「the」の検索結果

Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end. Covers extracting the implicit repro from a thin report (env, build, steps, data), the reproduce-minimize-isolate-capture loop, git bisect to find the introducing commit, building a deterministic minimal repro (fixed seeds, frozen time, stubbed network), writing the failing regression test BEFORE the fix (red) and confirming the fix flips it green, and writing repro evidence back into the ticket. Distinguishes flaky-not-reproducible from environment-specific. Use when: "reproduce this bug," "minimal reproduction," "repro steps," "find the commit that broke it," "git bisect," "make the repro deterministic," "write a failing test for this bug," "regression test for a defect," "can't reproduce this bug." Not for: Classifying/deduplicating/severity-routing existing failures without reproducing them — that is ai-bug-triage. Generating tests from specs rather than from a defect — that is ai-test-generation. Related: ai-bug-triage, ai-test-generation, test-reliability, systematic-debugging, qa-project-context.

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 craft of weaving story into interactive systems where the player is both audience and author. This skill covers the unique challenges of game narrative: branching structures that respect player agency, environmental storytelling that rewards exploration, dialogue systems that feel alive, and the delicate balance between authored experience and emergent narrative. Unlike linear media, games don't tell stories TO players - they create the conditions for stories to emerge WITH players. The narrative designer's job is to build the scaffolding that supports infinite player-authored moments while maintaining coherent themes and emotional arcs. This skill synthesizes lessons from Disco Elysium's internal monologue as gameplay, Hades' death-as-narrative-engine, interactive fiction's branching mastery (Inkle, Twine), and procedural narrative pioneers like Dwarf Fortress. It addresses ludonarrative harmony, bark systems, cinematics that respect agency, and the "and therefore" test that separates plot from story. Use when "narrative design, game story, game writing, dialogue system, branching narrative, player choice, environmental storytelling, bark system, quest design, lore delivery, ludonarrative, interactive fiction, inkle, twine, dialogue tree, player agency, cinematic design, voice direction, localization, procedural narrative, narrative, game-writing, dialogue, branching, player-agency, environmental-storytelling, quest-design, voice-acting, localization, interactive-fiction, procedural-narrative, ludonarrative" mentioned.

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。

Legendary blog writing that makes readers forget they're reading. This skill combines the narrative mastery of Paul Graham's essays, the technical accessibility of Julia Evans, the conversational wit of Wait But Why, and the viral mechanics of James Clear. Great blog posts don't inform—they transform. They take complex ideas and make them feel obvious. They turn strangers into superfans. They get shared not because someone should read them, but because someone needs to read them. This skill adapts to any topic: cybersecurity that reads like a thriller, AI explainers that feel like conversations, marketing insights that make you screenshot every paragraph, and coding tutorials that make you excited to build. Use when "write a blog post, blog post about, write an article, create content about, explain this topic, write about, long-form content, thought leadership, technical blog, how-to article, tutorial post, educational content, industry analysis, opinion piece, newsletter content, make this engaging, write for developers, explain like, writing, blog, content, articles, long-form, storytelling, technical-writing, thought-leadership, educational, tutorials, explainers, engagement" mentioned.

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。

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".

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。

游戏设计 (Game Design) — 设计游戏的规则 / 系统 / 机制 / 体验 的从业者认知操作系统 (以电子游戏为主, 含桌游 / 卡牌 / 棋盘游戏): 决定「玩家做什么、为什么有意义、每一刻的体验如何」的学科 —— 区别于游戏程序 (引擎 / 代码)、游戏美术 (视觉 / 音频)、游戏制作 (排期 / 预算 / 团队)。覆盖 (a) 核心设计理论与框架 (MDA 机制-动态-美学 Hunicke/LeBlanc/Zubek + Schell 的「透镜」+ Koster「乐趣即学习」理论 + Sid Meier「一连串有趣的决策」+ Salen & Zimmerman「有意义的游玩」/「二阶设计」/「魔法圈」+ Costikyan 论不确定性 + Suits/Huizinga 游戏哲学), (b) 系统与机制设计 (核心循环 + 游戏经济 sink/source/产出-消耗 + 正负反馈环 + 资源与成长系统 + 涌现 vs 脚本 Will Wright「可能性空间」+ Machinations 经济建模 Dormans + 支配 / 退化策略 + 正交设计 Garfield), (c) 关卡与遭遇设计 (灰盒 blockout + 节奏与张力 + 预告 telegraphing + 主线 vs 探索 + 环境叙事 + 锁钥 gating + 难度曲线), (d) 游戏手感与「juice」(Steve Swink《Game Feel》+ 即时响应 + 屏震 / 反馈 / 打磨 + 输入与镜头 + 「手感」是设计出来的不是附带的), (e) 玩家心理与 UX (Celia Hodent《The Gamer's Brain》+ 心流通道 挑战 vs 技能 Csikszentmihalyi/陈星汉 Jenova Chen + Bartle 玩家类型 + 动机与奖励节奏 + 新手引导 FTUE / 教学化 + 认知负荷 + 无障碍), (f) 平衡与调优 (Ian Schreiber《Game Balance》+ 对称 / 非对称 + 动态难度 DDA + 传递 / 非传递平衡 + nerf/buff + 消除支配策略 + 测试驱动调优), (g) 叙事与任务设计 (ludonarrative 失调 / 和谐 + 环境与系统叙事 + 分支 vs 线性 + Amy Hennig 角色驱动 + 任务结构), (h) 以玩家为中心的迭代流程 (Tracy Fullerton《Game Design Workshop》playcentric + 纸面原型 + 垂直切片 + 测试协议「看而不说 / 你不是你的玩家」+ 快速迭代 + game jam), (i) 类型与形态工艺 (roguelike/roguelite 与程序生成 Derek Yu + 平台跳跃 + RPG 系统 + 策略 4X + 解谜设计 Jonathan Blow + 多人 / PvP 平衡 + 桌游 / 卡牌设计 Reiner Knizia/Richard Garfield/Brenda Romero), (j) F2P / 长线运营 / 商业化设计 (核心 / 元 / 经济循环 + 抽卡 gacha / 开箱 loot box / 战令 battle pass 机制 + 留存 D1/D7/D30 + 转化 + 鲸鱼 + live ops 内容节奏 —— 并诚实处理掠夺式暗黑模式 / 强迫循环 / 剥削式商业化的伦理), (k) 设计师角色与工艺职业 (系统 / 关卡 / 叙事 / UX 设计师之分 + 通才 vs 专才 + 独立作者 vs 3A 团队 + 设计文档 + 传达设计意图 + GDC 工艺社区)。跨 3A / 独立 / 手游 F2P / 桌游。不含 游戏程序 / 引擎 (Unity/Unreal 编码 / 图形 / 网络同步) / 游戏美术 / 动画 / 音频 / 游戏制作 / 项目管理 / 排期 / QA / 游戏作为生意 / 发行 / 市场 / 电竞运营为终点 / 泛泛「我想做游戏」的 game-dev 教程 —— 本 skill 是「设计」学科: 规则 / 系统 / 机制 / 体验。 (Game Design — the cognitive operating system of practitioners who design the rules, systems, mechanics, and experiences of games (video games primarily, plus tabletop/board/card games): the discipline of deciding WHAT the player does, WHY it is meaningful, and HOW the moment-to-moment experience feels — distinct from game programming (builds the engine/code), game art (visuals/audio), and game production (schedule/budget/team). Covers (a) core design theory & frameworks (MDA Mechanics-Dynamics-Aesthetics Hunicke/LeBlanc/Zubek, Schell's Lenses, Koster's theory of fun = learning, Sid Meier 'a series of interesting decisions', Salen & Zimmerman 'meaningful play'/'second-order design'/'magic circle', Costikyan on uncertainty, Suits/Huizinga play philosophy), (b) systems & mechanics design (core loops, game economy sink/source/faucet-drain, feedback loops positive/negative, resource & progression systems, emergence vs scripting Will Wright 'possibility space', Machinations economy modeling Dormans, dominant/degenerate strategy, orthogonal design Garfield), (c) level & encounter design (blockout/greybox, pacing & tension, telegraphing, critical path vs exploration, environmental storytelling, gating & lock-and-key, difficulty curve), (d) game feel & juice (Steve Swink 'Game Feel', moment-to-moment responsiveness, screenshake/feedback/polish, input & camera, the 'feel' is designed not incidental), (e) player psychology & UX (Celia Hodent 'The Gamer's Brain', flow channel challenge-vs-skill Csikszentmihalyi/Jenova Chen, Bartle player types, motivation & reward schedules, onboarding/FTUE/tutorialization, cognitive load, accessibility), (f) balancing & tuning (Ian Schreiber 'Game Balance', symmetry/asymmetry, dynamic difficulty adjustment DDA, transitive/intransitive balance, nerf/buff, dominant strategy elimination, playtesting-driven tuning), (g) narrative & quest design (ludonarrative dissonance/harmony, environmental & systemic storytelling, branching vs linear, Amy Hennig character-driven, quest structure), (h) player-centric iterative process (Tracy Fullerton 'Game Design Workshop' playcentric design, paper prototyping, vertical slice, playtesting protocol 'watch don't talk / you are not your play

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。

Applies the existentialist and feminist philosophy of Simone de Beauvoir, French philosopher and author of The Second Sex. Reach for this skill whenever the user is grappling with existential dilemmas, moral ambiguity, gender dynamics, societal expectations, or relationship ethics. Trigger this skill for questions about freedom versus responsibility, bodily autonomy, marginalization, or when the user feels trapped by external labels or "immanence." Use this to help the user reclaim their agency, recognize the social construction of their situation, and make authentic choices that expand their transcendence while respecting the interconnected freedom of others.

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。

Bug-fix routine that fixes the whole class of bug, not just the reported instance. Use for any bug report, failing production behaviour, monitoring alert, audit finding or review finding that does real harm (a smaller review finding goes on the item's list, as ship-check says), and whenever the same kind of bug has been seen before. Reproduces it with a failing test, names the failure class, searches the task's scope for the same pattern (the whole codebase when the user's own prompt asks for the fix, not when it is picked from a task's list), fixes or records every hit, and adds the rule, invariant, helper or check that stops it coming back.

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。

Learns the words a user habitually writes to their coding agent that make its answers worse ("be 100% sure", "don't assume", "full review", "are you sure?", "all fine, right?"), from what they actually typed in their recent Claude Code sessions. Shows what each one does, what went wrong after it, and what to say instead, then writes the habit words block that maps each word to the checks it should trigger, so the checks run without the words. Use when asked to learn, read, refresh or review the user's habit words or prompts, "which of my words make you worse", from setup-first-pass's profile step, or when the start-of-session check says the habit words are due.

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。

Read this skill before the first step that uses the built-in browser, the browser pane inside the Claude desktop app (also called the in-app browser, the browser pane, Claude's browser, or "your own browser"), whose tools are named mcp__Claude_Browser__* when the session runs in the desktop app and mcp__remote-devices__Claude_Browser__* when a cloud session is linked to the person's computer; before those tools are turned on there may be a single enable__mcp__remote-devices__Claude_Browser tool instead. It covers the pane's persistent sign-ins, tabs and preview_start, reading pages as text, site approvals, what the pane cannot open, and what to do when it cannot be reached. It is not for Claude in Chrome (mcp__claude-in-chrome__* tools), which has its own skill, and it does not decide which browser to use.

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。

Install a Skill into the current workspace from a Git repository or local directory. Use this whenever the user wants to: - Add a new Skill to the agent ("install the X skill", "add the foo skill", "I want a skill that does Y, find one") - Pull the latest version of an already-installed Skill ("update the X skill", "refresh my skills") - List Skills currently active in the workspace - Remove a Skill they no longer need Trigger on phrases like "装一个 X skill", "安装技能", "install skill", "update skill", "list skills", "remove skill", "找个能 X 的 skill". Do not require the user to say the literal Skill name — if they describe a capability, propose a candidate Skill (Git URL or local path) and confirm before installing.

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。

Your competitor just launched. You have no idea how they grew so fast. Should you reverse-engineer their website? Track their social media? Map their growth flywheel? This gives you the complete SOP — from Wayback Machine snapshots to X/Twitter propagation analysis to growth flywheel scoring. Built from 150+ AI startup competitive analyses including the Lovable case study (4.3M views, 229K impressions launch day). By @WeiYipei. What's inside: • 4-step research framework (website teardown → social media → traffic sources → ad spend) • 3-version website evolution analysis (V1 / Beta / Launch via Wayback Machine) • X/Twitter propagation chain mapping (4-phase model + single-post teardown template) • Growth flywheel 6-stage scoring system (Activation → Referral → Acquisition → Retention → Revenue → Product) • KOL identification framework (Traffic King / Topic Starter / Mindset Shifter) • Content effectiveness ranking (validated: Visual Demo > User Story > Competitor Comparison) • ICP deep analysis template + Freemium pricing teardown • Complete self-check checklist 🇨🇳 你的竞品刚刚爆了。你完全不知道他们怎么做到的。该拆官网？盯社媒？画增长飞轮？这份 SOP 给你从 Wayback Machine 快照到 X/Twitter 传播链路还原到飞轮六阶段评分的完整方法论。基于 150+ AI 创业公司竞品分析实战，含 Lovable 完整案例。 🇯🇵 競合が突然バズった。どうやって成長したか全く分からない。このSOPは、Waybackスナップショットからツイッター伝播チェーン分析、フライホイール6段階スコアリングまでの完全な競合調査フレームワークを提供します。150以上のAIスタートアップ分析から構築。 🇰🇷 경쟁사가 갑자기 폭발적으로 성장했습니다. 어떻게 그렇게 빨리 성장했는지 모릅니다. 이 SOP는 Wayback 스냅샷부터 X/Twitter 전파 체인 분석, 플라이휠 6단계 스코어링까지 완전한 경쟁사 조사 프레임워크를 제공합니다. 150개 이상의 AI 스타트업 분석에서 구축. Triggers: "competitor research" | "competitive analysis" | "competitor analysis" | "growth flywheel" | "market research" | "竞品调研" | "竞品分析" | "增长飞轮" | "传播链路" | "競合分析" | "경쟁사 분석" | "social media teardown" | "Twitter propagation" | "content strategy analysis"

Act as a project-management copilot (PM/PMO) for the delivery loop: charters, plans and schedules, estimates, risk registers, status reports, scope changes, stakeholder communication, meeting actions, lessons learned, and portfolio roll-ups, in a per-project `_project/` workspace. Use whenever the user wants to start, plan, track, rescue, or report on a project: "kick off this project", "make a project plan / timeline / WBS", "what date can I commit to", "build a risk register", "run a pre-mortem", "write the weekly status report", "the deadline slipped, what now", "turn this meeting into action items", "review my project portfolio", in any language ("quản lý dự án", "gestion de projet", "プロジェクト管理", "项目管理"), even when they never say "project management". Also use whenever a `_project/` directory exists and the user asks about schedule, deadline, risk, status, scope, budget, or stakeholders. Not for what to build (product-manager) or company-level bets (strategy-board).

Comparative framing across contemplative and mind-body traditions — Sōtō Zen and Rinzai Zen, Theravada vipassana, Tibetan Vajrayana, classical yoga and its eight limbs, Daoist internal cultivation, secular MBSR and MBCT, engaged mindfulness as Thich Nhat Hanh teaches it, Christian contemplative prayer, Sufi dhikr, the Hesychast tradition of the Eastern Orthodox church — for the routing agent who has to understand where a user is already standing before recommending a practice. Covers the pedagogical voice of each tradition, the places they overlap, the places they genuinely disagree, and the non-sectarian framing the college department uses. Use when a user arrives with a prior tradition, when a query spans more than one tradition, or when the agent needs a vocabulary for what is shared and what is lineage-specific.

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。

Post a sitrep (situation report) for a live incident, in its incident channel: a short fixed-layout update for people who haven't read the whole channel — the current picture and what moved since the previous update. Use on "sitrep", "status update", "where are we", "what's the latest", "catch me up", "summarize the incident so far", when asked to keep posting on a schedule ("post a sitrep every hour until resolved"), or when the oncall memory sets an update cadence for this severity and the incident owner asks Claude to keep it. Reads the channel, alert thread and findings posted, re-reads the one key signal, and writes: status line, TL;DR, impact, what changed since the last sitrep, what's in progress and who has it, what's needed, when the next update comes, one chart. Facts come only from what people said or Claude read first-hand; cause and recovery time are never guessed. Fits one phone screen. Not investigation (`incident-investigate`) or the write-up afterwards (`incident-postmortem`).

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。

Write the postmortem for an incident, in its incident channel, once it is mitigated or resolved. Use on "write up this incident", "postmortem", "incident summary", "what happened here for people who weren't around", "draft the retro", or when the oncall memory says incidents of this severity get one. Reads the incident channel (and the alert thread it came from), the investigation findings and the data behind them, and writes a one-screen, zero-context write-up: what happened, impact with numbers, detection, timeline with durations, why it happened, what fixed it, follow-ups with proposed owners, and one before/during/after chart. Posted and pinned in the incident channel as its final pinned post, with edit requests updating that one pinned post in place — unless the person or the team's conventions say write-ups live elsewhere, in which case it is written there and only a link is posted, nothing pinned. A person edits and publishes it; never assigns blame.

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。

Drive a GitHub Copilot (or any bot reviewer) pull-request review to a clean pass without babysitting it: fix each finding in its own commit, reply to the review thread with the fix sha, resolve the thread, re-request the bot, and poll for the async re-review. Covers the thread node-id (PRRT_...) vs comment databaseId distinction, the resolveReviewThread GraphQL mutation, the copilot-pull-request-reviewer[bot] slug, and how to read the bot's verdict (COMMENTED plus a "human review recommended" banner is not a blocking finding). Use when Copilot has left review comments on your PR, when bot review threads must be closed out with an auditable fix-reply-resolve trail before merge, or when you need to verify that a re-review actually landed on the new HEAD rather than the old one.

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。

Run the memex session-init ritual at the start of a fresh session: load the bias-log, read the persistent-self trail in order, run the verification scoreboard, and surface the next slice from the docs. Use at the very start of any session that operates on the memex repo, when reconstructing context before doing work, or when an interrupted session needs to re-orient. NOT the `memex init` CLI command (which initializes the store/db) — this is the reconstruct-context ritual.

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。

Recover from stale RFDB nodes that survive `commit_batch` cleanup despite having their `file` field listed in `changed_files`. Use when: (1) re-running an enricher/orchestrator step but old data with the same file field stays in the graph, (2) `commit_batch(changed_files=[X], ...)` reports success but a query later still returns nodes with `file = X`, (3) you re-pointed structural nodes (e.g., DIRECTORY/FILE) from a synthetic file path to real file paths and the old synthetic-path nodes won't go away, (4) graph-stream / find_by_type returns a mix of "stale" and "new" nodes for the same logical entity. Root cause: `handle_commit_batch` calls `engine.find_by_attr({file: X})` to enumerate nodes-to-delete, but that query path returns only a PARTIAL set after compaction (L1 segments and the file→nodes index can desync). Workaround: enumerate stale nodes via the TS rfdb client `queryNodes({file: X})` (different code path that finds all of them) and call `deleteNode(id)` per node, then re-commit the intended state. Related: rfdb-manifest-l1-carryforward (same L1 family).

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 any material decision — code chunk, plan, strategy, design, scope cut, push to GitHub — convene a war-room. The session driver takes the CEO seat: frame the tradeoff, summon specialist seats from whatever agent roster the user has built, dispatch a cross-family voice via `ato dispatch` so priors actually disagree, decide. A failure-mode filter (wrong assumptions / overcomplexity / orthogonal edits / imperative-over-declarative — Karpathy's four are one good default, swap in your own) runs on every dispatch. Place in the v2.16 stack: war-rooms DECIDE before code starts; `ato-mission` EXECUTES the work between decisions (multi-step, goal-driven, persisted across days); `ato-review` VERIFIES the resulting commits. Use a war-room for the design verdict, hand the verdict to a Mission, review the merged result. Fires before: sending a code draft to the user as final, opening a PR, pushing to a remote-tracking branch, committing >50 LOC of behavior change, or delivering a plan or strategic recommendation as the final answer.

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。

Run the Upstash CLI (`upstash`) from a terminal, shell script, or CI job when no Upstash MCP tools are in the session. Do not load this skill when Upstash MCP tools are available (the Upstash plugin registers mcp.upstash.com) - they already cover creating, listing, renaming, and deleting Redis databases, running Redis commands, usage stats, backups, Vector and Search indexes, QStash schedules and messages, Blob buckets, and Box, so call them directly. Use this skill for shell work the MCP does not do - a CI step or provisioning script that needs `upstash` commands with JSON output, piping results into other commands, `upstash auth login` and API-key setup, team and member management, changing plans, regions, TLS, eviction, auto-upgrade, or budgets, minting temporary S3 credentials for a Blob bucket, connecting a coding agent to Upstash with `upstash setup` (the Upstash plugin, or the remote MCP server plus skills), or when the user explicitly asks for the CLI or for managing Upstash without the console.

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。

Clones a VIDEO ad end to end for a different product or offer, on the Novoads API. The deliverable is a finished rendered MP4 — the WHOLE ad, not its opening, and not a template. Reads the source's style, pacing, camera work, dialogue and tone, adapts it into a Seedance 2.0 prompt, prices it, renders it, files the source beside the clones and diffs each clip's transcript against the approved script. Use for "clone this video ad", "recreate this video for my brand", "make this ad but for my product" when the source is a video, "clone my competitors' VIDEO ads", or a video ad handed over with a product photo. **Among cloners the source's medium decides, not the wording**: "clone this ad" plus a video lands here; a still, or nothing attached, is clone-image-ad, and animating a still as-is is image-to-motion. This pack has no hook-only skill: for the opening alone, clone the whole ad and cut. If it does not move, wrong skill.

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。

Sales enablement, technical presales and deal acceleration for B2B SaaS revenue teams. Use this skill when planning outbound campaigns, running discovery calls, building deal strategy, creating battle cards, writing proposals, responding to RFPs, preparing a product demo, scoping a proof of concept or pilot, answering a security questionnaire or the AI annex buyers now attach to it, executing sales sequences, coaching qualification, or deciding what the website's AI chat agent is allowed to say. Also triggers on: outbound, cold outreach, reply handling, reply classification, out-of-office replies, auto-replies counted as replies, our reply rate is inflated, prospect replied remove me, opt-out by reply, is this list ready to send, launch readiness, CRM segment outbound, we emailed a current customer, outbound hit an open opportunity, ownerless leads, prospects engaging our competitors, competitor connections, displacement list, is this personalization creepy, can we mention they visited our site, signal freshness, deal strategy, pipeline, battle card, objection handling, common objections, why do we keep hearing this objection, mine call transcripts for objections, objection register, proposal, RFP, discovery call, MEDDPICC, sales sequence, qualification, sales engineer, solutions engineer, presales, demo plan, demo script, POC, proof of concept, pilot success criteria, technical evaluation, technical win, security questionnaire, vendor security review, SOC 2 questionnaire, AI security questionnaire, AI annex, AI vendor due diligence, the buyer is asking if we train on their data, do you train on customer data, which model do you use, model provider sub-processor, AI subprocessor disclosure, where does inference run, can the customer turn the AI feature off, AI-CAIQ, CSA AI Controls Matrix, ISO 42001, ISO/IEC 42001, NIST AI RMF, EU AI Act Article 50, are we a provider or a deployer, AI feature disclosure, our model vendor changed and nobody told the buyer, technical objection, mutual action plan, MAP, close plan, mutual close plan, buyer enablement, the deal is stalled, deal stalled after the demo, how do I get this deal to close, close date keeps slipping, JOLT, buyer indecision, no-decision loss, website chatbot, chat widget, AI chat agent, AI SDR, inbound AI SDR, conversational marketing, live chat, what should our chatbot be allowed to say, our chatbot quoted the wrong price, the bot promised a discount, do we have to disclose it is AI, EU AI Act chatbot disclosure, chatbot handoff to sales, chat transcript review, prompt injection on our chatbot, Drift, Qualified, Intercom.

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 the Skmtc CLI to scaffold projects, install or clone generators from JSR, configure schema sources and enrichments, and produce code artifacts from an OpenAPI v3 or GraphQL SDL schema. Teaches the workspace mental model (`<root>/.skmtc/<project>/`, client.json, bundle, manifest) and the agent contract (strict text / strict JSON modes, exit codes, recipe errors, `agent-context` + `doctor`); the command surface itself is discovered from the binary — `skmtc --help`, `skmtc <cmd> -h` — rather than carried in this skill. Use this skill when the user asks to "run skmtc", "generate code from an OpenAPI schema", "install a skmtc generator", "scaffold a skmtc project", "watch a skmtc project", "configure enrichments", "publish a stack", "deploy to skmtc-hub" (the command is `publish`; there is no `deploy`), "skmtc in CI", or invokes any CLI subcommand. For *authoring* a generator package (Projections, Snippets, transform functions), defer to `skmtc-generator`. When something is broken (no output, wrong output, error messages, a failed bundle build), verify before proposing a fix: read the manifest and the parse issues, and reproduce the failure first.

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。