4,816 件 ・ 関連度順
概要と使いどころ
基于域健康报告和沙盘Gap记录，识别断裂模式，生成具体的补全行动方案：新Skill提案/现有Skill修改建议/缺失触发链路描述。与 skill-evolution-planner-meta 的区别：后者基于历史日志做宏观演进规划；本Skill基于具体Gap证据做定向修复。触发词：「优化[域名]域」「修复[域名]域Gap」「[域名]域自优化」「根据健康报告生成修复方案」。通常由 skill-closure-verifier-meta 调用，也可独立触发。
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。
认知-工作对齐健康检查（第四维）。验证五个工作域的核心产出是否可追溯到元思维体系（L1.5原则 or L1文档），识别「漂浮」的工作任务，输出对齐报告。与现有三维健康检查互补：skill-system-health-check（内部一致性）/ cognitive-consistency-check（认知自洽）/ skill-domain-health-check（传播完备性）+ 本Skill（认知根对齐）= 四维完整体系。触发词：「检查工作任务与认知的对齐」「第四维健康检查」「检查工作任务是否有认知根」「认知体系和工作任务是否自洽」「认知对齐检查」。
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。
Diagnose and fix slow pyfixest regression GRIDS (many feols/fepois calls run sequentially) that stay slow despite demeaner_backend="cupy64" and an idle GPU. Use when: (1) a script looping dozens of pf.feols models on a 100k+ row panel takes ~1 min/model, (2) process inspection shows ~1-1.5 cores busy and nvidia-smi shows ~0% GPU utilization with a resident cupy context, (3) planning any worker prompt that will run a model grid (robustness variants x FE structures x domains). Root cause: per-model CPU-side single-threaded fixed costs (formulaic model-matrix build, interaction construction, singleton detection, cluster vcov) dominate wall time; GPU demeaning is a small slice. Fix: shard the model grid across OS processes and/or use pyfixest multiple-estimation syntax; mandate this IN THE WORKER PROMPT.
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。
Set up, format, fix, and clean up LaTeX regression and estimation tables in empirical economics or finance papers. Use when (a) creating a .tex, results.tex, main.tex, or preamble to display regression or estimation output from Python (pyfixest), Stata, or R — including any mention of estout, esttab, estauto, estwide, or table fragments; (b) formatting or repairing estout-style regression tables that overflow the right margin, have cramped or boxed notes, misaligned columns, or poor significance stars, or when asked to match a reference paper, make the note fill the table width, or choose among \estwide, \estauto, and landscape layouts; (c) diagnosing "Misplaced \omit" errors from \input-ed table fragments inside tabular environments. Covers \@@input, \estwide, \estauto, \estautoLT, \specialcell, \sym, minipage notes below tabulars, and the convert-and-verify workflow. Do NOT trigger for general LaTeX documents like beamer presentations, problem sets, letters, or CVs.
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。
One-shot module map — go up a layer of abstraction and get a domain-vocabulary module map of the codebase. Use when lost in unfamiliar code, after a long deep-dive session, or when you need to re-orient before planning.
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。
Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators, maintains a debt register, and recommends repayment scheduling.
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。
Detect non-deterministic (flaky) tests by reading CI run logs or test result history. Aggregates pass rates per test, identifies intermittent failures, recommends quarantine or fix, and maintains a flaky test registry. Best run during Polish phase or after multiple CI runs.
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。
Map test coverage to GDD critical paths, identify fixed bugs without regression tests, flag coverage drift from new features, and maintain tests/regression-suite.md. Run after implementing a bug fix or before a release gate.
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 creating, maintaining, debugging, or reviewing real-browser end-to-end tests with Playwright or Cypress, including Page Object models, CI artifacts, traces, flaky tests, cross-page visual regression, and critical user journeys such as login, payment, permissions, or CRUD. For layer planning or tests close to UI components, choose the matching testing workflow first; Chinese triggers include E2E, end-to-end testing, Playwright, Cypress.
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 diagnosing structural maintainability problems in existing frontend code before deciding how to refactor it, especially when evidence, false-positive checks, and candidate transformations are needed without editing business code.
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 designing, implementing, or reviewing Tailwind CSS design systems, token mapping, theme extension, utility class governance, component variants, dark mode, responsive utilities, safelists, or maintainable class composition; Chinese triggers include Tailwind, design Token, component variants, dark mode, class management.
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 maintaining or safely modifying existing non-framework frontend code: vanilla JavaScript, jQuery, HTML/CSS, MPA pages, server-rendered templates, legacy plugins, or long-lived code that should stay in its current stack. Use migration skill when planning a move to React/Vue/TypeScript; Chinese triggers include traditional frontend, native JS, jQuery.
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 user asks for general frontend code review, PR review, merge-readiness assessment, architecture maintainability, type-safety, rendering/state risks, style consistency, testability gaps, or a cross-cutting review summary. Delegate deep security, accessibility, E2E, or performance investigations to their specialized skills; Chinese triggers include code review, code review, 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。
Validate OpenClaw release candidates through OCM using the built OpenClaw artifact, a broad reusable scenario matrix, copied existing-user state, clean new-user state, concise pass/fail reporting, and focused failure notes. Use when asked to test OpenClaw origin/main, release readiness, upgrade behavior, plugins, services, channels, doctor recovery, packaging, or broad release risk.
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 a task needs the judgment of an environmental engineer — designing or sizing a wastewater/water treatment process, drafting or reviewing an NPDES or Title V air permit application, scoping a contaminated-site remediation (RI/FS), evaluating whether a process change triggers a permit modification, or checking a discharge/emissions dataset against regulatory limits.
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 a task needs the judgment of an Engine and Other Machine Assembler — following the specified multi-stage torque sequence for a multi-bolt joint rather than tightening bolts to final value in convenient order, measuring bearing clearance directly rather than confirming free rotation by hand, verifying critical clearances on the actual assembled stack-up rather than trusting individually-in-tolerance components, or testing sub-assemblies before final integration rather than only at final test.
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 a task needs the judgment of an Energy Engineer working on building and industrial energy efficiency — running an ASHRAE Level 1/2/3 energy audit, calculating envelope heat loss/gain with the degree-day method, comparing HVAC equipment on SEER/EER/IEER/COP rather than nameplate alone, designing an IPMVP measurement and verification (M&V) plan, or ranking energy conservation measures (ECMs) by savings-to-investment ratio for a capital plan. Distinct from a wind-energy-engineer or solar/PV engineer (own generation-asset design and yield) and from an electrical-engineer (owns utility-scale power delivery and protection) — this role owns the demand side: how much energy a building or process actually needs, and which retrofit reduces that number with numbers that hold up after the fact.
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 a task needs the judgment of an Energy Auditor — running a blower-door/duct-leakage diagnostic sequence on a home or light-commercial building, testing combustion appliances for worst-case backdraft risk before recommending air sealing, reconciling utility billing history against walkthrough findings, ranking retrofit measures by savings-to-investment ratio (SIR) for a weatherization or utility rebate program, or writing the prioritized scope of work an install crew executes without the auditor on site. Distinct from an energy-engineer (industrial/commercial capital planning, IPMVP measurement and verification, calibrated simulation) — this role owns the field diagnostics and the residential/light-commercial audit-to-scope handoff.
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 a task needs the judgment of an Endoscopy Technician — deciding whether to release or quarantine a scope after a failed leak test or minimum-effective-concentration (MEC) reading, handling a point-of-use treatment delay against the manufacturer's reprocessing window, triaging a borescope finding on a working channel, or troubleshooting equipment and passing accessories during a live GI procedure.
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 a task needs the judgment of an emergency medicine physician — risk-stratifying an undifferentiated chief complaint against a can't-miss diagnosis, deciding an ED disposition (discharge/observation/admit/transfer) under time and bed pressure, reasoning through EMTALA screening-and-stabilization obligations, or triaging a department under crowding/boarding load.
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 a task needs the judgment of an EMT (Basic Life Support tier) — deciding whether a chest-pain patient gets aspirin under protocol, dosing an epinephrine auto-injector for anaphylaxis and knowing when to repeat it, applying spinal-motion-restriction criteria instead of routine backboarding, recognizing the moment a call exceeds BLS scope and requesting ALS intercept, or working a patient refusal (AMA) to a legally defensible conclusion.
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 a task needs the judgment of an English Language and Literature Professor — backward-designing a first-year composition or literature syllabus against a shared outcomes rubric, deciding whether an AI-detection or plagiarism flag on a student essay warrants an integrity case, reading where a tenure case's monograph actually sits in a university press's pipeline, or handling a content complaint about an assigned literary text.
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 a task needs the judgment of an Engineering Teacher, Postsecondary — diagnosing a spike in a gatekeeper course's D/F/W rate, running a capstone design course with an industry sponsor, closing the loop on an ABET student-outcome assessment, or building a tenure/promotion teaching-effectiveness case beyond raw student evaluation scores.
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。