「judge」の検索結果

Report how many problems the two brains found: mutual review (the other model checks the work, from the peer-review records) and self-check (an agent finds its own error in its own conversation, judged by that agent's own model), side by side. Use when the owner asks whether the second agent or the reviews are worth it, or wants the week's review results.

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。

Surfaces Han's shared Human-Readable Output Standard — the readability rule and the writing-voice profile — into the calling skill's own context, so the caller drafts in voice and runs its self-check against the current standard sourced from one canonical copy. Use when a prose-producing skill needs the shared readability standard available in context before it drafts. Governs the shape of a written deliverable, where explanation-guidance governs what a run says to a person in a turn. Runs in the caller's context and hands control straight back; it does not produce a deliverable of its own, rewrite anything, or judge the caller's work. Does not run the adversarial rewrite pass — dispatch the readability-editor agent for that, or use edit-for-readability to rewrite an existing target. Does not cover explaining technical work to a reader who will not implement it — use explanation-guidance for that.

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 Han's shared Human-Readable Output Standard to a target you already have — a file on disk, text pasted into the prompt, or a draft already produced in the conversation — by dispatching the readability-editor to rewrite its prose so the main point comes first, headings are descriptive, each paragraph carries one idea, and sentences stay short and active, while preserving every fact. Use when you want to make a document or draft readable, edit or polish prose for readability, clean up writing, tighten wording, or re-apply the readability standard to something already written. Rewrites prose only, leaving code, diagrams, and citation identifiers unchanged. Does not write new feature or system documentation — use project-documentation. Does not restructure code or review it — use refactor to restructure code and code-review to audit it. Does not judge the underlying work or raise findings; it only rewrites the writing.

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。

Surfaces Han's shared standard for explaining technical work to a reader who will not implement it into the calling skill's own context, so the caller writes its escalations, confirmation turns, and stops as a concrete outcome the reader could observe rather than as a mechanism. Use when a skill is about to ask a person a question, stop for an input, or explain a technical consequence to someone who will not open the code. Governs what a run says to a person in a turn, where readability-guidance governs the shape of a written deliverable. Runs in the caller's context and hands control straight back; it does not produce a deliverable of its own, rewrite anything, or judge the caller's work. Carries guidance only and adds no self-check step.

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 choosing between engines or models for an agent pipeline and the answer must come from measurement on your own data, not from marketing pages: speech recognition for meeting recordings, the model that turns a transcript into notes, the critic model that checks it. Runs every variant in an isolated container, measures time, cost per hour of input (USD and RUB, with price source and date) and quality (WER/CER and course terms for ASR; code checks plus a judge of a different model for LLM steps), writes results.json/csv and one static analytics page. Triggers on "бенчмарк", "сравни движки", "сколько стоит час записи", "какую модель взять для пайплайна", "benchmark the pipeline", "compare ASR engines".

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。

Inspect an unfamiliar repository, turn a focused Markdown behavior scenario into a deterministic test in the repository's native test stack, run it, and preserve traceability between intent and code. Use when asked to add scenario tests, compile acceptance criteria or Given/When/Then Markdown into executable tests, reproduce a user-visible regression, or convert a narrow workflow specification into stable web, API, CLI, desktop, or mobile interaction coverage. Do not use for broad exploratory journeys or agent-judged smoke tests.

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 weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced runs) to perform real document tasks over six scenarios — five editing (MNDA form-fill + font fidelity, invoice table-edit/restructure + logo replace, résumé styling, contract redlining + commenting, contract finalize via accept/reject + comment reply/resolve) and one authoring (T. S. Eliot poetry journal: multi-column, verse, footnotes, links, figure) — renders every result with Word, has opus judge them against ground-truth rubrics, measures each exercise's tool economy, token cost, wall-clock, and correctness (from transcripts for Claude, the exercise.json ledger for the local harness), and synthesizes a prioritized ergonomics report. Use when the user says 'adversarial review', 'test docx-cli with weak agents', 'run the haiku harness', 'weak agent test', or wants to re-run yesterday's adversarial process.

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 Machine Learning Engineer. Use when a task calls for Machine Learning Engineer judgment. Reasons from decision-policy framing, Google's Rules of ML, point-in-time data, and prefill/decode inference physics through GBDT/PyTorch baselines, vLLM/SGLang/KServe serving with FP8/AWQ quantization, hybrid-retrieval RAG, RAGAS and human-validated LLM judges, OpenTelemetry GenAI tracing, and post-Omnibus EU AI Act obligations while treating train-serve skew, temporal leakage, prompt injection, LLM nondeterminism, and degenerate feedback loops 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。

Review SDS-PAGE or protein purification gel images using DNA sequence, protein sequence, base-pair length, expected protein size, and lane labels. Use when the user wants to judge whether a gel ran well, whether the main band matches the expected product, or whether there may be impurities, degradation, aggregation, or low expression.

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。

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

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 AI-generated text using rule-based analysis, LLM-as-judge scoring, and optional external APIs. Use when: auditing content for AI authorship, academic integrity checks, editorial review, SEO content audits.

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 AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch prompt regressions", "compare models", "evaluate LLM output quality", "set up AI quality gates", or "benchmark my agent before deploying". Covers eval frameworks (Cobalt, Promptfoo, Braintrust), LLM-as-judge scoring, threshold-based assertions, and GitHub Actions integration.

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。

Advanced Evaluation workflow skill. Use this skill when the user needs This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover, music, sound effects, and other hard constraints. Use when a user wants to turn an idea, story, feeling, or rough/over-specified prompt into a strong text-to-video prompt (Seedance, Sora, Kling, Veo, Runway, etc.), or asks to "rewrite", "improve", "clean up", or "vibe-ify" a video prompt. Do NOT use for long narrative films that need precise word-for-word dialogue sync, industrial shot lists meant to be executed verbatim, or functional/UI demos and step-by-step tutorials.

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 running or explaining the ClawScan CLI, including one-off agent-skill scans, benchmark runs, scanner fixtures, judge harness commands, env var validation, and interpreting clawscan-run-v1 and clawscan-benchmark-v1 artifacts.

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。

Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.

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 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs the local eval harness (golden fixtures × champion-vs-candidate, same input), dispatches blind pairwise judge subagents, aggregates a win-rate verdict, and on approval promotes the candidate into agent/src/prompts/mine.js. Triggers — "评估 prompt"、"挖矿 prompt 改好了吗"、"eval prompt"、"比一比两版 prompt"、"/wjs-evaling-voicedrop-prompts".

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 王建硕 wants to systematically improve his X (Twitter) content by iterating on the content-generation prompt (prompts/x/prompt.md, used by the every-6h tweet Action) and finding which prompt version produces the highest-reach tweets. Each prompt edit is a git-SHA-versioned, numbered experiment with a hypothesis; tweets are attributed to the version live at post time and judged on median impressions per tweet. Also mines per-tweet impression data for content-feature signals (angle / length / topic) that feed the next prompt edit. North-star = impressions per tweet. Triggers — "改 X 的 prompt", "X 内容改进", "哪版 prompt 最好", "什么内容 impression 高", "improve my tweets", "A/B test the X prompt", "/wjs-x-improving-content".

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 王建硕 wants to systematically grow his X (Twitter) followers by running numbered, A/B-testable growth experiments and tracking which ones actually work. Every action gets a number, a hypothesis, a target metric, a before-state (for rollback), and a verdict. The North-Star metric is the new-follower ÷ profile-visit ratio (conversion) — every profile change is judged against it. Daily it ingests the X Analytics CSV export, scores each running experiment, and recommends keep / rollback. Triggers — "涨粉", "增加 X 粉丝", "X 涨粉实验", "follower growth", "A/B test my profile", "今天的涨粉检查", "/wjs-x-increasing-follower".

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。

Judge claims through evidence and alternatives.

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。

Suede AI findings-only code review with full context: changed files, callers, contracts, and deploy surface. Covers TypeScript, React, Next.js, database, Swift/iOS, OWASP, accessibility, SEO, observability, commit hygiene, and deploy risk, ranked P0-P3 with file:line evidence and a fix path. Use when asked to review a diff, PR, branch, or commit range, find the bugs before merge, check a change for security or accessibility problems, or judge whether a change is safe to deploy. Emits findings and a ship gate, not a grade. NOT FOR: the A-F letter grade alone (use suede-code-grader); findings plus grade in one pass (use suede-code); making CI enforce the result on every merge (use suede-ci-gate); root-causing a live bug or failing test (a private Suede Labs companion, not in this pack).

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。

Suede AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates. Use when a change ships LLM, RAG, agent, classifier, prompt, or generated-media behavior, or when asked to write evals for an AI feature, design test cases for a model surface, audit existing eval coverage, or judge whether AI behavior is safe to ship. No AI-SPEC means no eval plan, and no eval plan holds the recommended ship verdict. NOT FOR: reviewing or grading the implementation code behind the AI surface (use suede-code); wiring a passing suite into CI as a required check (use suede-ci-gate); UAT of the built feature beyond the eval suite (a private Suede Labs companion, not in this pack).

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 diff changes a GitHub Actions workflow, a reusable action, a Dockerfile or compose file, Terraform/HCL, Kubernetes manifests or Helm values, or a cloud OIDC trust policy - judged only where concretely exploitable

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 methods a financial-ML result has to survive before it is evidence — purged cross-validation with an embargo, triple-barrier labelling, sample uniqueness under overlapping labels, fractional differentiation, meta-labelling, and multiple-testing correction. Written because the invariants were required of quant-researcher and nothing in the project explained how to satisfy them: a rule without a method produces either an invention or a block. Applied whenever a backtest, a feature or a label is being designed or judged.

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。