Top Agent Skills

Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already produced candidates that must be scored or reranked; use context-retrieval when the source corpus still needs to be searched.

Design and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.

Manage Git repositories and collaborative workflows — branching strategies, commit hygiene, conflict resolution, pull requests, hooks, and .gitignore management. Use when the user requests version control or provides relevant inputs for this workflow.

Verify the accuracy of claims and statements by extracting individual assertions, identifying authoritative sources, cross-referencing evidence, and assigning confidence-scored verdicts. Use when the user requests fact checking or provides relevant inputs for this workflow.

Summarize text using extractive, abstractive, hierarchical, and multi-document techniques, producing concise outputs at configurable detail levels. Use when the user requests summarization or provides relevant inputs for this workflow.

Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.

Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. Use when relevant context has already been selected and must be inserted safely; use context-retrieval to find it or context-optimization to choose and order it.

Retrieve relevant information from a knowledge base using semantic, keyword, or hybrid search to ground a query. Use when the task starts with a corpus or index that must be searched; use context-ranking when candidate chunks already exist and only need ordering.

Create clear, effective charts and dashboards from structured data using matplotlib, seaborn, and plotly. Use when the user requests data visualization or provides relevant inputs for this workflow.

Capture, organize, and retrieve notes efficiently using structured formats, tagging, and file management for meetings, ideas, research, and daily logs. Use when the user requests note taking or provides relevant inputs for this workflow.

Build sales battlecards with feature comparisons, objection handling scripts, positioning statements, and win themes for competitive deal scenarios. Use when the user requests competitive battlecard creation or provides relevant inputs for this workflow.

Write high-quality, SEO-optimized blog posts in multiple formats including how-to guides, listicles, opinion pieces, and case studies, with structured outlines, hooks, and calls-to-action. Use when the user requests blog post writing or provides relevant inputs for this workflow.

Design GraphQL APIs with well-structured schemas, efficient resolvers, pagination, and performance patterns like DataLoader and federation. Use when the user requests graphql api design or provides relevant inputs for this workflow.

Audit web interfaces against WCAG 2.1 AA/AAA standards, identify violations, and produce actionable remediation reports with code fixes. Use when the user requests accessibility testing or provides relevant inputs for this workflow.

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.

Automatically generate clear, comprehensive documentation for codebases — including API references, inline docstrings, README files, and usage guides. Use when the user requests code documentation or provides relevant inputs for this workflow.

Compress selected context to a target token budget while preserving decisions, evidence, constraints, and unresolved questions. Use when relevant material is already selected but too long; use context-optimization when selection, deduplication, and ordering are also required.

Inspect, profile, clean, reconcile, analyze, visualize, and verify spreadsheet data while preserving formulas, formatting, types, and source files. Use when working with .xlsx, .xlsm, .xls, .ods, .csv, or .tsv files; answering questions from a workbook; auditing formulas or data quality; comparing sheets or versions; producing pivots, charts, forecasts, or summary workbooks; repairing malformed tables; or validating that spreadsheet edits and calculations are accurate.

Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency, high-risk controls, general-purpose AI obligations, governance, and implementation milestones. Use when an organization needs to triage an AI use case, vendor, model, product, or portfolio for Regulation (EU) 2024/1689; prepare an AI inventory, gap register, implementation roadmap, or counsel briefing; assess provider, deployer, importer, distributor, product-manufacturer, authorised-representative, or GPAI-provider responsibilities; or re-check readiness after regulatory or product changes.

Conduct a structured literature review on a given topic by defining a search strategy, applying inclusion and exclusion criteria, extracting key findings, and synthesizing results into a coherent academic review. Use when the user requests literature review or provides relevant inputs for this workflow.

Extract, validate, and categorize invoice data against purchase orders and GL codes. Use when the user requests invoice processing or provides relevant inputs for this workflow.

Automate repetitive tasks and workflows using scripting, file watchers, scheduled jobs, CI triggers, and API polling to eliminate manual toil. Use when the user requests task automation or provides relevant inputs for this workflow.

Monitor cloud infrastructure and applications using metrics, logs, and traces to provide real-time observability into performance, health, and reliability. Use when the user requests cloud monitoring or provides relevant inputs for this workflow.

Automatically organizes files in a directory into a clean structure based on configurable rules — by file type, date, project, or priority — with support for duplicate detection, naming conventions, and archival strategies. Use when the user requests file organization or provides relevant inputs for this workflow.

Schedules meetings with internal and external stakeholders by parsing natural language requests, resolving time zones, checking calendar availability, proposing optimal slots, and managing invitations and RSVPs. Use when the user requests meeting scheduler or provides relevant inputs for this workflow.

Perform systematic exploratory data analysis to understand dataset structure, distributions, relationships, and anomalies before modeling. Use when a dataset is new, its quality is unknown, or the user requests open-ended profiling; use data-analysis instead for a defined hypothesis or decision question.

Analyze source code for security vulnerabilities using static analysis tools, custom rules, and CI-integrated scanning pipelines. Use when the user requests static application security testing or provides relevant inputs for this workflow.

Design structured customer onboarding workflows with phased checklists, email templates, success milestones, and ownership assignments. Use when the user requests onboarding playbook creation or provides relevant inputs for this workflow.

Classify expenses by category, department, and tax deductibility from transaction data. Use when the user requests expense categorization or provides relevant inputs for this workflow.

Write clear, searchable help center articles and FAQ entries based on support data, product documentation, and common customer questions. Use when the user requests knowledge base article writing or provides relevant inputs for this workflow.

Deploy, manage, and scale applications on Kubernetes clusters using manifests, Helm charts, and autoscaling configurations. Use when the user requests kubernetes deployment or provides relevant inputs for this workflow.

Build structured knowledge graphs from unstructured text by extracting entities, mapping relationships, generating graph triples, and visualizing the result. Use when the user requests knowledge graph creation or provides relevant inputs for this workflow.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

对 wiki 提问，综合检索相关页面后回答，好的回答可 crystallize 回 wiki

扫描全 wiki 发现健康问题，生成修复建议报告（覆盖全 9 种 entity + graph 一致性）

按 scope 重置 wiki 到干净 scaffold（wiki / raw / log / checkpoints / all）。适用于开发迭代或 setup 失败后的无痛重启。

交互式 API key 配置引导 — 检测当前 .env 状态，逐步引导配置 Semantic Scholar、DeepXiv 和 Review LLM

通用多轮迭代改进：对任意研究制品反复调用 /review → 解析反馈 → 修复 → 更新 wiki，直到达标

通用跨模型审查：Review LLM 对任意研究制品进行独立评审，输出结构化评分、wiki 实体映射与改进建议

从 wiki 知识生成论文 Related Work 章节：主题分组 → 叙事结构 → LaTeX 输出，遵循 citation-verification 和 academic-writing

用领域基础知识填充 wiki/foundations/，避免后续 /ingest 为教科书材料创建重复的 concept 页面

基于 anchor 论文、topic 关键词或当前 wiki 状态，产出一份排好序的候选论文 shortlist，供用户或上游 skill 决定是否进一步 `/ingest`。当用户问 "接下来该读什么"、"找和这篇相似的论文"、"推荐相关工作"、"这个方向周围有什么" 时触发；`/ingest --discover` 也会内部调用本 skill。本身不 ingest，只提出候选。

实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

Claim-driven 实验设计：界定目标 claims → 设计实验块（baseline/validation/ablation/robustness）→ 构建执行顺序 → 可选 Review LLM review → 写入 wiki

查看所有运行中实验的状态，可选自动收集已完成实验并推进流水线

从 claim graph 编译论文大纲：编译 evidence map → 叙事结构 → 章节计划 + figure plan + citation plan，Review LLM review 必选

从 PAPER_PLAN 起草 LaTeX 论文：逐 section 从 wiki 取材撰写 + 生成 figures/tables + BibTeX 验证 + de-AI polish

汇总某个经管实证变量在文献中的测算口径、数据来源、模型角色和项目可用性

LaTeX 编译 → PDF：latexmk 编译 + 自动修复 + 页数/匿名/字体/[UNCONFIRMED] 检查 + 提交清单

将一篇经管实证论文摄取为实证研究 wiki：论文卡片 + 变量 + 数据 + 模型 + 机制 + 识别 + 稳健性 + 异质性 + 表格线索

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Managing dependencies, CI/CD optimization, Docker configuration, and operational observability (logging/alerting/health checks). Use for build errors or dev environment issues.

Curating cross-agent knowledge and institutional memory: extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices. Use for memory curation.

Enumerating failure modes via pre-mortem analysis. Systematically identifies failure scenarios for plans, designs, and features, scoring them with RPN/AP. Does not write code.

Converting repository changes into detailed learning documents. Use when turning diffs into teaching materials, recording design decisions, or creating onboarding materials for new members.

Game audio generation agent. Produces code (Python/JS/TS/Shell) for SFX, BGM, Voice, Ambient, and UI sounds using ElevenLabs/Stable Audio/MusicGen/Suno/OpenAI TTS/JSFXR. Handles LUFS normalization and middleware integration.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Search arXiv papers by keyword, author, category, or ID.

Engineering privacy and data governance: PII detection, data flow mapping, consent patterns, GDPR/CCPA-compliant implementation, DPIA. Use when privacy-by-design is needed.