全部能力

Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking,…

Load automatically when planning, researching, or implementing ANY Medusa backend features (custom modules, API routes, workflows, data models, module links,…

Analyzes current or recent session for errors, inefficiencies, and improvement opportunities across skills, tools, hooks, and communication. Use after…

Retrieve the full catalog of tradable commodities across energy, metals, and agriculture using Octagon MCP. Use when researching commodity markets, identifying…

Track and analyze Amazon keyword rankings. Set up rank monitoring workflows, interpret ranking changes, and develop strategies to improve organic search…

Provides expertise on Chroma vector database integration for semantic search applications. Use when the user asks about vector search, embeddings, Chroma,…

Evidence-based health research using tiered trusted sources with GRADE-inspired evidence ratings. Integrates Apple Health data for personalized context. Use…

Publish or refresh developer-facing API documentation for REST, GraphQL, webhook, SDK, and developer-portal surfaces: reference docs, quickstarts, task guides, auth/setup notes for API consumers, truthful example requests, error/retry/limit guidance, and migration updates. Use when the contract already exists and the main job is helping integrators succeed with the API, not designing resources or versioning strategy. Triggers on: API docs, developer portal, OpenAPI reference, SDK docs, webhook docs, quickstart, integration guide, endpoint reference, pagination docs, rate-limit docs, migration note, and partner API guide. Route contract design to `api-design`, internal specs/runbooks to `technical-writing`, end-user UI help to `user-guide-writing`, auth implementation to `authentication-setup`, and release-note hygiene to `changelog-maintenance`.

Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other…

Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent…

Write comprehensive widget and integration tests using pattern-based testing (Golden Variants, State Matrix, Interaction Contracts). Use when testing UI…

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or…

Build real deck artifacts when the user needs editable slides, not just prose: investor decks, roadmap/QBR decks, launch decks, architecture/demo decks, workshop/training decks, and game pitch or milestone decks. Use when the job is to choose one deck mode, one smallest useful artifact packet, and one honest handoff surface (HTML review, PPTX, PDF, Google Slides, or Figma Slides). Triggers on: presentation, slide deck, slides, pitch deck, roadmap deck, investor deck, launch deck, architecture review deck, demo deck, workshop slides, keynote, board deck, QBR deck, and game pitch deck. Route long-form docs to `technical-writing`, end-user tutorials to `user-guide-writing`, research manuscripts to `research-paper-writing`, and broad marketing planning to `marketing-automation`.

Organize messy conference LaTeX template .zip files into clean Overleaf-ready structure. Use when the user asks to "organize LaTeX template", "clean up .zip…

Decide when repeating a full prompt is a useful accuracy hack for non-reasoning or lightweight LLM tasks, and when the real fix is better prompt structure, retrieval, or a stronger model. Use when the user has long-context retrieval, options-first multiple choice, or position-sensitive prompts on models like Haiku, Flash, or mini variants — even if they ask in domain language like the model missed the instruction at the end, forgot the question after a long context block, or keeps failing inventory/index lookups. Do not use as a universal prompt-engineering default for reasoning-heavy, tool-heavy, or RAG architecture problems.

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis,…

Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and…

This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster",…

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature…

Download PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`. **Trigger**: PDF download, fulltext, extract text, papers/pdfs, 全文抽取, 下载PDF. **Use when**: `queries.md` 设置 `evidence_mode: fulltext`（或你明确需要全文证据）并希望为 paper notes/claims 提供更强 evidence。 **Skip if**: `evidence_mode: abstract`（默认）；或你不希望进行下载/抽取（成本/权限/时间）。 **Network**: fulltext 下载通常需要网络（除非你手工提供 PDF 缓存在 `papers/pdfs/`）。 **Guardrail**: 缓存下载到 `papers/pdfs/`；默认不覆盖已有抽取文本（除非显式要求重抽）。