3,440 件 ・ 関連度順
概要と使いどころ
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。
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。
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。
Cross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubric — is single-agent + tools enough? do agents need to know about each other? does the output need one voice? — maps the answer to single-agent / supervisor / swarm / sequential / hierarchical. Activates when a coder agent is tempted to "split the work into roles" or reaches for a multi-agent framework. Encodes the *selection rubric* that the per-framework skills assume but never surface. Search keywords: when to use multi-agent, single vs multi agent, do I need multiple agents, supervisor vs swarm, multi-agent vs single agent, agent team design.
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。
Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-set version, versioned together so a deploy is reproducible and rollback is atomic. Activate when preparing to deploy an LLM app, when asking "what exactly is running in prod right now?", when a deploy must be reproducible months later, or when an incident needs a clean rollback. The core reframe: an LLM app artifact is NOT an ML model — it is a manifest over many independently-mutable parts, not one weights file. Do NOT activate for one-off prompt edits with no deploy, for a single-component demo, or where a vendor owns the whole prompt lifecycle. For versioning ONE compiled prompt use [[agentsop-per-model-artifacts]]; for the CI comparison mechanism use [[agentsop-regression-gate]]. Search keywords: prompt versioning, reproducible deploy, what is running in prod, rollback LLM app, model pinning, prompt registry, version prompts and config.
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。
Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edit", delegate breadth to a read-only repo-map, and drop files once edited. Use when an LLM coder-agent edits multiple files, when the working set must stay focused, or when the model starts editing the wrong file / missing targets because too much context dilutes attention. Search keywords: context window full, agent edits wrong file, too much context, /add /drop files, working file budget, context dilution, lost in the middle.
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。
A 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace into Greenfield / Brownfield-large / Mid-size-familiar / Library-SDK, then maps the state to an agent strategy (autonomy, context primitive, tool choice). Use BEFORE picking Cursor vs Claude Code vs Aider, BEFORE turning on repo-map, BEFORE writing the first prompt. Skip only if the same repo was gated within the last day and nothing changed. Search keywords: greenfield vs brownfield, new project vs existing codebase, project setup strategy, legacy codebase agent, where to start a coding agent.
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 protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise the second call is safe. Framework-agnostic — applies to LangGraph node bodies that re-run on resume, MCP tools, OpenAI tool-calling retries, CrewAI delegated tool invocations, and direct HTTP wrappers. Search keywords: duplicate email sent, charged twice, exactly-once, idempotency key, tool called twice, retry side effect, double-send, at-least-once delivery.
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。
Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an explicit counter + exit predicate + stagnation signal + escalation path that live OUTSIDE the LM's control. This is a tool- level, framework-agnostic skill. It maps onto LangGraph (recursion_limit + state counter + interrupt), CrewAI (max_iter + max_rpm + human_input), Claude / OpenAI SDKs (max_iterations + tool_use_budget), DSPy (declared evaluation budget), Aider (REPL + explicit retry cap), and AutoGen (max_consecutive_auto_reply). Search keywords: infinite loop, recursion limit, recursion_limit, GraphRecursionError, max iterations, max_iter, agent stuck, agent won't stop, runaway agent, ReAct loop not terminating, agent repeating itself.
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。
Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset, or framework version changes. Activate when adopting compiled prompts (DSPy, GEPA, BootstrapFewShot output), when supporting multiple LMs in production, when a provider deprecates a model snapshot, or when a framework deprecates a config surface (LlamaIndex `ServiceContext` → `Settings`, Aider edit-format defaults). Do NOT activate for one-off raw prompt edits or for truly model-agnostic system prompts that have been swap-tested. Search keywords: prompt portability, model swap, recompile prompt, model deprecation, prompt per model, prompt breaks on new model, version compiled 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。
Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor, DSPy optimizer-LM vs task-LM, vLLM speculative draft+target, LangGraph supervisor+worker are the same shape). Use when designing or cost-optimizing a pipeline that calls an LM many times, when deciding which steps need a strong reasoner vs a cheap executor, or when adding an escalation valve for when the cheap tier degrades. Search keywords: reduce LLM cost, cheaper model, lower token cost, model cascade, route to cheap model, strong model plus cheap model, LLM cost optimization.
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。
Translate a complete mathematical modeling contest problem sentence by sentence into precise modeling language, preserve every substantive condition and definition, expose hidden constraints, draw a mandatory Mermaid cross-question flowchart, audit omissions, and deliver one easy-to-open Markdown report. For Huawei Cup (CPGMCM) graduate-contest problems, additionally prepend a plain-language layer that rewrites the background and questions as a primary-school word problem with a mandatory term-mapping table. Optionally render the finished report as one standalone HTML page on request. Use whenever a user supplies a CUMCM, CPGMCM, or other modeling problem and asks to interpret, translate, unpack, read closely, identify requirements, or avoid missing details before modeling.
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 complete mathematical-modeling competition paper with an atomic checklist covering abstract readability, page structure, typography, headings, pagination, figures, tables, equations, anonymity, metadata, visual balance, and page allocation. Return the review in chat or Markdown by default, and provide the bundled single-sheet checklist when the user requests a reusable form. Use when the user provides a PDF or Word paper and asks for a full-paper format and writing-compliance audit; do not replace technical model correctness 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。
数学建模竞赛论文写作全流程指导。覆盖国赛(CUMCM)和美赛(MCM/ICM)，从论文结构规划、各章节撰写、模型检验、参考文献规范到最终格式检查。与math-modeling-solver形成"解题→写作"配对——可接收solver输出的论文草稿片段直接展开写作。当用户提及数学建模论文写作、建模比赛、国赛/美赛/电工杯/亚太杯/深圳杯/华为杯论文、CUMCM、MCM/ICM、数模论文结构、摘要写作、模型检验、灵敏度分析、latex建模模板、word建模排版、Memo/Letter写作、模型命名、Our Work流程图，或需要写/修改/优化/检查建模论文的任何部分时，都必须使用此 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。
Find leaked secrets in source code, Git history, build artifacts, and infrastructure — and audit the secrets-management posture preventing future leaks. Use when the user mentions 'secrets audit,' 'secret scanning,' 'leaked credentials,' 'API key in code,' 'gitleaks,' 'trufflehog,' 'git history scan,' 'secrets management,' 'vault audit,' 'rotation policy,' 'AWS Secrets Manager,' 'HashiCorp Vault,' 'Doppler,' '1Password Secrets Automation,' 'sealed-secrets,' 'External Secrets Operator,' or needs to find or prevent credential exposure.
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。
Secure authentication patterns (OWASP, NIST). Use for login, registration, password reset, sessions, JWT, OAuth, MFA, passkeys.
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。
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
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。
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
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。
Implement authentication and authorization with Better Auth - a framework-agnostic TypeScript authentication framework. Features include email/password authentication with verification, OAuth providers (Google, GitHub, Discord, etc.), two-factor authentication (TOTP, SMS), passkeys/WebAuthn support, session management, role-based access control (RBAC), rate limiting, and database adapters. Use when adding authentication to applications, implementing OAuth flows, setting up 2FA/MFA, managing user sessions, configuring authorization rules, or building secure authentication systems for web applications.
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 style-driven slide images strictly with the Image 2 model, assemble those images into image-only PPTX decks, and manage reusable visual style libraries from documents or visual references. Use when the user asks for a "PPT Skill", "风格驱动 PPT", "提炼风格做 PPT", "调用某个风格做 PPT", "图片版 PPT", "保存 PPT 风格", "列出 PPT 风格", "文档生成 PPT", "文章生成 PPT", "把文档做成演示文稿", or wants to extract, save, reuse, and apply visual style keywords specifically for visual slide/image deck 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。
Polish, translate, diagnose, and restructure technical manuscript text into IEEE-style academic English using routed failure-mode guidance. Use for IEEE abstracts, introductions, related work, methods, experiments, conclusions, figure captions, rebuttals, Chinese-to-English technical writing, AI-like or template-like academic prose, and engineering prose that needs clearer problem logic, contribution framing, method rationale, evidence discipline, natural author voice, or reviewer-ready wording.
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 building HTML email templates with React components, adding a visual email editor to an application using the React Email visual editor, rendering emails to HTML, or sending emails with Resend. Covers welcome emails, password resets, notifications, order confirmations, newsletters, transactional emails, and the embeddable email editor component.
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。
Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
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。