「rubric」の検索結果

Use when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and needs to turn them into principles. Outputs a v0 grader in 30 minutes using OpenJudge SimpleRubricsGenerator, plus a roadmap to reach calibrated evaluation.

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 has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline 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。

When the user needs a comprehensive marketing plan for a client, a company they advise, or their own product. Also use when the user mentions "marketing plan," "growth plan," "GTM plan," "go-to-market plan," "AARRR plan," "90-day marketing plan," "12-month marketing roadmap," "fractional CMO plan," or "fCMO plan." Generates an exhaustive 13-section plan structured by AARRR (Acquisition, Activation, Retention, Referral, Revenue), customized to the client's current budget, team, and stage, mapped to future funding milestones, cross-referenced with the 139-idea marketing-ideas library and an embedded 17-section current-state audit rubric, with a full marketing operations stack showing which skills and MCP/API integrations execute each part. Outputs a Notion-paste-ready markdown document. For positioning and ICP context before planning, see product-marketing. For stage-specific deep work, see onboarding, signup, emails, referrals, pricing.

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。

Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long 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。

Dung khi can danh gia CON NGUOI trong team marketing dua tren du lieu — KPI scorecard theo tung vai tro writer, designer, media buyer; diem manh co vi du that; diem can cai thien; development plan 30-90 ngay; rubric cham 1-5. Kich hoat khi user nhac 'danh gia nhan vien', 'performance review', 'review nhan su', '1:1 review thang', 'nguoi nay lam duoc khong', 'co nen tang luong khong', 'feedback cho team member'. Khong dung cho — tong ket mot campaign thay vi con nguoi thi dung skill 63-campaign-retrospective; duyet chat luong mot output cu the thi dung skill 62-marketing-review; giao viec va dat deadline thi dung skill 64-team-brief.

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 leader evaluates a marketing TEAM MEMBER using data — a KPI scorecard by role, strengths with real examples, areas to improve stated as observable behavior, a 30 and 90 day development plan, and a 1-5 rating rubric. Trigger on 'performance review for my marketer', 'evaluate a team member', 'monthly 1:1 review', 'feedback for my content writer', 'development plan for an employee', 'is this person underperforming'. Also use when the user is unhappy with someone and cannot articulate why. Not for — evaluating a campaign rather than a person, see `63-campaign-retrospective-global`; reviewing one piece of output, see `62-marketing-review-global`; scoring an external vendor, see `67-agency-vendor-brief-global`.

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。

Compile a repository's instruction files (AGENTS.md, CLAUDE.md and friends) into an Abide rubric, then validate and calibrate it.

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。

Creates a lesson plan, student-facing materials, and observation template. Load this skill BEFORE asking the teacher any clarifying question about grade, subject, topic, standard, or timing. Use when a K-12 teacher needs a math, ELA, science, or social studies lesson built from scratch — even if grade, subject, or topic isn't yet stated. Do NOT load for grading, a rubric, assessment feedback, a quiz, or a standards lookup — answer those directly. Triggers on explicit requests (lesson plan, mini-lesson, unit plan, daily plan) and implicit teacher intent: "I'm teaching long division to 5th graders," "need to teach photosynthesis tomorrow." Core signal: teacher needs new instructional content created. A new lesson that asks for differentiated, tiered, or leveled materials is still ONE planning request — this skill produces those materials inside the lesson package; do not also invoke k12-lesson-differentiation. Not for differentiating an existing lesson (use k12-lesson-differentiation) or passage rewrites.

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。

Adapts an existing K-12 lesson (math, ELA, science, or social studies) for students at different proficiency levels (below / at / above grade level). Load this skill BEFORE asking the teacher any clarifying question about the lesson, tiers, or student levels. Triggers on explicit asks to differentiate, tier, or scaffold a lesson, and on implicit signals like "my students are at different levels". Produces 1 teacher-facing differentiation plan + 3 student-ready tier documents as editable Word documents in a single output turn, rendered from one material-source JSON via bundled scripts (shared content is written once so tiers cannot drift). Uses the Learning Commons Knowledge Graph when connected; works without it. This skill adapts a lesson the teacher brings or names. Not for creating a new lesson from scratch — a new-lesson request that asks for differentiated or leveled materials is k12-lesson-plan-creation's job, one package. Not for grading, rubrics, assessment feedback, or quizzes.

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。

Helps a teacher prepare to teach an existing K-12 lesson (math / ELA / science / social studies) — a prep partner that thinks through the lesson's key student task with the teacher and leaves a short teacher-only prep note. Triggers on asks to internalize, prepare for, get ready to teach, or understand a lesson, including implicit ones ("help me get ready for tomorrow's lesson"), and right after another skill built a lesson, which it can follow. Not for building or adapting a lesson, grading, rubrics, assessment feedback, or generating quizzes or student-facing material, and not for single-fact lookups a sentence would answer ("what standard is this?", "how long is this lesson?").

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。

Make 100 versions of Claude fight to the death over one task. Spins up N sub-agents (default 100, --quick for 16), gives every one the exact same task plus a different strategy card (reasoning mode, workflow, strategy), then runs a single-elimination bracket: they attack each other's solutions, defend and revise, and a judge scores every match on a written rubric until one solution survives. Use when the user is not satisfied with an answer, calls it a bad answer, says try again or do better, says "arena", or asks to make them compete.

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 and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or when the codebase has changed enough that the rules file may be stale. Scans the repository for every rules file, grades each against a quality rubric, outputs a quality report, and applies targeted edits only after user approval.

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。

Create distinctive, production-grade frontend interfaces with high design quality and accessible markup. Use this skill when the user asks to build or beautify web components, pages, applications, landing pages, dashboards, artifacts, or React/HTML/CSS UI. Generates creative, polished code that avoids generic AI aesthetics, then self-checks it against an objective accessibility and quality rubric.

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 `paper-review` has claims plus evidence gaps and needs the final referee-style report.

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。

Scaffolds eval.yaml evaluation specs for skills, custom agents, and redistributable gh-aw workflow packages in the dotnet/skills repository. Use when creating skill or workflow-package tests, writing evaluation stimuli, defining graders and rubrics, sizing an eval for statistical power, or setting up test fixture files. Handles the Vally eval.yaml schema, fixture organization, and overfitting avoidance. Do not use for running or debugging existing evals (use improve-skill-quality) nor for skills authoring (use create-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。

Produce a high-confidence, CONCISE implementation / architecture / strategy PLAN that follows the OMC plan system end to end. It first runs OMC's real requirements interview (auto-chains the `omc-plan` skill: one question at a time, explore-first, Analyst consult) to produce an initial plan in `.omc/plans/`, then DEEPENS that plan with a 3-round ITERATIVE fusion loop — each round an Opus 4.8 panelist (Agent subagent) and a GPT-5.5 panelist (via codex) critique/improve it IN PARALLEL and BLIND, then Opus 4.8 (the orchestrator) judges and synthesizes one tighter plan that seeds the next round, stopping early on convergence. Writes the final dense plan back to the same `.omc/plans/<slug>.md`, then offers the OMC handoff (`/omc-plan --review` → `/team` or `/ralph`). Use for high-stakes planning, architecture decisions, strategy calls, and hard debugging — especially when the user runs /plan or asks how to approach a non-trivial build. Reuses the `fusion` skill's run_codex.sh + judge rubric. NOT for trivial tasks (single pass is enough).

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。

按常见评分点生成建模论文结构与写作清单，并根据题目类型与数据条件给出模型选择与对照实验路线。Invoke when需要“论文格式/评分对齐/模型选型/路线不确定”。

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。

Decomposed, multi-criteria metric design for LLM pipelines. The metric IS the model — change the metric and the optimizer changes behavior. Decompose by default; bool during compile, float during eval; calibrate against human; mitigate judge bias. Search keywords: LLM-as-judge, llm as judge, eval metric, evaluation score, scoring function, rubric, RAGAS, G-Eval, judge bias, verbosity bias, how to evaluate LLM output.

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。

Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does arithmetic/parsing/data transforms, when prose reasoning hallucinates a computation (under-coding), or when a sandbox round- trip is wasted on a judgment task (over-coding). Search keywords: code interpreter, agent does math wrong, calculator hallucination, when to run code vs reason, program of thought, PoT, tool vs reasoning.

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。

ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. The local `dspy` skill lists the modules but never surfaces the *selection criterion*: reasoning shape is chosen by task structure, not by reflexively defaulting to CoT. Activate every time a new LM-calling node/step is added to a pipeline. Do NOT activate for one-shot prompts, optimizer/teleprompter choice (that is the dspy SOP's job), or non-LM control flow. Search keywords: chain of thought vs ReAct, when to use CoT, reasoning type, ReAct vs CoT vs PoT, which dspy module, predict vs chain of thought.

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。

Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.

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。

Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a real project usually combines DSPy (compile) + LlamaIndex (retrieve) + LangGraph (orchestrate) + vLLM (serve), and you choose ONE per layer, not one to rule all. Use when starting any LLM/agent/RAG project, or whenever the "which framework?" question is asked. Deliberately neutral — unlike vendor docs and the LangChain-biased `framework-selection` on skill.sh, this skill has no horse in the race.

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。

Decision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dspy]] library skill: it does NOT teach DSPy syntax — it answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a `dspy.Signature`, and how do I name/describe its fields so the optimizer and the calling code both get a clean contract." Activate when: a prompt string grows past ~50 lines; the LM output is consumed by code (parsed, branched on, stored) rather than read by a human; the same prompt is reused across >1 call site; or a teammate asks "should this be a Signature?". Do NOT activate for one-shot throwaway prompts, or for HOW-TO questions about DSPy modules /optimizers/compile — defer those to the [[dspy]] skill and the [[agentsop-dspy]] workflow skill. Search keywords: typed prompt, structured prompt, DSPy Signature, prompt as a function, prompt contract, when to formalize a 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。

Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run inference, or when cost / data-residency pressure forces a re-evaluation.

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。