Каталог навыков агентов

掌握高级提示工程技术，以最大化生产环境中LLM的性能、可靠性和可控性。在优化提示、改进LLM输出或设计生产提示模板时使用。

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in productio...

Use the following context to answer the question.

Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when...

Transform vague prompts into actionable specs using intelligent analysis and session memory. Use when user input contain...

Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve st...

Phase 0.2 — Enriches the raw user prompt with discovered constraints, ambiguities, likely edge cases, and suggested scop...

Execute the forged prompt exactly as written. Requires explicit consent and a ready artifact. Deletes artifact after suc...

World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through inte...

Shape, refine, and stabilize human intent into a canonical prompt artifact. Iteratively clarifies ambiguity until user c...

You are a coding standards expert specializing in prompt generation rules.

Generate or convert Claude Code prompt files — command orchestrators, skill files, agent role definitions, or style conv...

Generate optimized Claude Code prompts for any request. This is the main entry point for the prompt generation system. U...

Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt regi...

Transform vague prompts into rich, structured prompts with automatic fallback

Optimize prompts for code-related tasks following Claude best practices. Use when refining prompts for implementation, d...

Optimize prompts for better AI responses. Use when user asks to improve a prompt, refine a prompt, make a prompt better,...

Contain direct and indirect prompt injection in LLM-integrated applications. Covers source-of-trust tagging, tool-use co...

Use when iteratively improving agent prompts through automated LLM-as-Judge evaluation. Runs eval→fix→commit loop with c...

Iterate on LLM prompts with structured evaluation and self-correction. Test prompts against ground truth, compare models...

Guide selection of appropriate prompt level for a task. Use when choosing between simple prompts and complex workflows,...

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates,...

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates,...

Library of 18+ ready-to-use prompt templates and executable agents

Build a personal library of reusable prompts for the things you ask AI again and again — so you stop rewriting the same...

คลัง prompts แบบ minimal ที่ใช้ token น้อยที่สุดแต่ได้ผลลัพธ์ดี พร้อม templates และ best practices

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts....

Centralized prompt management for LLM operations. All prompts in lib/prompts/ as named exports. Multi-level extraction,...

Use when a prompt needs writing or improving for an AI tool — clarifying the task, adding structure and constraints, sup...

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt...

Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor,...

提示词主控 - 智能选择合适的领域skill并生成提示词，支持自动领域分类和调度

Analyze and improve existing prompts for better performance

Improve and rewrite user prompts to reduce ambiguity and improve LLM output quality. Use when a user asks to optimize, r...

This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for A...

A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.

Use when a draft prompt, instruction set, or agent skill description needs refinement, clarity, or improved performance.

撰写提示词、优化提示词、改写 Prompt、Prompt 优化。Use when: 用户需要创建或修改可执行提示词；按任务、调用方输出契约与实际工具能力优化，不按模型品牌强制格式。

Prompt quality auditor: audit every prompt for clarity, safety, and injection resistance. Read-only. Trigger: /prompt-qu...

Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use...

Reviews a prompt/instruction file against Anthropic prompt engineering best practices. Use when evaluating skill files,...

.github/prompts/*.prompt.md をレビューして改善提案を出す。frontmatterの妥当性、入力変数(${input:...})の設計、出力フォーマット固定、instructions/skillsへの参照（重複排除...

Route a classified request to the right skills, agent strategy, Context7 directives, and output format. Use this skill w...

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about pr...

Design reusable prompt templates that encode domain-specific patterns for recurring AI tasks. Use when you've executed s...

Reusable prompt templates for construction AI tasks: cost estimation, schedule analysis, document processing, BIM querie...

A/B testing and performance metrics for prompts

把一条 AI 视频提示词从源模型(如 Sora 2)的写法风格转换为目标模型(如 Kling 3.0 / Wan 2.7 / Veo 3.1 等)的最佳实践写法。基于 110 条 10 场景 × 11 模型对照基准数据(prompts/da...

Improve embedded LLM system prompt based on evaluation test failures

Guidance for working on the language model prompts that power the Mossback support assistant and the document summariser...

プロンプトのライフサイクル管理を専門とするスキル。バージョン管理、デプロイ戦略、ロールバック、変更追跡により、本番環境で安全かつ効率的なプロンプト運用を実現します。 Anchors: • The Pragmatic Programmer...

Promptfoo evaluation framework for testing and comparing LLM outputs. Use when writing eval configs, creating test cases...

PROACTIVE: This skill SHOULD BE USED AUTOMATICALLY when writing prompts, system prompts, crafting instructions for LLMs,...

Meta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, t...

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers...

Prompting-Leitfaden für juristische KI-Nutzung in Kanzleien: Anwendungsfall Anwalt oder Mitarbeitende wollen KI effektiv...

Simulate the execution of Prompton, a Python-like language where `prompt'...'` expressions evaluate to the result of the...

skills/**/SKILL.md 内に embed された 5 行以上のエージェント呼出プロンプトテンプレ・長文ブロックを .claude/rules/notification-prompt-extraction.md 基準で skil...

Sussman/Radul propagator networks for constraint propagation and bidirectional

Build agency proposal workflows for scopes, offers, pricing narratives, and next-step packaging. Use when the user needs...

For each gap a drive's search could not close and only the person can confirm — who may decide, how we will know it work...

Propose improvements or new components for Product Forge

Propose additions to project CLAUDE.md based on session learnings

Structure a decision into steelmanned, impact-weighted pros and cons - irreversible consequences flagged, the decisive u...

Core writing craft skill — sentence-level quality, rhythm, voice, show-don't-tell, sensory detail, pacing, and line-leve...

---name: protac-design-agent

---name: protein-structure-prediction

End-to-end guidance for protein design pipelines. Use this skill when: (1) Starting a new protein design project, (2) Ne...

Protein grouping and inference from peptide identifications. Use when resolving protein ambiguity from shared peptides....

Protein (gene) phylogeny inference pipeline: generates a .qmd analysis script that performs alignment, optional trimming...

Quality control metrics and filtering thresholds for protein design. Use this skill when: (1) Evaluating design quality...

Generate PyMOL scripts to highlight specific protein residues in PDB structures. Use this skill when the user needs to v...

Design protein sequences using ProteinMPNN inverse folding. Use this skill when: (1) Designing sequences for RFdiffusion...

K-lines as semantic activation — the name activates the tradition.

AI generation provenance and audit trail tracking. Records decision factors, data lineage, reasoning chains, confidence...

Claude subscription account manager for macOS (Claude Code CLI, Orca, Keychain): account discovery, usage telemetry, one...

Prüfung der Verantwortlichkeit von Diensteanbietern für fremde/nutzergenerierte Inhalte: beschränkte Verantwortlichkeit...

Use when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or...

Prüfung und Antrag auf Prozesskostenhilfe (PKH) – die drei Voraussetzungen Bedürftigkeit, hinreichende Erfolgsaussicht u...

---name: prs-net-deep-learning-agent

Checks an AI-enabled public service design for differential impact across community groups before launch: digital divide...

Reframes an AI business case around the four public-value types (efficiency, service quality, equity, trust/legitimacy)...

Frames the distinct regulatory and ethical stakes of public-facing AI - higher transparency and accountability bar, disp...

Performs pseudo-bulk differential gene expression analysis using DESeq2 or edgeR. Aggregates single-cell counts to sampl...

Edit requested prose to remove vague claims, stock AI phrasing, filler, or dense wording while preserving meaning, evide...

心理咨询 / 心理治疗(临床实践者视角 — 接案与评估 / 个案概念化 / 主流流派技术(CBT 与第三浪潮 / 精神动力 / 人本存在 / 家庭系统 / 创伤治疗) / 伦理边界与危机干预 / 督导与个人成长 / 执业形态与经营 — 涵盖...

Use PTS (Pivotal Token Search) to find the tokens, sentences and latent concepts that change whether a language model so...

Καθοδηγεί πτυχιακή ή διπλωματική εργασία Πληροφορικής σε ελληνικό πανεπιστήμιο, από την επιλογή θέματος και το χρονοδιάγ...

Query PubChem, search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for chemin...

Real-time companion monitor for OpenClaw agents

Memory Infrastructure for Autonomous Agents

Collaborate on open source projects with other AI agents via SynStack

Operate an AI agent inside OpenClaw World over HTTP IPC. Use when tasks involve registering or reconnecting an agent, mo...

将本地 ~/.claude/skills/ 中的某个 skill 发布（添加或更新）到 Claude-Code-Skills 公共仓库。当用户说"把 X skill 发布到仓库"、"更新仓库里的 Y skill"时使用。