Don't use for setting up workload autoscaling specifically (use gke-workload-scaling instead).

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。

golden-failed-check-repair-재현

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。

Rebuild the pgvector gold index after source data changes. Invoke manually — replaces each collection, do NOT trigger automatically.

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。

Perform DCSync attacks to replicate Active Directory credentials and establish domain persistence by extracting KRBTGT, Domain Admin, and service account hashes for Golden Ticket creation.

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 en platform engineering (developer experience, IDP, golden paths, self-service, métriques)

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 after changing prompts, skills, the compiler, or editorial policies — or when the user asks to measure edit quality, run regression evals, check agreement with approved edits, or says '評価して', '一致率を測って', 'eval を回して'. Compares agent output against human-approved golden projects.

Perform DCSync attacks to replicate Active Directory credentials and establish domain persistence by extracting KRBTGT, Domain Admin, and service account hashes for Golden Ticket creation.

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。